{"as_of":"2026-08-10T13:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b64730437a1459e58692e59fa7e0ce21adb6872254db1a99854ff9ea26d1e43d","coverage":[{"denominator":64,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":64,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T18:52:20.893254Z","state":"measured"},{"denominator":64,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":64,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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/2507.07262/citation-record","integrity":"/paper/2507.07262/integrity","json":"/paper/2507.07262/citation-record.json","paper":"/paper/2507.07262"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:52:22.139820Z","title":"Past, present, and future of face recognition: A review","venue":null,"work_id":"bca07b2a-c93d-4e50-bccd-60c120a6ec3e","year":2020},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.580219Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:0cef703bf44e89d878bca249eb2d09064dc3fd602f18d90371d745b1e65976d3","observation_id":"e48df077-2342-46aa-9616-093405f55e55","resolution":{"observed_at":"2026-08-06T18:52:22.144542Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:22.122881Z","title":"Flamingo: A visual language model for few-shot learning","venue":null,"work_id":"dee77501-b8da-42f0-9aa1-4b5bc802153e","year":2022},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.585227Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:dc4235c633d34323d3096dd3bc3e8c8fca97e3ac21f42bba9e2b9b68696f56c2","observation_id":"99ad2030-3e66-40c2-9f0f-0e2d4bed5a20","resolution":{"observed_at":"2026-08-06T18:52:22.128616Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:22.105936Z","title":"Activity- biometrics: Person identification from daily activities","venue":null,"work_id":"1f30b86d-35eb-466b-b993-f6f24204b167","year":2024},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.589789Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:34de141829c4a7c44e497414bdc0194146ea1178756cb359d722d0fe8bd0b240","observation_id":"2573e222-20a6-4a20-b683-6816c5eae2e2","resolution":{"observed_at":"2026-08-06T18:52:22.111442Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:22.089891Z","title":"Understanding depth and height percep- tion in large visual-language models","venue":null,"work_id":"f07916b1-ff45-4779-bc98-3a45f52ae05d","year":2025},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.594857Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:c065b732cb0271afdd211ea15b95a82b5c352abd48f04c6ba7fd1d5d9bf249b1","observation_id":"5bc06174-64ac-4f73-b4e5-03a465e736c1","resolution":{"observed_at":"2026-08-06T18:52:22.094565Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:20.600686Z","title":"Hierarq: Task-aware hierarchical q-former for enhanced video understanding","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.600686Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:6a137b533d07a92e331327c8d87d19d43c89dd2163c3000b47d4938d1a67e91c","observation_id":"29cc909d-9706-4917-a008-b5be92decc9b","resolution":{"observed_at":"2026-08-06T18:52:20.600686Z","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":"2026-08-06T18:52:22.060793Z","title":"Salient-to-broad transition for video person re- identification","venue":null,"work_id":"ce768755-2e91-4b46-8753-43ca916b26c9","year":2022},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.605531Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:acdbbe64e6f96322fdc54b17d7d305b180085d947e2a4ebdabc3b56795d41a1a","observation_id":"364abcec-6455-4e0d-9e50-6fc065065175","resolution":{"observed_at":"2026-08-06T18:52:22.065579Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:22.045158Z","title":"Pstr: End-to-end one-step person search with trans- formers","venue":null,"work_id":"c8806ebf-9c9c-415d-98c8-764f7ebdadd2","year":2022},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.610359Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:7da69a34212af0eee4740bd375b385c8397f240aeb648d336ede175aa96bc713","observation_id":"05ca45c4-87ff-4fad-9c87-362eed998534","resolution":{"observed_at":"2026-08-06T18:52:22.050410Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:22.028888Z","title":"Learning recurrent 3d attention for video-based person