{"as_of":"2026-08-18T10:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0046de6edba9fc7f33735b0661ae48e01e44654dddaacdd2af5e9caae65fb7fb","coverage":[{"denominator":38,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":38,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-12T05:07:47.077399Z","state":"measured"},{"denominator":39,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":39,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T23:39:12.146803Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-15T23:39:12.175553Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"cited_work":{"arxiv_id":"2607.03068","doi":null,"metadata_source":"pith","pith_arxiv_id":"2607.03068","snapshot_observed_at":"2026-08-15T23:39:12.175553Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","venue":"cs.CV","work_id":"02d60093-c080-4031-9343-1ee1556ce6fb","year":2026},"citing_paper":{"arxiv_id":"2608.12773","last_updated":"2026-08-13T03:31:31Z","snapshot_observed_at":"2026-08-16T23:10:58.663823Z","submitted_at":"2026-08-13T03:31:31Z","title":"CW-BASS v2: Saturation-Aware Pseudo-Label Selection for Semi-Supervised Segmentation under Foundation-Model Teachers","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T23:39:12.146803Z"},"links":{"cited_paper":"/paper/2607.03068","citing_paper":"/paper/2608.12773"},"observation_digest":"sha256:efadcea03437f271a9cb4d3022fb94b58ed6d78063a4519a1c5c87260d696063","observation_id":"3bf27dfc-a081-4a76-803f-ed8099cfd0c7","resolution":{"observed_at":"2026-08-15T23:39:12.181503Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2607.03068/citation-record","integrity":"/paper/2607.03068/integrity","json":"/paper/2607.03068/citation-record.json","paper":"/paper/2607.03068"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T05:07:47.077399Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:9d6afeed0a597089ad33b5f6d8cbba2bb4a963b1d55d024c0c3e5613c82c2ed3","observation_id":"825c4c32-a768-4f5e-a4f3-7e66de252d98","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"Learning imbalanced datasets with label- distribution-aware margin loss","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:8def123db887a4e3172c6f0abb70cc409e94ef2c1ae255d7e3245f8c6a79b8a5","observation_id":"a2467164-5de9-4a40-8e70-37b7ff434242","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"Softmatch: Addressing the quantity-quality tradeoff in semi- supervised learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:4b1d7ecaa87d7dcf87ee05b462223f0ee7f6eb653517bb94bb709e38668e7923","observation_id":"b9e83dff-4e07-454f-b5a8-151387479306","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"Semi-supervised semantic segmentation needs strong, varied perturbations","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:cb35bf0600cbe241300fdaac31d6776604c175800a54b89fe14bb5b8e6a13937","observation_id":"03f49a6f-7bb6-40e8-a82c-c9e0449be47d","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.07691","last_updated":"2025-05-12T15:58:08Z","snapshot_observed_at":"2026-08-15T22:08:02.160217Z","submitted_at":"2025-05-12T15:58:08Z","title":"Feedback-Driven Pseudo-Label Reliability Assessment: Redefining Thresholding for Semi-Supervised Semantic Segmentation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.07691","snapshot_observed_at":"2026-07-12T05:07:47.077399Z","title":"Feedback-driven pseudo- label reliability assessment: Redefining thresholding for semi-supervised semantic segmentation.arXiv preprint arXiv:2505.07691, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"cited_paper":"/paper/2505.07691","citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:670df933475caf0c5ad15007aab34e12ad2b634bbd0209c8d759eba4614bac6b","observation_id":"9c38e035-9230-403f-8de8-37190fade14a","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:4f1da6d08fc19ebf8753ea844b8889544fdf4aaf79a83b3aa221a620f29a5767","observation_id":"2caf7f9a-7cae-4038-95bf-435b6b33310e","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"Re-distributing biased pseudo labels for semi-supervised semantic segmentation: A baseline investigation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:1bd8d61cae61c21c251feda0212dc326947de8c77c23e6fd3541f95dea0c02a1","observation_id":"8a510cf7-f173-427e-8bfc-d5de6fca2313","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"Beyond pixels: Semi-supervised semantic segmenta- tion with a multi-scale patch-based multi-label classifier","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:5b25f8ff8c9b723a1455bf2a051de682c18dff8a1ed54ed1aa5c05055ab3aaa9","observation_id":"094af108-caf7-47a6-8c63-d9d4db84a995","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"SemiVL: Semi-supervised semantic segmenta- tion with vision-language guidance","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:328e65a8557fd69236a9b8321f6aa5b4cf7408b3b7740c929f99673b7b0669d4","observation_id":"7e2f580d-5fc2-465f-ab6d-033d7fcd1d23","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"Semi-supervised