{"as_of":"2026-08-13T18:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:42411a98866ca54ca319785814ededd3cf361aa397a7aff5bbde75c0691c98cd","coverage":[{"denominator":106,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T22:24:44.303692Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2412.03512/citation-record","integrity":"/paper/2412.03512/integrity","json":"/paper/2412.03512/citation-record.json","paper":"/paper/2412.03512"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2112.05814","last_updated":"2022-10-15T21:18:49Z","snapshot_observed_at":"2026-08-13T17:17:53.614748Z","submitted_at":"2021-12-10T20:15:03Z","title":"Deep ViT Features as Dense Visual Descriptors","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.05814","snapshot_observed_at":"2026-08-11T22:24:43.904338Z","title":"Deep vit features as dense visual descriptors","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:43.904338Z"},"links":{"cited_paper":"/paper/2112.05814","citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:0465ec170f7f68383b41444c1388851bdd18db3af2a9132ae7c9008316223559","observation_id":"be09a5fb-5527-4516-b6a1-5649e8772b4b","resolution":{"observed_at":"2026-08-11T22:24:43.904338Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:43.909714Z","title":"Segdiff: Image segmentation with diffusion proba- bilistic models, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:43.909714Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:e1d97e0dbd7a4266e83eddb450da821efe5d8b439f7df46ed7631d227741131f","observation_id":"7dd3006f-bd6c-4e21-b71c-3bd55a7b6f92","resolution":{"observed_at":"2026-08-11T22:24:43.909714Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:43.913837Z","title":"Parameter efficient fine-tuning of self- supervised vits without catastrophic forgetting, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:43.913837Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:df32a8d10783aad9750fe67ff3fb2bd4f2824289ce5f1e997578f53754fc5d59","observation_id":"c5c61ad1-4f54-4f4e-8755-8110f109fba6","resolution":{"observed_at":"2026-08-11T22:24:43.913837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:43.917985Z","title":"Label-efficient semantic segmentation with diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:43.917985Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:993465e27a972c2736aaac09b2de9fa13215b03a54afb825982e1bc58d793b44","observation_id":"f469bf3a-e1c6-4588-b93e-e961a0a7a112","resolution":{"observed_at":"2026-08-11T22:24:43.917985Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:43.922122Z","title":"Surf: Speeded up robust features","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:43.922122Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:f724afd9757030a59aa4bed21c24bf46d2c12f22fffbca270b3d1bde73aa1518","observation_id":"80f88df1-3662-4a11-878d-88827890609e","resolution":{"observed_at":"2026-08-11T22:24:43.922122Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:43.926057Z","title":"Courville, and Pascal Vincent","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:43.926057Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:0f6436d6acc2559b5e2701743ef5db7cde273621aa15b90c794bb4f2b4c80aaf","observation_id":"43cfa5eb-e0bf-44ec-a28b-86b1d5186341","resolution":{"observed_at":"2026-08-11T22:24:43.926057Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.09673","last_updated":"2024-09-20T21:21:56Z","snapshot_observed_at":"2026-08-13T00:06:55.915196Z","submitted_at":"2024-05-15T19:27:45Z","title":"LoRA Learns Less and Forgets Less","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.09673","snapshot_observed_at":"2026-08-11T22:24:43.930046Z","title":"Cunningham","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:43.930046Z"},"links":{"cited_paper":"/paper/2405.09673","citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:9836bd06d7f181e2aa8f767af6a76d917b9c89c1eb2816f56cd1b81376c324b3","observation_id":"3812dc25-8d98-4a60-84aa-5a169d086f29","resolution":{"observed_at":"2026-08-11T22:24:43.930046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:43.934444Z","title":"Subpixel heatmap regression for facial landmark local- ization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:43.934444Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:dd0f9337919e151ea42ff093f6efed7b2d7546605970cfa8fd152f2ca7e46dc1","observation_id":"1b965d40-f8a7-48f6-9378-42682d9bd1b8","resolution":{"observed_at":"2026-08-11T22:24:43.934444Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:43.938510Z","title":"Diffu- siondet: Diffusion model for object detection","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:43.938510Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:27b3e011b1b56e7c7d5f924c973459d80cf2bde3b4a4813162d72a59f86a1ff2","observation_id":"582d872a-72a3-4932-9490-69c18ddeb079","resolution":{"observed_at":"2026-08-11T22:24:43.938510Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:43.942309Z","title":"Hinton, and David J","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:43.942309Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:7c2a4ee44f48a49b30d5aa59a4f7865a463aa634887d82b26a276ecb722b2fad","observation_id":"73ad56ae-1c8b-4805-857c-94141ad69ae1","resolution":{"observed_at":"2026-08-11T22:24:43.942309Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:43.946103Z","title":"Cats: Cost aggregation transformers for visual correspondence","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:43.946103Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:c835d6b3dcf3d622781b3a4d7d68226e4fc075914b90ef85f895bb943deb85d3","observation_id":"45e4a267-d7b8-42db-b351-f748913e2287","resolution":{"observed_at":"2026-08-11T22:24:43.946103Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.06817","last_updated":"2022-10-30T14:40:46Z","snapshot_observed_at":"2026-08-13T16:41:04.582551Z","submitted_at":"2022-02-14T15:54:58Z","title":"CATs++: Boosting Cost Aggregation with Convolutions and Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.06817","snapshot_observed_at":"2026-08-11T22:24:43.949990Z","title":"Cats++: Boosting cost aggregation with convolutions and transformers","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:43.949990Z"},"links":{"cited_paper":"/paper/2202.06817","citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:0d2f3ad0dbac586a68344c555811c2cb2638080814dfc82d4e539fcaab5eb839","observation_id":"63912e09-4ca4-4980-91eb-3d262ac4ab0b","resolution":{"observed_at":"2026-08-11T22:24:43.949990Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.15779","last_updated":"2023-05-25T06:46:28Z","snapshot_observed_at":"2026-08-13T11:33:46.921422Z","submitted_at":"2023-05-25T06:46:28Z","title":"Custom-Edit: Text-Guided Image Editing with Customized Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.15779","snapshot_observed_at":"2026-08-11T22:24:43.954189Z","title":"Custom-edit: Text-guided image editing with customized diffusion