re- identification","venue":null,"work_id":"0d4f58d8-3cd9-47f4-8707-cf507953a6e7","year":2020},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.616272Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:561090e9d5186371b7036315796236765a10857c5ff44cb3024ebbd53416534b","observation_id":"1f42738b-0f44-4660-8fc5-65e3195b6385","resolution":{"observed_at":"2026-08-06T18:52:22.034048Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:22.010800Z","title":"Learning 3d shape feature for texture-insensitive person re-identification","venue":null,"work_id":"67eb7827-340b-4cec-9066-e31dd66c8d70","year":2021},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.620770Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:965c1712b693f8347269c49cea330e8271e33001ed90e90b75dcb271e05810c3","observation_id":"98f20114-f644-412e-9b6a-2b984fda14de","resolution":{"observed_at":"2026-08-06T18:52:22.017537Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.993113Z","title":"Unveiling the power of clip in unsupervised visible-infrared person re-identification","venue":null,"work_id":"f46f3d13-211e-4b8c-8b84-48c2a19347ae","year":2023},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.625596Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:4ffe5a65383174a2aafd0deaff6e87888a3a7560f7a2e5710aa3048a879414b6","observation_id":"0007c9e5-e016-492a-bb88-cbe0e2b60275","resolution":{"observed_at":"2026-08-06T18:52:21.998500Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.06500","last_updated":"2023-06-15T08:00:18Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-05-11T00:38:10Z","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.06500","snapshot_observed_at":"2026-08-06T18:52:20.630736Z","title":"Instructblip: Towards general- purpose vision-language models with instruction tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.630736Z"},"links":{"cited_paper":"/paper/2305.06500","citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:954025281446dfb494a5eaf85b5173b33b9d1188ab33391f9983252f9330d6c4","observation_id":"3ae4a553-b721-44b2-919e-c94d5e4eb72b","resolution":{"observed_at":"2026-08-06T18:52:20.630736Z","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":"2026-08-06T18:52:21.977473Z","title":"Mevid: Multi-view extended videos with identities for video person re-identification","venue":null,"work_id":"dbc5036f-53bc-4a1b-8187-41e1970e4435","year":2023},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.635710Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:6383e72197e986d1639b2101bfbde0ba30aa23cbbd99d8c791a90c9a4c27ad8f","observation_id":"82870dcf-cc39-4408-95de-babb06fa1d39","resolution":{"observed_at":"2026-08-06T18:52:21.982147Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.04805","last_updated":"2019-05-24T20:37:26Z","snapshot_observed_at":"2026-07-30T09:12:38.100527Z","submitted_at":"2018-10-11T00:50:01Z","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.04805","snapshot_observed_at":"2026-08-06T18:52:20.640744Z","title":"BERT: Pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.640744Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:5581038138f18bed3faf4c225ec866c344a153505760af8d1092d6b886685d45","observation_id":"5b28d836-ebc6-4646-95a4-2f41a448688c","resolution":{"observed_at":"2026-08-06T18:52:20.640744Z","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":"2026-08-06T18:52:21.961301Z","title":"Learning disentangled rep- resentation for robust person re-identification","venue":null,"work_id":"5b87fc40-20bd-4bd2-a155-919d10117f0a","year":2019},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.645724Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:5d8396eb0c5166207bcb351aadc417bd6d06249e0c4ecbd3075caea470e08169","observation_id":"79915838-366e-49c8-a1c6-2bda68279088","resolution":{"observed_at":"2026-08-06T18:52:21.966573Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.945494Z","title":"Video-based person re-identification with spatial and tempo- ral memory networks","venue":null,"work_id":"7d317d73-fa2e-4453-b584-33365456c04f","year":2021},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.650362Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:781967b56e99c38f2ee3a081f6b91d293fcd436498a19cce0afaeffa2b06c14e","observation_id":"61346fb6-826d-4ecc-b17c-21ec27ecc8f7","resolution":{"observed_at":"2026-08-06T18:52:21.950235Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.929802Z","title":"Gaitpart: Temporal part-based model for gait