semantic segmentation via adaptive equalization learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:38b3adf88763f44275783eb22b4f46ddfb69999cc9497484868b52985ba20105","observation_id":"05b80ae6-6fdc-4232-9fa1-b1f94d6b8f6b","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"Semi-supervised semantic segmentation via gentle teaching assistant","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:db25dce3f32342fbdaeaea05b606a33f72e78423a08061d4045355dbd8ca9865","observation_id":"d178719e-c374-49dc-9cd8-35d287d77a95","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.11606","last_updated":"2023-03-21T05:56:53Z","snapshot_observed_at":"2026-08-17T08:01:04.741193Z","submitted_at":"2023-03-21T05:56:53Z","title":"CAFS: Class Adaptive Framework for Semi-Supervised Semantic Segmentation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.11606","snapshot_observed_at":"2026-07-12T05:07:47.077399Z","title":"CAFS: Class adaptive framework for semi-supervised semantic segmentation.arXiv preprint arXiv:2303.11606, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"cited_paper":"/paper/2303.11606","citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:d99cdd8cc62d7f38c2007946a65604ff0433de216b56a343ddfdc873d13183b6","observation_id":"689a2535-30ce-4417-ac57-1518613daf59","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"Supervised contrastive learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:3610d4cd980c235ce19ef381d96c8764b8339d60f2cf34fea468e1f496d10cc2","observation_id":"52769978-5d15-46ac-a5ce-b3180e2a1cee","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"Ro- bust pseudo-label learning for semantic segmentation: An encoding perspective.arXiv preprint arXiv:2512.06870,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:2d2ec4b56d129d1715308869cde8b248916ae31bb939aa433b53d49f9ea2524e","observation_id":"4a7f656e-da7f-4ab7-89ce-cc59ab9952b1","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:336f347c4906aac4d9776852f2704faa953518abf61f638287c7a11f1a3eb004","observation_id":"e687feb5-ed1c-4627-b1e8-ae46306ccc68","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"Perturbed and strict mean teachers for semi-supervised semantic segmenta- tion","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:0515a54357d71aaef991e2bcb689e73dcd2cd6780e92229f57710193ebe77124","observation_id":"6cd77941-ed7e-4bdc-b2aa-34771f6487ea","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"Improving semi-supervised semantic segmentation with sliced-wasserstein feature alignment and uniformity","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:d3eb8f562053f02dd2d26b141242f2affea3fd6d79f94018da432698c0b5b316","observation_id":"949a8526-c6f3-409b-9cd2-e1e1242c98a6","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"RankMatch: Exploring the better consistency regularization for semi-supervised semantic segmentation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:03cbbbb0f4a61c0c4d3f677526ac885018acecede780c34f1747cbf05cd8918f","observation_id":"98d87ba7-d5d4-4b27-98f9-92ed3001d418","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"V o, Marc Szafraniec, et al","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:1037f93e01990b696728e5fbdc7c2bd7151e4825b5879934e76e04645646fe19","observation_id":"78acc956-46c2-47e7-8686-eb466e75108a","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"Vi- sion transformers for dense prediction","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:4e41d0b0ba957a1996b4874c6d58b64efcdb4ce2214b94981b33e11303f37829","observation_id":"9ed9255e-6501-4b34-baf6-b411ec1aea7c","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"PrevMatch: Revisiting and maximizing temporal knowledge in semi-supervised semantic segmenta- tion","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:4eeb1cfa02cdd8050c0dae2a83ccc8a57fe79bfa2a604c8d3c901334eda9e1a5","observation_id":"a3b9ffab-f164-4a66-8adf-7bb1df283709","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"Fixmatch: Simplifying semi-supervised learning with consistency and confidence","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:17b5a8e6c343df3ab86c532d2e71d0b47f7d800f6af5cbbe942a71e65187396b","observation_id":"735458e2-c64b-45af-b467-ddc3ec170d55","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"DAW: Exploring the better weighting function for semi-supervised semantic segmentation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:228b3c38a1d4ae90a21d936120fbb19d2794a81e2acc23608d2be49fb08315c7","observation_id":"2baca6d7-56b5-48cb-a8cd-32ba93ed2dd2","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"CorrMatch: Label propagation via correlation matching for semi-supervised se- mantic segmentation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:2981973922487880d646b88383e95017867159fcb072b112e1239e4dc298cc41","observation_id":"4a04f8ba-38a4-433a-8960-d62d13596ed5","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"CW-BASS: Confidence-weighted