models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:43.954189Z"},"links":{"cited_paper":"/paper/2305.15779","citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:d7cc1116f4fb44fec8ecd70b33d5e3f555f7bde4ea810cbb266005632537506d","observation_id":"d4ee3ce6-ed39-4471-ad1d-49c2767551d4","resolution":{"observed_at":"2026-08-11T22:24:43.954189Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:43.958425Z","title":"Choy, JunYoung Gwak, Silvio Savarese, and Manmohan Krishna Chandraker","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:43.958425Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:f2bd32cf9d91322a3c49ed655c0c28b6451ac96e9abe5624855ad3e4d36b3deb","observation_id":"9fe64cc7-e90f-495c-9d18-8173cce57e5b","resolution":{"observed_at":"2026-08-11T22:24:43.958425Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:43.962308Z","title":"Diffedit: Diffusion-based semantic image editing with mask guidance","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:43.962308Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:8d8fd1bb66823b1ea0531e18b18ec919d81c7cc102e031061b7ffaf7cc671f04","observation_id":"1badf69e-fa84-4fce-9841-0062f6541009","resolution":{"observed_at":"2026-08-11T22:24:43.962308Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.06013","last_updated":"2024-01-12T11:46:25Z","snapshot_observed_at":"2026-08-13T04:44:28.726343Z","submitted_at":"2024-01-11T16:22:42Z","title":"Surgical-DINO: Adapter Learning of Foundation Models for Depth Estimation in Endoscopic Surgery","version":2},"cited_work":{"arxiv_id":"2401.06013","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.06013","snapshot_observed_at":"2026-08-11T22:24:44.691577Z","title":"Surgical-DINO: Adapter Learning of Foundation Models for Depth Estimation in Endoscopic Surgery","venue":"cs.CV","work_id":"55d3ad5a-6795-4ce7-9a90-c81de0ebc9ca","year":2024},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:43.965990Z"},"links":{"cited_paper":"/paper/2401.06013","citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:fa7c7fa6b3c36e3d73a4f49ad5a351b33fb4e5aa80954118e7deb9e772e04060","observation_id":"25731bb4-6bf4-45f4-aa56-c1fbc8bd7c2b","resolution":{"observed_at":"2026-08-11T22:24:44.696313Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:43.970358Z","title":"Diffusion models beat gans on image synthesis","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:43.970358Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:0e4ef43dc4df7697458bf1f4544a0de817fe6408721c1a8accdaba13918c7eb7","observation_id":"2c9899f0-7bfd-42f0-bd5a-5eb71a3dc5a7","resolution":{"observed_at":"2026-08-11T22:24:43.970358Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:43.974275Z","title":"An im- age is worth 16x16 words: Transformers for image recog- nition at scale","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:43.974275Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:ead91dfb2867df03317bd80b1a27be62c41b0e7109ae484e9f5769c58e80e5ca","observation_id":"da03f972-4744-42f8-a390-636f06e5b25a","resolution":{"observed_at":"2026-08-11T22:24:43.974275Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.05021","last_updated":"2023-08-29T05:20:36Z","snapshot_observed_at":"2026-08-13T12:28:39.344752Z","submitted_at":"2023-03-09T03:48:24Z","title":"DiffusionDepth: Diffusion Denoising Approach for Monocular Depth Estimation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.05021","snapshot_observed_at":"2026-08-11T22:24:43.978107Z","title":"Diffusiondepth: Diffusion denoising approach for monocular depth estima- tion","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:43.978107Z"},"links":{"cited_paper":"/paper/2303.05021","citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:58319bb0a3eaed8aed926d9e5bc14f084c797d2c41d93a87a1f786e03b0f48e5","observation_id":"59835a1d-f249-47c1-b970-1751bfc9eacd","resolution":{"observed_at":"2026-08-11T22:24:43.978107Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.00783","last_updated":"2024-06-30T17:59:58Z","snapshot_observed_at":"2026-08-12T23:31:49.158301Z","submitted_at":"2024-06-30T17:59:58Z","title":"Diffusion Models and Representation Learning: A Survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.00783","snapshot_observed_at":"2026-08-11T22:24:43.982128Z","title":"Diffusion models and representation learning: A survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:43.982128Z"},"links":{"cited_paper":"/paper/2407.00783","citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:826a3cc65a97b0513d6c66631e7cd6fdb981acee1275d63656f69316607c1da0","observation_id":"666dd1dd-2b13-4494-ad9f-9eea6f582417","resolution":{"observed_at":"2026-08-11T22:24:43.982128Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.00430","last_updated":"2023-11-01T10:45:07Z","snapshot_observed_at":"2026-08-13T05:35:04.248097Z","submitted_at":"2023-11-01T10:45:07Z","title":"Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.00430","snapshot_observed_at":"2026-08-11T22:24:43.986137Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:43.986137Z"},"links":{"cited_paper":"/paper/2311.00430","citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:1969da0878913f8de79992f8985173d80abc2b14519fa3e777a2ef1b621bbe39","observation_id":"eb5fb8ac-8210-41a8-a5f2-85902c6dde62","resolution":{"observed_at":"2026-08-11T22:24:43.986137Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:43.990134Z","title":"Aiatrack: Attention in attention 9 for transformer visual tracking","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:43.990134Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:adb5c4d60652d06a36226b263b467e48b31b84d2a1eb15385bf99f1388e98b08","observation_id":"75670774-8721-4534-b8c1-dbc8db8406f3","resolution":{"observed_at":"2026-08-11T22:24:43.990134Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:43.993900Z","title":"Do semantic parts emerge in convolutional neural net- works? Int","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:43.993900Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:f04f0ccb7cac46520534d6c2c4a012d5fb8024574b874e4accc93e18837eb095","observation_id":"c3c4a383-81a5-46cb-b5c0-421de29876f0","resolution":{"observed_at":"2026-08-11T22:24:43.993900Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1406.2661","last_updated":"2014-06-10T18:58:17Z","snapshot_observed_at":"2026-07-06T03:46:00.791740Z","submitted_at":"2014-06-10T18:58:17Z","title":"Generative Adversarial Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1406.2661","snapshot_observed_at":"2026-08-11T22:24:43.997618Z","title":"Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron C","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:43.997618Z"},"links":{"cited_paper":"/paper/1406.2661","citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:90acc26bbb33c719ea550a5a5f6e18acdb9b30e60b345ed71654fc3eee933822","observation_id":"b1fc8274-df9f-44e8-8972-e2f5e7dabf25","resolution":{"observed_at":"2026-08-11T22:24:43.997618Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:44.001927Z","title":"Bootstrap your own latent-a new approach to self-supervised learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.001927Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:1cae7aeb95d49e636b984a55f8ca6c00f6a97929b02ae2432d2d45bf7c5af361","observation_id":"98d01253-c4e4-4b44-a93f-838c78d3744a","resolution":{"observed_at":"2026-08-11T22:24:44.001927Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.05544","last_updated":"2023-06-08T20:30:55Z","snapshot_observed_at":"2026-08-13T11:20:45.094748Z","submitted_at":"2023-06-08T20:30:55Z","title":"BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.05544","snapshot_observed_at":"2026-08-11T22:24:44.005581Z","title":"Susskind","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.005581Z"},"links":{"cited_paper":"/paper/2306.05544","citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:8df91976cfd2e99ca693836bdcbdd93fbe37fd92e22e76ae8edc2e0e670baf2a","observation_id":"10d43d9a-100c-496d-bbe8-c455a295c182","resolution":{"observed_at":"2026-08-11T22:24:44.005581Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.08543","last_updated":"2026-01-31T09:16:35Z","snapshot_observed_at":"2026-08-13T16:04:46.474244Z","submitted_at":"2023-06-14T14:44:03Z","title":"MiniLLM: On-Policy Distillation of Large Language Models","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.08543","snapshot_observed_at":"2026-08-11T22:24:44.009869Z","title":"Knowledge distillation of large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.009869Z"},"links":{"cited_paper":"/paper/2306.08543","citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:165ed6c3fd20a7bbb2da5c61aab5aa1cc0e565912a33a3125b64026ab8deb8f9","observation_id":"9300710a-b2b6-4f6f-b626-a710110f6abb","resolution":{"observed_at":"2026-08-11T22:24:44.009869Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.13788","last_updated":"2024-12-19T17:51:42Z","snapshot_observed_at":"2026-08-13T00:49:16.784722Z","submitted_at":"2024-03-20T17:51:53Z","title":"DepthFM: Fast Monocular Depth Estimation with Flow Matching","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.13788","snapshot_observed_at":"2026-08-11T22:24:44.013987Z","title":"Depthfm: Fast monocular depth estimation with flow matching","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.013987Z"},"links":{"cited_paper":"/paper/2403.13788","citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:8b913baecdf9cf87f6b8f643ac67b7068b7067773e38ead217f8ea56c2ee30d1","observation_id":"379c0acc-0628-4953-8fd6-2585f8f043aa","resolution":{"observed_at":"2026-08-11T22:24:44.013987Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:44.018344Z","title":"ASIC: aligning sparse in-the-wild image collec- tions","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.018344Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:5ccb8f1438030ad23a17d0ffb36f9d17a74c93b47b6fb916d941da62751798ec","observation_id":"562e7378-a79b-476f-8d33-8c0c496530e3","resolution":{"observed_at":"2026-08-11T22:24:44.018344Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:44.022369Z","title":"Proposal flow","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.022369Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:c3cdb524cd39020346fb8167dff3bb188346039cb2a4b9e1a5905499be3db208","observation_id":"f9649c3e-459d-4da6-bad1-8a8a69f01026","resolution":{"observed_at":"2026-08-11T22:24:44.022369Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:44.026394Z","title":"Rezende, Bumsub Ham, Kwan-Yee K","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.026394Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:65bc6893cc0ed9e7b7397c52c3480d5b8d78fce373363e18645c7cee717d8dcf","observation_id":"f607eb5e-48d0-4254-a2b2-743ebe84ab09","resolution":{"observed_at":"2026-08-11T22:24:44.026394Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:44.030452Z","title":"Unsupervised semantic correspondence using stable diffusion","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.030452Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:5c43779e1c0911e96f18f6a3c01fdc6621a3116ff64d13e4600b3689d2147981","observation_id":"d507d817-3229-4ae6-9409-649291127a6a","resolution":{"observed_at":"2026-08-11T22:24:44.030452Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:44.034730Z","title":"Prompt-to-prompt im- age editing with cross-attention control","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.034730Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:f8c8392947f48edcac9fad536722a6425e49151c171bcdbb7320cd8fb0488d7d","observation_id":"a1136f05-15ce-4a26-a589-622865a0795b","resolution":{"observed_at":"2026-08-11T22:24:44.034730Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-07-06T04:11:24.157003Z","submitted_at":"2015-03-09T15:44:49Z","title":"Distilling the Knowledge in a Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.02531","snapshot_observed_at":"2026-08-11T22:24:44.038919Z","title":"Hinton, Oriol Vinyals, and Jeffrey Dean","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.038919Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:c4dea7df82520395d3481a76954ad3c59eb6e0987606188e0494698ca770c2cd","observation_id":"16dd80df-8843-47d7-bfce-fd70a4c89156","resolution":{"observed_at":"2026-08-11T22:24:44.038919Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:44.043389Z","title":"Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen- Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.043389Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:9b0fe4e16993311f1dd2445043a8f6ca5280c0e85be778fc458f704e5b8cf654","observation_id":"06f91b16-016b-4aa6-83b6-73f31c1d4f3f","resolution":{"observed_at":"2026-08-11T22:24:44.043389Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:44.047332Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.047332Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:b529119428c14443562124df057aaa6da9e8c518ff5121dc3c7812811103f0f1","observation_id":"17a82fd2-19b9-4fd5-8349-60664dbba32b","resolution":{"observed_at":"2026-08-11T22:24:44.047332Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:44.051257Z","title":"Twigg, Po-Chen Wu, Junsong Yuan, Cem Keskin, and Robert Wang","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.051257Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:3654e7eb34e6aaabfbd343f2b7351efa08e177dc8c4e8fb9094fe97ae79efe1f","observation_id":"a830d97c-c2e6-4d8c-89a3-37b807d89130","resolution":{"observed_at":"2026-08-11T22:24:44.051257Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:44.055369Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.055369Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:f8ee9d451a6ba9f9edb638832a038a8b34f14367bd96b43e5b9cd82bb8ef9724","observation_id":"9e79176d-860f-4a92-91d5-a060b691408c","resolution":{"observed_at":"2026-08-11T22:24:44.055369Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:44.059655Z","title":"Difnet: Semantic segmentation by diffu- sion networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.059655Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:c0de1a6877f0d1004b84e6efcb135f9fa5ab5734e69ab4b9375466976bc80e83","observation_id":"efbcf423-c1e7-4f63-a1d6-bf9f6629f33f","resolution":{"observed_at":"2026-08-11T22:24:44.059655Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.381642Z","title":"COTR: correspondence transformer for matching across images","venue":null,"work_id":"3e804257-3ab8-434f-ab5a-e1e8cb9fad84","year":2021},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.063668Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:8c977189c9a408924a29a7fcfbfb096a4f40a56cbc48f6cbc87bd5f410a37968","observation_id":"6cc73c12-f489-4d87-9ac0-6e133624fe96","resolution":{"observed_at":"2026-08-11T22:24:45.385570Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.368640Z","title":"Imagic: Text-based real image editing with diffusion mod- els","venue":null,"work_id":"4c136dae-78d4-4d08-a95a-5d1a8b555d2a","year":2023},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.067682Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:22de26135e8cef3840a3e6d69d290b6a7e88a8fb07d2479b7ee84140fa622f5d","observation_id":"7045dac0-b0b2-4a02-9e77-90c4937754d5","resolution":{"observed_at":"2026-08-11T22:24:45.372832Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.355309Z","title":"Scherer, K","venue":null,"work_id":"afb6048f-d039-4ab6-9349-94985c0d8ae5","year":2024},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.071484Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:d876105fb3519ac688894b6ec9433fc6778fd9167ba2b695248b18240efdfee5","observation_id":"b4aa7987-63ba-42b0-876d-132eaf54530b","resolution":{"observed_at":"2026-08-11T22:24:45.359228Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.342921Z","title":"Recurrent transformer net- works for semantic correspondence","venue":null,"work_id":"ead0e5c1-1e1d-44ca-80e4-cce587c3e324","year":2018},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.075428Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:12b0838f3e58a4e8e9452db3d3094e8f272f5cba1a4499bbaf6304ce9ccb4d65","observation_id":"f1b6f582-6b74-464b-8906-286164aa8fac","resolution":{"observed_at":"2026-08-11T22:24:45.347047Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.330616Z","title":"FCSS: fully convolutional self- similarity for dense semantic correspondence","venue":null,"work_id":"c56bfd67-84ec-42d0-8d22-fbb0c7db100a","year":2019},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.079200Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:b085c978395375a749ab271bafba6f215df11d366787fd7abaec65c58d3a092f","observation_id":"0cbd6594-ec27-4ab7-b3cf-8698d277a24a","resolution":{"observed_at":"2026-08-11T22:24:45.334802Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.317835Z","title":"Transfor- matcher: Match-to-match attention for semantic correspon- dence","venue":null,"work_id":"e8471aa9-ce2a-4162-a226-c35edb9cb269","year":2022},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.083075Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:c55f6c9f37d6815a0e2d8c9083178264c2a53ecc24f218f69f4d65a2ad0c04ce","observation_id":"badf5d04-c5be-44ec-aefa-664245b3da35","resolution":{"observed_at":"2026-08-11T22:24:45.322045Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.305768Z","title":null,"venue":null,"work_id":"52b74e78-14a5-40aa-acbc-97d31c439a6a","year":2016},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.086866Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:65e4b3bdda23cefbea647e8319b52b9b708d981ae3a94750e37c28b00dda1c19","observation_id":"a15575a0-1baa-4758-a819-e3017c437aa2","resolution":{"observed_at":"2026-08-11T22:24:45.309718Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.293234Z","title":"To the point: Correspondence-driven monocular 3d category reconstruc- tion","venue":null,"work_id":"fb11f046-756b-4295-a24d-6415b91039e2","year":2021},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.090789Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:3d98ea2fb9851804dfa16eb723ad9c8eb106aa8d1eabfe76cf741955f4c140cb","observation_id":"a4ae2e79-e12a-415e-addf-b086b5b06049","resolution":{"observed_at":"2026-08-11T22:24:45.297499Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.281056Z","title":"Sfnet: Learning object-aware semantic correspon- dence","venue":null,"work_id":"00f8cb99-8b17-40c7-b6ba-27188c9071e5","year":2019},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.094557Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:f3139db98c9fcd22484d59dffa8f093d42942417ac58598d3eed17fd244d6c09","observation_id":"9b6103af-ff01-4a5d-889e-5729cc1fee69","resolution":{"observed_at":"2026-08-11T22:24:45.285108Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.268843Z","title":null,"venue":null,"work_id":"31cdf096-03e7-49b2-8b72-38cecba3d96e","year":2021},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.098619Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:26b10a321b1d618ae807591eb6db1aa4b61a7201dc043465b340e9888b9e5af7","observation_id":"9d0c394d-2097-440f-a350-068862799766","resolution":{"observed_at":"2026-08-11T22:24:45.272842Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.255807Z","title":"Li, Mihir Prabhudesai, Shivam Duggal, El- lis Brown, and Deepak Pathak","venue":null,"work_id":"a2e10ea8-b5cf-40e0-b9f7-55bc78862c6c","year":2023},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.102653Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:c21f4307698bfea444bd58abe99f1e3d01414a02fd59e74d78e783919b20c68e","observation_id":"837c8e9c-7c1f-4705-86a3-29ad9e5385d1","resolution":{"observed_at":"2026-08-11T22:24:45.259868Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.243396Z","title":"Costain, Henry Howard- Jenkins, and Victor Prisacariu","venue":null,"work_id":"ac2370d9-b314-4a8e-a35e-d73751ed1214","year":2020},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.106590Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:024378e69e0fd9326bf1405c7b00ffef4dc9ff8138f43d08bfff6b38865b765b","observation_id":"0e97621b-4b45-4866-9dbc-137a094a03e5","resolution":{"observed_at":"2026-08-11T22:24:45.247401Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.230961Z","title":"Probabilistic model distillation for se- mantic correspondence","venue":null,"work_id":"4b4e248c-020c-4ca2-a37a-1550aae0ccd0","year":2021},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.110346Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:df4ab8643973629a3e2916d8a510fb3464f6465d6c0ed2d5498ad05b441ede8e","observation_id":"1cd50be7-d0d8-4045-affb-49d0e439b935","resolution":{"observed_at":"2026-08-11T22:24:45.235069Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.02385","last_updated":"2023-05-03T18:52:38Z","snapshot_observed_at":"2026-08-13T11:49:50.310648Z","submitted_at":"2023-05-03T18:52:38Z","title":"SimSC: A Simple Framework for Semantic Correspondence with Temperature Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.02385","snapshot_observed_at":"2026-08-11T22:24:44.114364Z","title":"Simsc: A simple framework for seman- tic correspondence with temperature learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.114364Z"},"links":{"cited_paper":"/paper/2305.02385","citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:98d96e57b2d1f042c183792fb5a6973d7934bd82b1d674ed526fc8f45d8c231b","observation_id":"7c018949-9e27-4f7c-8f8b-2a8c2b3a3e08","resolution":{"observed_at":"2026-08-11T22:24:44.114364Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.17569","last_updated":"2024-03-26T11:52:23Z","snapshot_observed_at":"2026-08-13T05:39:41.064984Z","submitted_at":"2023-10-26T16:58:01Z","title":"SD4Match: Learning to Prompt Stable Diffusion Model for Semantic Matching","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.17569","snapshot_observed_at":"2026-08-11T22:24:44.118468Z","title":"Sd4match: Learning to prompt stable diffusion model for semantic matching","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.118468Z"},"links":{"cited_paper":"/paper/2310.17569","citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:3a80a7c8688b20b1a0331580dba240387b6df4781adef9e9368ba12e8d1d016e","observation_id":"a307562d-9aae-4e9e-9084-71a6fb347ef6","resolution":{"observed_at":"2026-08-11T22:24:44.118468Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.08448","last_updated":"2021-04-17T04:54:54Z","snapshot_observed_at":"2026-08-09T06:13:48.717821Z","submitted_at":"2021-04-17T04:54:54Z","title":"Data Distillation for Text Classification","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.08448","snapshot_observed_at":"2026-08-11T22:24:44.122871Z","title":"Data distillation for text classifi- cation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.122871Z"},"links":{"cited_paper":"/paper/2104.08448","citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:fee9d5bf4f6253d1a0530e503c613b036bf96ef15d5b19fed8314395feb2293a","observation_id":"fc4bfb2a-d917-4f8a-9cf2-e1348f9ecd7f","resolution":{"observed_at":"2026-08-11T22:24:44.122871Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.214214Z","title":"Cycle-consistency based hierarchical dense semantic cor- respondence","venue":null,"work_id":"d2dfe74e-412d-4b5c-aac1-ec78ac329160","year":2018},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.126978Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:09cdc4cf16258d3210b72564c3b5d5d23d65de2d3044e90f9a8b9951754e2bcf","observation_id":"68954d6d-2db3-441b-a6c9-c5ffcfa970af","resolution":{"observed_at":"2026-08-11T22:24:45.219476Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1405.0312","last_updated":"2015-02-21T01:48:49Z","snapshot_observed_at":"2026-07-06T03:42:37.507458Z","submitted_at":"2014-05-01T21:43:32Z","title":"Microsoft COCO: Common Objects in Context","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1405.0312","snapshot_observed_at":"2026-08-11T22:24:44.131080Z","title":"Belongie, Lubomir D","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.131080Z"},"links":{"cited_paper":"/paper/1405.0312","citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:a9c7244b7585892448d746717654e7704b04bacf63d1388d855206c75a356bd4","observation_id":"167bd2da-70b2-49eb-a337-b0730bed6855","resolution":{"observed_at":"2026-08-11T22:24:44.131080Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.201982Z","title":"Scale Invariant Feature Transform, vol- ume 7","venue":null,"work_id":"13bf4618-9fc4-458e-bec3-329dad3adbfd","year":2012},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.135225Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:c072f992902585c90944b86dd93d33da02e63d7a2ef243f56db39cb99297130f","observation_id":"ef9319cb-9b35-443d-ba95-92af86884698","resolution":{"observed_at":"2026-08-11T22:24:45.205950Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.189049Z","title":"Sift flow: Dense correspondence across scenes and its applications","venue":null,"work_id":"e1f2fd61-2eb2-46a5-ad2f-7a4bd08ce7a2","year":2011},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.139093Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:3539eec6dc6e121c1cada933d8fe45b5cb1d236205d7c9a737cd077bebf7beb4","observation_id":"da556a3d-0899-46e2-a6b7-48bdf235122b","resolution":{"observed_at":"2026-08-11T22:24:45.193649Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.176623Z","title":"Structured knowledge dis- tillation for semantic segmentation","venue":null,"work_id":"a3fec177-1828-4201-8774-c49bab630889","year":2019},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.142982Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:3e97039bf3cbf3af1f683e71a03788d16371fed33d6e733bafbb3ce6c3f9064a","observation_id":"e1a56005-eac7-4524-b26e-ffd9eb70af61","resolution":{"observed_at":"2026-08-11T22:24:45.180661Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.163892Z","title":"Do con- vnets learn correspondence? In Zoubin Ghahramani, Max Welling, Corinna Cortes, Neil D","venue":null,"work_id":"0225431c-4846-4c7b-8121-b925255d5b45","year":2014},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.147003Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:afce8c764aa9ef4fefebc4d17f76e83e318ea1ae4face0f8ea06cd1c2c9e1862","observation_id":"f38c300b-ae51-4414-ad11-37026d77764c","resolution":{"observed_at":"2026-08-11T22:24:45.167820Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.151021Z","title":"Diffusion hyperfeatures: Searching through time and space for semantic correspon- dence","venue":null,"work_id":"d0fa3b04-a544-4b53-9f13-c8bbe28b3e5a","year":2023},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.150839Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:bbf689896d8d35e3533d30168a215c276683211bdd65bd82b84e3b6b79b72675","observation_id":"3f05e4b5-c657-48b2-96ae-3fbd418c907f","resolution":{"observed_at":"2026-08-11T22:24:45.155512Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.13216","last_updated":"2024-07-05T16:07:13Z","snapshot_observed_at":"2026-08-13T04:57:28.979508Z","submitted_at":"2023-12-20T17:35:24Z","title":"Improving Semantic Correspondence with Viewpoint-Guided Spherical Maps","version":2},"cited_work":{"arxiv_id":"2312.13216","doi":null,"metadata_source":"pith","pith_arxiv_id":"2312.13216","snapshot_observed_at":"2026-08-11T22:24:44.522574Z","title":"Improving Semantic Correspondence with Viewpoint-Guided Spherical Maps","venue":"cs.CV","work_id":"7edd8517-2894-4d99-a0ad-9029d48097b8","year":2023},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.154822Z"},"links":{"cited_paper":"/paper/2312.13216","citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:2651c29ee7a46865787bb8d3840c77601031f91d7272b35abdb6e40b516b160c","observation_id":"1194276c-1ae6-4c34-935e-01057210d062","resolution":{"observed_at":"2026-08-11T22:24:44.527146Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.138731Z","title":"Kingma, Stefano Ermon, Jonathan Ho, and Tim Salimans","venue":null,"work_id":"e75d8794-ff6f-42e7-90b4-f3a5a3247f77","year":2023},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.159053Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:b8e036937abf5adf26de0badbd393651e20a15612f3776a493c43c7c0b71dacd","observation_id":"b13790e7-ca1d-4c12-8958-2120ed278b3d","resolution":{"observed_at":"2026-08-11T22:24:45.142932Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.126589Z","title":"Con- ditional teacher-student