recognition","venue":null,"work_id":"aa2b8ab1-76f1-4227-8c48-d8849966a751","year":2020},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.654695Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:7703fc9a7942d021e9a5798a7d4f625f41e05dae029242928181b4549a111db1","observation_id":"ce80f609-50a1-4be5-914b-c6ba2fb9507f","resolution":{"observed_at":"2026-08-06T18:52:21.934890Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.912890Z","title":"Opengait: Revisiting gait recognition towards better practicality","venue":null,"work_id":"a04bbed5-e726-452b-8118-8399821546cd","year":2023},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.658881Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:f1ad4ee18ff324022e294cc201ce78eb982b09824e25f8d320a11196bd045c66","observation_id":"1d9c9b49-e6fb-44b4-8449-1948d40f4b1f","resolution":{"observed_at":"2026-08-06T18:52:21.917696Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.897181Z","title":"Appearance-preserving 3d convolution for video-based person re-identification","venue":null,"work_id":"6fde9d0f-30b3-499b-846e-e290eebe774b","year":null},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.663307Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:006845b2c76eea13ee9f101bd95dc87c9ce4d6d61099ff83c20ca7728c2a9904","observation_id":"64b084c4-a05c-4ea2-8e9c-df228d0e17d6","resolution":{"observed_at":"2026-08-06T18:52:21.902083Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.865702Z","title":"Clothes-changing person re-identification with rgb modality only","venue":null,"work_id":"4e93505c-dcd6-4efa-ba8f-6d83fc4c8c3e","year":2022},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.671910Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:ed72b8fd386622bd8945ecbaf15a1e440a70d76062f5758f239aba4356e61363","observation_id":"46eb0e18-0f0e-42c9-998a-4c6910db38f6","resolution":{"observed_at":"2026-08-06T18:52:21.871121Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.850974Z","title":"Semantic-aware consistency network for cloth- changing person re-identification","venue":null,"work_id":"ff9765e9-1251-41a9-bf26-f8a8283fdd68","year":2023},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.676768Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:09a2080bd662435742c3975191767772158484690f2b20bb8a146d9e0e725b3d","observation_id":"1edc2ed4-2dab-4948-8ffd-0b58c818b4fe","resolution":{"observed_at":"2026-08-06T18:52:21.855627Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.833745Z","title":"Dense interaction learning for video-based person re-identification","venue":null,"work_id":"d4e7f12b-0bfb-4f43-9d01-580d25b80ea6","year":2021},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.680901Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:765a40bb313f1a7f714178891e102f429bfb98b3f74f43ac26ae6461367bb72f","observation_id":"7df17907-4403-449e-a862-e98515c409eb","resolution":{"observed_at":"2026-08-06T18:52:21.839062Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.816565Z","title":"Instruct-reid: A multi-purpose per- son re-identification task with instructions","venue":null,"work_id":"6eb5e08b-377f-40f5-8cb2-8d8a798ef40a","year":2024},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.685441Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:075782a34742951463d88ce3295bd4bdfd8bf8015f675f1367169016263fdf13","observation_id":"20309024-5577-4665-a862-9835ab7c145e","resolution":{"observed_at":"2026-08-06T18:52:21.821476Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.798602Z","title":"Fine-grained shape-appearance mutual learning for cloth-changing person re-identification","venue":null,"work_id":"65d2f7c4-c34a-46be-a210-2a90451ddbcd","year":2021},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.689700Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:4a311af4c546b0aa72ab72e23cafd24dfbfea9cfbbf111d51fdf787da6154d55","observation_id":"3d8cb323-a61b-49bd-a869-da50d94d23e7","resolution":{"observed_at":"2026-08-06T18:52:21.803373Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.783189Z","title":"Temporal complementary learning for video person re-identification","venue":null,"work_id":"1516f6d6-a273-4f86-aff3-9ad27b1deff0","year":null},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.694784Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:ed3264d0f76e1a569d11ee1c97325c9f51e907c22849821ebc8da273bc05256e","observation_id":"d879ab81-9b6f-4b1f-9168-f18a159fe1cc","resolution":{"observed_at":"2026-08-06T18:52:21.788257Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.767396Z","title":"Bicnet-tks: Learning efficient spatial- temporal representation for video person re-identification","venue":null,"work_id":"a8c9f686-be73-4417-af2a-cc71ff274a04","year":2014},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.699111Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:45620626a7ee4c6c6b9b50bafda04e57cae8feaa04c1c8a54837cbf0e05b3b38","observation_id":"0e4ef487-e7c4-4b15-bb0d-b58af44664ab","resolution":{"observed_at":"2026-08-06T18:52:21.772036Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.752369Z","title":"Empowering visible- infrared person re-identification with large foundation mod- els","venue":null,"work_id":"f3207a51-e7f1-411a-aabd-8837c0bc3870","year":2024},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.703721Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:506e9776ea69d824f2d469641c5c92713d504839af28e201f1501b9c67e9989b","observation_id":"27cae840-efdf-4e14-af75-355a15e5d3d9","resolution":{"observed_at":"2026-08-06T18:52:21.757199Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.734487Z","title":"Celebrities-reid: A benchmark for clothes variation in long- term person re-identification","venue":null,"work_id":"df39d1fc-603a-4668-afba-d6272fe8fd02","year":null},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.709353Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:0c5f66fa77dbc40cb55e02e7d537bb4f1cbbc0e83913441641882bd1db5e3992","observation_id":"e3149049-61e9-4acb-8f66-3922b1e13bfa","resolution":{"observed_at":"2026-08-06T18:52:21.740501Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.715596Z","title":"Rethink- ing temporal fusion for video-based person re-identification on semantic and time aspect","venue":null,"work_id":"0b032f7a-9a66-4e70-9be4-f0d90bfdd9ba","year":null},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.713832Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:5e04558555b3148592eaa8db74c4b9760d13c4b8d9d3a38d0cb0adb439d91045","observation_id":"97e3ad22-2d7f-4928-8382-9b0b0c7cea5c","resolution":{"observed_at":"2026-08-06T18:52:21.721254Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.697481Z","title":"Cloth-changing person re- identification from a single image with gait prediction and regularization","venue":null,"work_id":"8b3fbaa3-9491-4a5b-b504-4954c7d80a20","year":2022},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.718185Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:0883e7175268c79e10e1d6d8ea2ba4917725f3a070ad33a87579df3d66480b35","observation_id":"1faf1dd3-10a0-4770-96e0-dfefad9a4428","resolution":{"observed_at":"2026-08-06T18:52:21.702700Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.03326","last_updated":"2024-10-26T16:35:13Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-08-06T17:59:44Z","title":"LLaVA-OneVision: Easy Visual Task Transfer","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.03326","snapshot_observed_at":"2026-08-06T18:52:20.722629Z","title":"Llava-onevision: Easy visual task transfer","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.722629Z"},"links":{"cited_paper":"/paper/2408.03326","citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:9cccc618fdb3633ff9833b6659c543993ed57e885641a44f80f54e081750281b","observation_id":"100710cb-b314-4f3c-a0ce-f5f776bcc86c","resolution":{"observed_at":"2026-08-06T18:52:20.722629Z","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":"2026-08-06T18:52:21.680815Z","title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","venue":null,"work_id":"ac733a2c-f8fb-4032-b69c-6a0861f9bf93","year":2023},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.727597Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:c6d0a5bdc54b67f9db9a769eda1dfddf093435e2f58102af6a8cda6a306cc5b7","observation_id":"28900edd-db8d-4755-b977-b85efdee0b34","resolution":{"observed_at":"2026-08-06T18:52:21.686277Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.662961Z","title":"Clip-reid: exploiting vision-language model for image re-identification without concrete text labels","venue":null,"work_id":"d9516c10-8539-44ac-b576-d5212db18f6a","year":2023},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.732131Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:7ac4fa3a7f80804e551037a831c8d01e9c35524d8e38a64dff9f7f8bd01fc472","observation_id":"695a82be-a134-4f44-b0ec-abab7919c9e1","resolution":{"observed_at":"2026-08-06T18:52:21.668984Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.646858Z","title":"Gaitedge: Beyond plain end-to-end gait recognition for better practicality","venue":null,"work_id":"1142e083-2bf0-45b3-a52a-d9af86cf4196","year":2022},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.736737Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:afdab20763522d91ef9bd68835ab2feafc498825f1354b70f5e84bf5f31dce9b","observation_id":"c9a65634-11c9-4bef-b4a8-1e2a182e1e62","resolution":{"observed_at":"2026-08-06T18:52:21.651890Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.628932Z","title":"Differ: Disentangling iden- tity features via semantic cues for clothes-changing person re-id","venue":null,"work_id":"5dc16870-3903-4fc3-bd1e-85c8b395311f","year":2025},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.741485Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:ba2e82e03837ae209015bc665b0659ac8566a37276ab83c143bd2f7e7a38215d","observation_id":"b7648811-badc-4ed3-8268-91685944a667","resolution":{"observed_at":"2026-08-06T18:52:21.634111Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.611723Z","title":"Gait recognition via effective global-local feature representation and local tempo- ral aggregation","venue":null,"work_id":"7542a845-ce6b-4e68-9d92-9ef24b3307b3","year":2021},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.745901Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:ef099554ab578fb6011dbb4aa5662836794cb7b6da3430e9dbe6392ef368d8ec","observation_id":"dd83f67d-7650-450d-8b7e-2dbfaec87844","resolution":{"observed_at":"2026-08-06T18:52:21.616558Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.595804Z","title":"Visual instruction tuning","venue":null,"work_id":"f7a3efdf-a042-479b-838a-54ba10a97392","year":2023},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.750437Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:4408e79e59e82265c07d2c78871ab87577779eb97c2291ca56690191c5fcd6f9","observation_id":"a7640542-0ce7-4820-bbdd-3c2de310279a","resolution":{"observed_at":"2026-08-06T18:52:21.600703Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.577399Z","title":"Deeply coupled convolution–transformer with spatial– temporal complementary learning for video-based person re- identification","venue":null,"work_id":"fd4618fb-1370-44a3-9faf-2437b075a3cc","year":2023},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.754799Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:426767b624e57e24994bba7ad76f2b43515126c28937f9dff218c3a99cc357df","observation_id":"a2efec4c-02d6-4234-8d5c-3c510ea7698d","resolution":{"observed_at":"2026-08-06T18:52:21.583472Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.558927Z","title":"Magface: A universal representation for face recognition and quality assessment","venue":null,"work_id":"ae03837d-316a-4efc-ba1f-673c86a85394","year":2021},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.759342Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:878edc4ecaeaaa252339848d20b665c96a6ee17221fdba3870c66a5959a6c45a","observation_id":"70382ac3-c9eb-4b2d-8048-c1ec8a042cf6","resolution":{"observed_at":"2026-08-06T18:52:21.564542Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-06T18:52:20.763563Z","title":"Gpt-4 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.763563Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:f3bae70be12419abbfc78a0c37aca6392faba129a28b5232bc488d39f2df662d","observation_id":"3df67c21-27ed-4211-b313-2c5534728366","resolution":{"observed_at":"2026-08-06T18:52:20.763563Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2011.13475","last_updated":"2021-03-22T17:06:19Z","snapshot_observed_at":"2026-08-09T19:02:39.825429Z","submitted_at":"2020-11-26T21:04:17Z","title":"Fine-Grained Re-Identification","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.13475","snapshot_observed_at":"2026-08-06T18:52:20.768624Z","title":"Fine-grained re-identification","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.768624Z"},"links":{"cited_paper":"/paper/2011.13475","citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:d963a0d9d97b2f30099c2f4900cdede418ed6b7028a064319d5ec301d1e172a9","observation_id":"673a657d-d8b9-4d67-8182-175420bdcab8","resolution":{"observed_at":"2026-08-06T18:52:20.768624Z","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":"2026-08-06T18:52:21.543420Z","title":"Colors see colors ig- nore: Clothes changing reid with color