boundary-aware learning for semi-supervised semantic segmentation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:4d4de16dc530b190f37cb362d31f27973762b0522642af90f003da5e0164746f","observation_id":"84ab47b0-c0ee-47a7-b013-7ccb8b410780","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:1e7cd533493e123ff0d93799f4079c634b31bf6d18c1cf2151291c66f1a483cb","observation_id":"231ebb8d-d1bb-43ef-9a04-df83749ef003","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"Seesaw loss for long- tailed instance segmentation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:161cfd4716744806f0b1d150f7fb07c9a23d1975d931d0dd3a13bbf54f37873b","observation_id":"d5ce9b08-4a82-4861-a569-bea025190cb4","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"Towards the uncharted: Density-descending feature perturbation for semi-supervised semantic segmentation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:7c3cfb6ae5df68ec9852e1fd5cc2b4fd084ff3a0386602960cfeb53273315f56","observation_id":"8d97651d-dc2b-425a-af82-c7c537814a45","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"Semi-supervised semantic segmentation using unreliable pseudo-labels","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:bb4394d5a64fb6e7799c43e9160b99f6049eb5ed5260ab4ad3abc37276673591","observation_id":"2c9f2d45-42f1-48c7-8c1e-f9685e884159","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"Freematch: Self-adaptive thresholding for semi-supervised learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:63b865344db617100d0e481489e29652c2f36954ed5a20c1722c9e25dd5c6792","observation_id":"6477392f-1cd7-4009-a917-c0c1fe1f3ca0","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"CReST: A class-rebalancing self-training frame- work for imbalanced semi-supervised learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:14aadf3700c0d8df2a238eb46aa8c921b880ea32d2840c03853fe98938d3adc7","observation_id":"2499fd39-52c7-4420-9f9a-f17b6f3506fa","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"Allspark: Reborn labeled features from unlabeled in trans- former for semi-supervised semantic segmentation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:d1afbf28e552a3d511db85dcdfa2864ea7bd120c74bda490bd18c024b0f999ea","observation_id":"abf9368b-d646-4506-92a2-3b619cddce24","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"St++: Make self-training work better for semi-supervised se- mantic segmentation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:bd37dd1181cc04ce24ac44f34213d456257e42b4030a9f043463bca9cbcc2f9a","observation_id":"9d07f8eb-6cf8-411f-bf64-617a5f27a0f5","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"Revisiting weak-to-strong consistency in semi-supervised semantic segmentation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:81ccfa4bccc96fba4d0c79933da245aef3b3a710f34c0064d386395729c91c93","observation_id":"ff44dd93-db26-4ce0-945d-214242b87bfa","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"UniMatch V2: Pushing the limit of semi- supervised semantic segmentation.IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:699a74690d54269ca2f7a69815c6126fbc173a4406ddd1ca61eb67ce1d7f1737","observation_id":"1f4ed6b2-70e7-481e-a9de-b03c4eda5dd2","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"Flexmatch: Boosting semi-supervised learning with curricu- lum pseudo labeling","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:e81af9e25479bb7e3a9cc245a62bf4fbc4176f4ca8c2b19fe69a4ff1e3efbc16","observation_id":"06417ae9-e1d9-47cd-9ab3-b7b51dd121a5","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"Instance-specific and model-adaptive supervision for semi-supervised semantic segmentation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:b45497f22afab4d40e541654bae3f54ce10c0c9d41fb0af67da5f9acd6ccbf99","observation_id":"85446d5b-bc0d-44ea-b104-793ab0c1f933","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","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":"2026-07-12T05:07:47.077399Z","title":"rare classes have lower confidence and should be given lower thresholds to admit more of their pseudo-labels","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-07-12T05:07:47.077399Z"},"links":{"citing_paper":"/paper/2607.03068"},"observation_digest":"sha256:27c87bf484e05ce236bc02d6a460ce08292ac7da9ea66724344f9ba6381492c9","observation_id":"c5f04651-e4fc-448f-9d78-231787c4ab99","resolution":{"observed_at":"2026-07-12T05:07:47.077399Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.03068","last_updated":"2026-07-03T08:01:37Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-17T23:25:33.488077Z","submitted_at":"2026-07-03T08:01:37Z","title":"PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation"},"reference_resolution":{"displayed":38,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":37,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":38},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 1 inbound Pith citation observation for arXiv:2607.03068."}