learning","venue":null,"work_id":"d42c0ae3-7278-4ba9-af86-a3aeacc1f776","year":2019},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.163267Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:a53cfae1c4dc3d918394b208125da4c8e16472c47681e6c9dcf0f43afbb3ab85","observation_id":"47c0d404-61e5-4aba-9b5c-eef67505096e","resolution":{"observed_at":"2026-08-11T22:24:45.130635Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.10543","last_updated":"2019-08-28T04:16:52Z","snapshot_observed_at":"2026-08-11T20:36:49.773677Z","submitted_at":"2019-08-28T04:16:52Z","title":"SPair-71k: A Large-scale Benchmark for Semantic Correspondence","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.10543","snapshot_observed_at":"2026-08-11T22:24:44.167314Z","title":"Spair-71k: A large-scale benchmark for semantic corre- spondence","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.167314Z"},"links":{"cited_paper":"/paper/1908.10543","citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:71ec9463331a7f3c61e93558f676c142e5d9e6e493797d4a9729a6018500eb50","observation_id":"c501aa75-1cee-4245-b38c-442ba2024efd","resolution":{"observed_at":"2026-08-11T22:24:44.167314Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.114199Z","title":"Learning to compose hypercolumns for visual correspon- dence","venue":null,"work_id":"fbca0d9b-c1cb-4c80-bfc7-4c83457b6b1e","year":2020},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.171658Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:79cb8f9d01f746511b411a74b00a999185801b3761c9c354973985660c8fac74","observation_id":"eb6ab857-0a94-488e-8b8a-8f52d9629f02","resolution":{"observed_at":"2026-08-11T22:24:45.118236Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.101018Z","title":"Coordgan: Self-supervised dense correspondences emerge from gans","venue":null,"work_id":"6bfb4849-3f76-4536-8b91-a63130e8bb67","year":2022},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.175593Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:0cf13ad56ff6c065259c331a5de17974d99ebf8d53f4198217f7171f99b0d744","observation_id":"4d935ffe-8d88-4229-9c24-1d19b09a54a8","resolution":{"observed_at":"2026-08-11T22:24:45.105378Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.08702","last_updated":"2023-07-17T17:59:40Z","snapshot_observed_at":"2026-08-13T10:54:00.465035Z","submitted_at":"2023-07-17T17:59:40Z","title":"Diffusion Models Beat GANs on Image Classification","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.08702","snapshot_observed_at":"2026-08-11T22:24:44.179447Z","title":"Diffusion models beat gans on image classification","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.179447Z"},"links":{"cited_paper":"/paper/2307.08702","citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:9757c3ef2daa37c80df42f11e5100eb0ad097b39b8986e77c52b1622f455ed64","observation_id":"1b5f4e4f-15ee-429a-ae31-304972c1cc8e","resolution":{"observed_at":"2026-08-11T22:24:44.179447Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.07193","last_updated":"2024-02-02T10:24:09Z","snapshot_observed_at":"2026-08-11T10:12:11.384939Z","submitted_at":"2023-04-14T15:12:19Z","title":"DINOv2: Learning Robust Visual Features without Supervision","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.07193","snapshot_observed_at":"2026-08-11T22:24:44.183660Z","title":"Rabbat, Vasu Sharma, Gabriel Synnaeve, Hu Xu, Herv ´e J ´egou, Julien Mairal, Patrick Labatut, Armand Joulin, and Piotr Bojanowski","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.183660Z"},"links":{"cited_paper":"/paper/2304.07193","citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:8ea3a2e01c161a0067d51f8102b8f4f702dd1b9db25d9d8d4f317b7e73071f2f","observation_id":"c384e28a-dfc7-4b2c-a56f-769cff374d20","resolution":{"observed_at":"2026-08-11T22:24:44.183660Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.10754","last_updated":"2019-09-24T08:14:40Z","snapshot_observed_at":"2026-07-06T08:24:05.808457Z","submitted_at":"2019-09-24T08:14:40Z","title":"FEED: Feature-level Ensemble for Knowledge Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.10754","snapshot_observed_at":"2026-08-11T22:24:44.187943Z","title":"FEED: feature-level en- semble for knowledge distillation","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.187943Z"},"links":{"cited_paper":"/paper/1909.10754","citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:01116c368e140442bdfab2fd1ec268486518ba5a3e799b5a3ea9a9695159bd78","observation_id":"836d8776-e4ca-49bb-abf8-0241a6759eb9","resolution":{"observed_at":"2026-08-11T22:24:44.187943Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.088196Z","title":"Com- mon objects in 3d: Large-scale learning and evaluation of real-life 3d category reconstruction","venue":null,"work_id":"aefa5ee0-6067-419e-af95-160445d821b3","year":2021},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.192087Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:29371f46b5927e0289472fb53050e281da46f4df2d837decd4deeeef2b952ed5","observation_id":"3458e8d6-7e9f-42b6-ac59-262047e545f3","resolution":{"observed_at":"2026-08-11T22:24:45.092637Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.075588Z","title":"Con- volutional neural network architecture for geometric match- ing","venue":null,"work_id":"bc148e0e-c8b9-410a-acff-f0b524449586","year":2019},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.196207Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:01905beea69d836faf50464042c975780e4bcffc2bdd1712e2fdf07a36d75695","observation_id":"24c4f08a-9cc2-486e-bd58-cce31b56a291","resolution":{"observed_at":"2026-08-11T22:24:45.079783Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.062822Z","title":"Effi- cient neighbourhood consensus networks via submanifold sparse convolutions","venue":null,"work_id":"619f2f41-81b5-4d66-a341-07156eddc497","year":2020},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.199967Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:b7ab509388f7c3ff82b90b1315bcf26b197ba15a080d41a44d090040fb83e07f","observation_id":"15d6d90c-0dd5-44e9-91e5-755129cc5276","resolution":{"observed_at":"2026-08-11T22:24:45.067015Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.049484Z","title":"Neighbourhood consensus networks","venue":null,"work_id":"fed5f42e-2b8c-49ae-9c05-c7b2ae89ba4e","year":2018},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.203863Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:76e0d9e997b8b86f11cb88162f5c4bbe63354dd93d8dcb07433a8f8476f5cdf7","observation_id":"4d223e80-6392-436a-8956-3efc6a51ba36","resolution":{"observed_at":"2026-08-11T22:24:45.053885Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.036937Z","title":"High-resolution im- age synthesis with latent diffusion models","venue":null,"work_id":"582ecd11-b618-4c6c-8be5-8a8ce2e950d2","year":2022},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.207867Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:d8490b2da09c16a1fd53ecdee2f296915f2333273abf4a80031fe0de80b806f9","observation_id":"fae757bb-b2cc-4ed2-966d-7e06bbbe69c1","resolution":{"observed_at":"2026-08-11T22:24:45.041179Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.024395Z","title":"Fit- nets: Hints for thin deep nets","venue":null,"work_id":"bd90b5a2-170e-4d4d-bd33-5719d395fe6b","year":2015},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.211700Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:3ab3eae7495a7365ee41c62aedd73853da5a23829f0a0d5662ba1486342ed9bd","observation_id":"418170c8-e0bd-4d4e-9ccb-33afe50a6b19","resolution":{"observed_at":"2026-08-11T22:24:45.028502Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:45.011670Z","title":"Progressive distillation for fast sampling of diffusion models","venue":null,"work_id":"49439519-0ca7-43c1-8e97-474b8bc330a8","year":2022},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.215538Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:27d680f2c5f12d0ee0871bd04757c2dd25b7a4418384b8f030883745f48ad374","observation_id":"5ee73d86-d6d8-4a72-9675-5eeb27dc7845","resolution":{"observed_at":"2026-08-11T22:24:45.015809Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.01108","last_updated":"2020-03-01T02:57:50Z","snapshot_observed_at":"2026-08-07T19:07:36.327251Z","submitted_at":"2019-10-02T17:56:28Z","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.01108","snapshot_observed_at":"2026-08-11T22:24:44.219344Z","title":"Distilbert, a distilled version of BERT: smaller, faster, cheaper and lighter.CoRR, abs/1910.01108,","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.219344Z"},"links":{"cited_paper":"/paper/1910.01108","citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:463ca2775ceea4cc9620c24510df9316c371b8872659b01871e5d6ca59c4d32d","observation_id":"7e770fb1-be8a-46a2-b99c-155c6b47c2d3","resolution":{"observed_at":"2026-08-11T22:24:44.219344Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1610.09650","last_updated":"2016-11-02T16:32:23Z","snapshot_observed_at":"2026-07-06T05:16:41.164761Z","submitted_at":"2016-10-30T13:54:39Z","title":"Deep Model Compression: Distilling Knowledge from Noisy Teachers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1610.09650","snapshot_observed_at":"2026-08-11T22:24:44.223640Z","title":"Balasubramanian","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.223640Z"},"links":{"cited_paper":"/paper/1610.09650","citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:e9d13b6e879407d9928b95d274056fd919cc02385c408df3b2f1ab5b2ef481ee","observation_id":"78f4ba49-9c17-4c52-9779-cafa20334bd7","resolution":{"observed_at":"2026-08-11T22:24:44.223640Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.14816","last_updated":"2023-02-28T18:08:21Z","snapshot_observed_at":"2026-08-13T12:34:58.634833Z","submitted_at":"2023-02-28T18:08:21Z","title":"Monocular Depth Estimation using Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.14816","snapshot_observed_at":"2026-08-11T22:24:44.227957Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.227957Z"},"links":{"cited_paper":"/paper/2302.14816","citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:f590f27c4e383566c3550687859ccc96b49b4e8fe64d431758ecc9c8f215e88e","observation_id":"bd2c2d33-cc64-4ac0-8bcd-71ddf07d8533","resolution":{"observed_at":"2026-08-11T22:24:44.227957Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:44.999105Z","title":"Baumann, Vincent Tao Hu, and Bj ¨orn Ommer","venue":null,"work_id":"6770fc32-1b79-4399-8fa1-d0717bd66eea","year":2024},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.231893Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:b42a1116405ae12232e1a200789f77f8a3bff52733b68b1a64bc67650d2594f0","observation_id":"e652ef8a-05ea-43f7-ad70-1a2775d1c74a","resolution":{"observed_at":"2026-08-11T22:24:45.003108Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.07198","last_updated":"2023-11-13T09:38:30Z","snapshot_observed_at":"2026-08-13T05:27:14.983684Z","submitted_at":"2023-11-13T09:38:30Z","title":"MonoDiffusion: Self-Supervised Monocular Depth Estimation Using Diffusion Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.07198","snapshot_observed_at":"2026-08-11T22:24:44.235864Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.235864Z"},"links":{"cited_paper":"/paper/2311.07198","citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:83c9a156a3a43de0267e7d83e13edb517f179c2e6239669cce5facf052593820","observation_id":"f76fc88a-3cb9-44ed-82bc-c106e2341fdb","resolution":{"observed_at":"2026-08-11T22:24:44.235864Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:44.986711Z","title":null,"venue":null,"work_id":"0dc9f32c-7d80-44ed-8a6b-d88a71327070","year":2023},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.239923Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:96f1510de36c8c9cbb171eee647459b2860c05de84f96de5c77bcdba771a2834","observation_id":"1abd3497-5806-453b-8a35-92d34a34079c","resolution":{"observed_at":"2026-08-11T22:24:44.990804Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:44.974278Z","title":"Dpodv2: Dense correspondence-based 6 dof pose estima- tion","venue":null,"work_id":"5e4d8c3d-b949-40cb-8120-4710e07f0dd9","year":2022},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.243601Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:9c860c809ea7055b6755455697a10d4861382c559e820931a0f4a303d4501d46","observation_id":"9d115557-9d5d-4f45-887d-8a9bed66a54a","resolution":{"observed_at":"2026-08-11T22:24:44.978330Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:44.962198Z","title":"Consistency models","venue":null,"work_id":"122a0e42-547c-46b0-9f8f-b78346325d1e","year":2023},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.247551Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:6820c2a70fe886a78577175b79828d0052d168962c2cd9c2b4892411fd6db70e","observation_id":"7972dbd5-4949-4e89-938e-0dbb3f50413b","resolution":{"observed_at":"2026-08-11T22:24:44.966079Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:44.949752Z","title":"Visual correspondence-based explanations improve AI ro- bustness and human-ai team accuracy","venue":null,"work_id":"c404c675-9bc4-43ea-bd5a-c1a981c6bc75","year":2022},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.251337Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:25c8c7bad23e7db5d8af5275afd7771d404f214a96d16fb7582d39b8f8481a50","observation_id":"77bb72be-27d1-477f-8d75-d497d2c72658","resolution":{"observed_at":"2026-08-11T22:24:44.953874Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.02057","last_updated":"2023-02-04T01:39:16Z","snapshot_observed_at":"2026-08-13T12:51:05.654923Z","submitted_at":"2023-02-04T01:39:16Z","title":"Semantic Diffusion Network for Semantic Segmentation","version":1},"cited_work":{"arxiv_id":"2302.02057","doi":null,"metadata_source":"pith","pith_arxiv_id":"2302.02057","snapshot_observed_at":"2026-08-11T22:24:44.400497Z","title":"Semantic Diffusion Network for Semantic