disentanglement","venue":null,"work_id":"be358f9b-f9d2-4d62-b2ac-09a6cdfc0bce","year":2025},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.772890Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:a849303020a1e8a33a9bbda9421e30d5084c0ef0bea7167ad9459a84d1f82759","observation_id":"177c4138-0132-47a1-9426-26b309dc3283","resolution":{"observed_at":"2026-08-06T18:52:21.548361Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:20.777628Z","title":"Coarse attribute pre- diction with task agnostic distillation for real world clothes changing reid","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.777628Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:14e07f3cabe7a518c0d101f5b2ecb7ab1e3ade9dbd1f8abe37f6ecc7dd8756df","observation_id":"e92f2951-cea4-4c54-a52b-0975561cf2cf","resolution":{"observed_at":"2026-08-06T18:52:20.777628Z","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":"2026-08-06T18:52:21.526624Z","title":"Video person re-id: Fantastic techniques and where to find them (student abstract)","venue":null,"work_id":"660b0745-da31-4efd-b056-9d1bd726ca4c","year":2020},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.783374Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:35502ae3dcbce37f4e3ecfd1824f0c31ca1a3d5b11ab76e896e1d798fdf4cfdc","observation_id":"9d5f5162-185f-4a8a-a1d9-f0f33dabb023","resolution":{"observed_at":"2026-08-06T18:52:21.531391Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.510519Z","title":"Robust re-identification by multiple views knowledge distil- lation","venue":null,"work_id":"81d5a67e-431e-4ca8-b325-fe839e922600","year":2020},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.788061Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:d5cecf8aa90b2779d6d532d31fb44afc2d0ebc7d179b91376972162ebab25127","observation_id":"85d1dbc6-2d42-45a0-9fb4-2f76b374716f","resolution":{"observed_at":"2026-08-06T18:52:21.515359Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.494392Z","title":"Long-term cloth-changing person re-identification","venue":null,"work_id":"e8b34b8d-208a-4006-8109-087ca6673eda","year":2020},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.793942Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:c634aa946d79a07a8d7ddd9b760a84c57aea31751772138b4e49d19f8620e1b0","observation_id":"688b3cac-8471-4db8-beff-c580816fda0b","resolution":{"observed_at":"2026-08-06T18:52:21.499343Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:20.799514Z","title":"Learning transferable visual models from natural language supervision, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.799514Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:ca43ec8b2b39548c2d357825e85d56fc1ee8aadaa428001f551fa2cfbbef9e29","observation_id":"25db6be3-e4f6-46da-9869-70f7833884a7","resolution":{"observed_at":"2026-08-06T18:52:20.799514Z","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":"2026-08-06T18:52:21.466604Z","title":"Probing conceptual understanding of large visual-language models","venue":null,"work_id":"f47e2710-2d10-45f9-8f16-2ade2c6c804f","year":2024},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.805289Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:b6cc07b07ff9f2a1b91ef49acd5d54bfa205d0e86feb349ca974845f2d06761c","observation_id":"64548b82-6860-4b8a-9ee6-42885761ba61","resolution":{"observed_at":"2026-08-06T18:52:21.471425Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.450121Z","title":"Robustness analysis on foundational segmenta- tion models","venue":null,"work_id":"dc7d9e0f-1252-41d2-9d6b-5283ac6eaed9","year":2024},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.811621Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:dcdf9cee9e2dd2b1d1292038f509a6b6ac51a1d81171043658ebc03303250a86","observation_id":"e56bdcc5-aaad-46d1-8897-f7db02d25f9c","resolution":{"observed_at":"2026-08-06T18:52:21.455566Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15389","last_updated":"2023-03-27T17:02:21Z","snapshot_observed_at":"2026-07-06T15:08:34.018146Z","submitted_at":"2023-03-27T17:02:21Z","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15389","snapshot_observed_at":"2026-08-06T18:52:20.816533Z","title":"Eva-clip: Improved training techniques for clip at scale","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.816533Z"},"links":{"cited_paper":"/paper/2303.15389","citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:2d91c1c766f2b693a7c55b04eeab5b2e244abcb0609c73488495e9f750a0fbf8","observation_id":"6bb3c8f8-6695-4c19-b84b-332a9eae0e47","resolution":{"observed_at":"2026-08-06T18:52:20.816533Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.18111","last_updated":"2026-05-11T16:39:12Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-11-27T07:45:25Z","title":"When Large Vision-Language Models Meet Person Re-Identification","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.18111","snapshot_observed_at":"2026-08-06T18:52:20.821736Z","title":"When large vision-language models meet person re-identification","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.821736Z"},"links":{"cited_paper":"/paper/2411.18111","citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:390717e12fe5b63e72cd9610421d7fbdb615b85237b43f0bd8466242bbd6fa91","observation_id":"32e9a0a2-1f01-498a-9e29-cb6ab7cd875c","resolution":{"observed_at":"2026-08-06T18:52:20.821736Z","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":"2026-08-06T18:52:21.434693Z","title":"Pyramid spatial-temporal aggrega- tion for video-based person re-identification","venue":null,"work_id":"fdea9faf-ec3c-4fe8-93c0-f737f8cd2d1d","year":2021},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.830776Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:54d4a22acf07ed439c20a9ab48af9a48b079a2936553c880e86d6cd7f066cd3a","observation_id":"42c5dec4-0f81-4b98-b321-0f052d77f7b0","resolution":{"observed_at":"2026-08-06T18:52:21.439301Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.418458Z","title":"Internvideo2: Scaling foundation models for multimodal video understanding","venue":null,"work_id":"1374a838-a1d2-4953-81a2-fc32d15e23cc","year":2024},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.835243Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:1ed6470e4678857bfc5b3eda6fc9186116e2d0a48ae7775ffa54ae62e873ca2b","observation_id":"a2840999-9e11-4a29-a8f9-be66d751dab6","resolution":{"observed_at":"2026-08-06T18:52:21.423355Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.402478Z","title":"Clip-driven fine-grained text-image person re-identification","venue":null,"work_id":"1de49702-5a4d-4a85-8408-e36c2b580c41","year":null},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.840721Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:7264fa75b541a2d8855b92923cbb565cc6515a568eb4a5f7da7dbd5dc04b77dd","observation_id":"5ea083a2-84e3-432d-8bca-415e56983242","resolution":{"observed_at":"2026-08-06T18:52:21.407333Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.386220Z","title":"Person re- identification by contour sketch under moderate clothing change","venue":null,"work_id":"8ab8bdef-1410-4a2f-bad7-f1a0c1392145","year":2019},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.849189Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:d6a8634308d1ef2eb82b4a595829477b1c3cb8dc844c401d85f21ebe7ea53c0a","observation_id":"c34730f0-e68d-4390-a2f4-38870f14dbd5","resolution":{"observed_at":"2026-08-06T18:52:21.391563Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.369391Z","title":"Good is bad: Causality inspired cloth-debiasing for 10 cloth-changing person re-identification","venue":null,"work_id":"6758d349-8654-4392-97f1-aff39fe63026","year":2023},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.853797Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:e55a9bba291ded7b92768c92a27224ced1863c9b8d9027540148e11b9413507e","observation_id":"f2e867bf-8a5d-4ff0-91e2-e6d97b0da61d","resolution":{"observed_at":"2026-08-06T18:52:21.374444Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.353102Z","title":"A pedestrian is worth one prompt: Towards language guidance person re-identification","venue":null,"work_id":"205c5b5f-3cfe-498a-8702-006f441aa0e4","year":2024},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.858437Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:d8dd6b4dd42a8a72f7a8d8c204a5350c471f4cfe4d78dd00aefb545b711c82a1","observation_id":"462ef686-4e84-4035-baa9-02348c373778","resolution":{"observed_at":"2026-08-06T18:52:21.357915Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.335787Z","title":"Deep learning for person re- identification: A survey and outlook","venue":null,"work_id":"84fddc53-d72c-4307-8819-0b01efe6a952","year":2021},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.863384Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:269f5d2f5226a585d041e1caf085910fb9b25838b32a02f329b6b57aed3c0c55","observation_id":"2e224dd9-5f17-43ff-96df-dc857658eb70","resolution":{"observed_at":"2026-08-06T18:52:21.341375Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.318131Z","title":"Tf-clip: Learning text-free clip for video- based person re-identification","venue":null,"work_id":"e143dc19-6394-4f36-856a-8ae20355dd9b","year":null},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.869009Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:631edf7dab9e15da85b9f476c59c027ee4cf83e8c0510523be4bfc5dc1d6382a","observation_id":"0811c2ba-779c-4fce-9afc-410c2b74efbb","resolution":{"observed_at":"2026-08-06T18:52:21.323546Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.301731Z","title":"Multidirection and multiscale pyramid in transformer for video-based pedestrian retrieval","venue":null,"work_id":"47eefd9d-14bd-4082-b730-3da43b0d1cda","year":2022},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.874549Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:4f28a14ed79426e4ead10e42b0a572a6a8fd5141d58c253e9d37b1ce6ad80069","observation_id":"37bf8db4-8d20-4668-ac8d-f9651490916f","resolution":{"observed_at":"2026-08-06T18:52:21.306655Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.285448Z","title":"Sigmoid loss for language image pre-training","venue":null,"work_id":"398ae75d-26f3-4a51-8445-32581e89cee6","year":2023},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.879569Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:fa5e64cb00595e270a311785623667c6423d2750a0916763fbab29f85e030739","observation_id":"391e62b5-b454-4737-a041-a37e78690b4c","resolution":{"observed_at":"2026-08-06T18:52:21.290385Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.10592","last_updated":"2023-10-02T16:38:35Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-04-20T18:25:35Z","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.10592","snapshot_observed_at":"2026-08-06T18:52:20.884202Z","title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.884202Z"},"links":{"cited_paper":"/paper/2304.10592","citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:4ac22eb9fbfa19d2c5a5e67a039738292c0aaca3059d1308dcb1027402f29965","observation_id":"d4862713-91ea-44af-8bec-17aa3e1eecbc","resolution":{"observed_at":"2026-08-06T18:52:20.884202Z","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":"2026-08-06T18:52:21.268583Z","title":"Sharc: Shape and appearance recognition for per- son identification in-the-wild","venue":null,"work_id":"a60baaba-0ee5-429d-a6cb-c959a9b0caba","year":null},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.888797Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:eb1ffce4e9ad9918c8651d72c54a46a77ffe069d34c12d59d3ef974660df085f","observation_id":"8846d348-e5e6-452c-92c9-677dc47e5b20","resolution":{"observed_at":"2026-08-06T18:52:21.274285Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.881408Z","title":null,"venue":null,"work_id":"92a555d8-b897-4ba9-a842-715cd8db05c4","year":2020},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":243,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.667733Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:9f8788418cd17697bc3017f1aba778adc44e43c86f20ab1feb9f8620b9de7433","observation_id":"1d890aac-24ce-4825-bcf8-9a8ab2e2c92f","resolution":{"observed_at":"2026-08-06T18:52:21.886412Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-06T18:52:21.251462Z","title":"a [body shape] person","venue":null,"work_id":"c3d8dcee-69e1-4c0c-ae94-898b3cabd743","year":null},"citing_paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-06T18:52:20.893254Z"},"links":{"citing_paper":"/paper/2507.07262"},"observation_digest":"sha256:bd96eedaa7235964da83cbf0b6e29dd6af6e508949a6e2a1d19a70679decb42e","observation_id":"5d7634c6-8a65-4646-afa3-c9b832aa0d85","resolution":{"observed_at":"2026-08-06T18:52:21.256823Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.07262","last_updated":"2025-07-09T20:16:16Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T18:42:57.629756Z","submitted_at":"2025-07-09T20:16:16Z","title":"DisenQ: Disentangling Q-Former for Activity-Biometrics"},"reference_resolution":{"displayed":64,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":1,"unresolved":11,"verified_exact":0,"verified_fuzzy":52},"total_outbound_references":64},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 64 of 64 outbound references and 0 inbound Pith citation observations for arXiv:2507.07262."}