Segmentation","venue":"cs.CV","work_id":"7881cef8-ba48-4ad4-b514-778a21f0b48e","year":2023},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.255674Z"},"links":{"cited_paper":"/paper/2302.02057","citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:1385e685ff69d22a7005de721a5dc049412a04122f62cd819f58a0b248a84c14","observation_id":"ea152dfc-5589-496d-939c-ec26518220be","resolution":{"observed_at":"2026-08-11T22:24:44.406861Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.00773","last_updated":"2023-10-11T10:29:59Z","snapshot_observed_at":"2026-08-13T11:04:02.330407Z","submitted_at":"2023-07-03T06:33:49Z","title":"DifFSS: Diffusion Model for Few-Shot Semantic Segmentation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.00773","snapshot_observed_at":"2026-08-11T22:24:44.260014Z","title":"Diffss: Diffu- sion model for few-shot semantic segmentation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.260014Z"},"links":{"cited_paper":"/paper/2307.00773","citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:695d620951c2a09d8517aff65b22eb333b0340b1c83494386891c710c94d5d47","observation_id":"21f70711-19b5-4ce6-bcb8-cbfd5cadc773","resolution":{"observed_at":"2026-08-11T22:24:44.260014Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:44.937734Z","title":"Emergent correspondence from image diffusion","venue":null,"work_id":"3998a1e8-87e5-487e-8ed8-918e1b82b2ea","year":2023},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.264842Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:a4c333df07d97633e3273dcf1c9da94f08fa09f39e7751185b4940a5a3a73415","observation_id":"7b137ba9-243c-4a51-b557-05aa95641742","resolution":{"observed_at":"2026-08-11T22:24:44.941677Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:44.925363Z","title":"Splicing vit features for semantic appearance trans- fer","venue":null,"work_id":"f1b38cd3-3d08-4850-a8a8-e180ff58f18a","year":2022},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.268576Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:a23443dc4d145078e049fd379f850ac476ef583eb00ffff00f46503c55298a5d","observation_id":"7fd7031e-60f6-468a-8156-fc78cc4898b9","resolution":{"observed_at":"2026-08-11T22:24:44.929363Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:44.912746Z","title":"Plug-and-play diffusion features for text-driven image-to-image translation","venue":null,"work_id":"5fb2aa93-cb78-48c8-89e3-453d7515dd48","year":2023},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.272537Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:9b84dc9144e3a900334006cc77955dd72c02048817643850720ed90667fd1dbe","observation_id":"d1d38909-e921-4629-bbd1-983dbc5c64a2","resolution":{"observed_at":"2026-08-11T22:24:44.917027Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:44.900674Z","title":null,"venue":null,"work_id":"637a276f-ba2a-4e62-a211-fe8d629b4091","year":2011},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.276495Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:de96c01583ac621b17317ebe36ff76ee337f477eb2a0a91c6e9a47522457f1e7","observation_id":"9a84d71c-81a8-489c-a572-dd6d13666e30","resolution":{"observed_at":"2026-08-11T22:24:44.904427Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:44.887784Z","title":"Learning feature descriptors using cam- era pose supervision","venue":null,"work_id":"40f13ce8-6ca3-4710-a1c5-c6fece4cb65e","year":2020},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.280319Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:89332035fe7fd7120a64a5a6af747bf03aa4a0dd2bf702a4631ca89cdba50797","observation_id":"03446d48-fad0-463a-bcbb-a374b8e0e6cf","resolution":{"observed_at":"2026-08-11T22:24:44.892289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:44.875342Z","title":null,"venue":null,"work_id":"b64c9ba0-1919-4f53-bc78-b33757ed77a2","year":2019},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.284086Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:6ef11cc517f05f8db0f0604c5c9159d08d03a07077dba01df65189efd0c4e163","observation_id":"3ef7bf07-18c9-4dfd-837b-f9335929eca7","resolution":{"observed_at":"2026-08-11T22:24:44.879276Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:44.862655Z","title":null,"venue":null,"work_id":"d90309eb-5afa-4135-b322-1c2dd9963968","year":2022},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.288037Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:f27a48f8a645a9c78bc23aa6593dcc19f0118ee8c8fc7fae5fa36ba16b14b966","observation_id":"edc1b58e-9bfc-42f0-92b0-d1393d6742f3","resolution":{"observed_at":"2026-08-11T22:24:44.866660Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:44.849036Z","title":"Diffumask: Synthesizing images with pixel-level annotations for semantic segmentation using dif- fusion models","venue":null,"work_id":"8a371145-bae1-4511-ab1d-34c4b2365df9","year":2023},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.292056Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:e3b359b0372d54dc0de05b5894d7c9287ff76f49373838c6be19a56519ebdb9a","observation_id":"cea42e17-ab5a-4aff-ad23-5c55048b07a2","resolution":{"observed_at":"2026-08-11T22:24:44.853148Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:44.836606Z","title":"Open-vocabulary panoptic segmentation with text-to-image diffusion models","venue":null,"work_id":"4316d2c8-0812-4fc2-99c3-13b6794210d2","year":2023},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.295968Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:90707454a828e4bac16df7067e375b1650b8607c257adad20962d6f1641fc141","observation_id":"6f43dddc-4244-4ef7-a87c-89915bd7d42f","resolution":{"observed_at":"2026-08-11T22:24:44.840648Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:44.822721Z","title":"A gift from knowledge distillation: Fast optimization, net- work minimization and transfer learning","venue":null,"work_id":"139db829-2012-44a1-8ca4-0186abf9d24e","year":2017},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.299742Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:77b7f537a466f593a9b0b557841f48d9d01305f3b6b197490d63645c4eb70384","observation_id":"6cd1c0c8-da7d-4036-8d1c-fbcd0b8f09c1","resolution":{"observed_at":"2026-08-11T22:24:44.827472Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:24:44.808603Z","title":"Paying more at- tention to attention: Improving the performance of convo- lutional neural networks via attention transfer","venue":null,"work_id":"6999644a-9e8b-45c5-bda2-c01876420521","year":2017},"citing_paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-11T22:24:44.303692Z"},"links":{"citing_paper":"/paper/2412.03512"},"observation_digest":"sha256:f6fb2c72c704b7a18c2eab3b2de50a1afc9ed7fce69825152e3923e68d66603b","observation_id":"1332a207-15b6-43bf-9e9c-021354066a76","resolution":{"observed_at":"2026-08-11T22:24:44.812953Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.03512","last_updated":"2024-12-04T17:55:33Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T23:02:44.275284Z","submitted_at":"2024-12-04T17:55:33Z","title":"Distillation of Diffusion Features for Semantic Correspondence"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":57,"verified_exact":3,"verified_fuzzy":40},"total_outbound_references":106},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 100 of 106 outbound references and 0 inbound Pith citation observations for arXiv:2412.03512."}