{"as_of":"2026-08-10T07:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:adf33a30c6793974143ce61571b9a91c14f3571d190124bdaecdb7dd939758ee","coverage":[{"denominator":78,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":78,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T05:11:16.777182Z","state":"measured"},{"denominator":78,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":78,"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/2506.08694/citation-record","integrity":"/paper/2506.08694/integrity","json":"/paper/2506.08694/citation-record.json","paper":"/paper/2506.08694"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:11:17.978790Z","title":"Learning to see by moving","venue":null,"work_id":"1ca6eaa6-af50-4343-a7c7-9847152d1041","year":2015},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.344759Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:7e22b91e1c109cd2c2af69c42068a1224ad3b6d6aff2750b77a49037d896210c","observation_id":"a5ad3b01-0073-470b-8895-ab081bb1d9a9","resolution":{"observed_at":"2026-08-07T05:11:17.982977Z","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":"2026-08-07T05:11:17.964845Z","title":"Dense unsupervised learning for video segmentation","venue":null,"work_id":"9af759bf-0011-46ef-96d8-bf87353c9909","year":2021},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.349567Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:9ba61efda5fc7b04370421ea56b6417af0f8da62db389932039c8842220e6299","observation_id":"db4cc989-9d1e-4b3f-9ce7-58e9ba9648bd","resolution":{"observed_at":"2026-08-07T05:11:17.969157Z","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":"2026-08-07T05:11:17.949944Z","title":"Self-labelling via simultaneous clustering and repre- sentation learning","venue":null,"work_id":"8c6fd984-9825-4aff-9096-b35045186106","year":2020},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.354007Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:60871cec0127f1d7226c846ab37a540319ad6c89c00f5f957c07c1e1fef84b12","observation_id":"13c712f3-8021-44a6-8684-a7ca781683c7","resolution":{"observed_at":"2026-08-07T05:11:17.954958Z","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":"2026-08-07T05:11:17.936027Z","title":"Self-supervised learning from images with a joint-embedding predictive architecture","venue":null,"work_id":"54171891-db36-4071-b1ad-2080b0ae860b","year":2023},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.358686Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:8eb2915808556a8c0b13e29beb7bff5df59098722a34a278ab7c8576d700950d","observation_id":"5fa130ba-ff4b-4ec3-85d2-d5da205a0a1e","resolution":{"observed_at":"2026-08-07T05:11:17.940502Z","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":"2026-08-07T05:11:17.921628Z","title":"Towards in-context scene understanding","venue":null,"work_id":"a5578786-788d-43d7-a8cb-977dc1a0c7de","year":2023},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.363535Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:bf953a28d66a08acb4d04277085d767534e8c5eb8cf6900ef52db5a40778a454","observation_id":"7204653e-6ade-4389-96c9-0f28de26aebf","resolution":{"observed_at":"2026-08-07T05:11:17.926305Z","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":"2026-08-07T05:11:17.907270Z","title":"Object discovery from motion- guided tokens","venue":null,"work_id":"8d2c0237-41d4-4c7a-b4b9-ce35fa49c1d3","year":2023},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.368083Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:71df27b36695f731f8e0b94dda74889a0d11f76f1671a11b95603acb0b19e655","observation_id":"1d675641-6f7d-4735-975b-3f1026a1f410","resolution":{"observed_at":"2026-08-07T05:11:17.911638Z","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":"2026-08-07T05:11:17.892753Z","title":"Revisiting feature prediction for learning visual representations from video","venue":null,"work_id":"f109143a-fa04-4fe4-9892-0ac96f61ef1a","year":2024},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.372643Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:a8ae0ea92df3f03c1689bb9cb99598a3bf6950511644903a11a3e64664133976","observation_id":"d7367ea5-5cdf-469b-9da0-cfb26d39e72d","resolution":{"observed_at":"2026-08-07T05:11:17.897574Z","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":"2026-08-07T05:11:17.877714Z","title":"Coco- stuff: Thing and stuff classes in context","venue":null,"work_id":"e0bf1316-0b0e-4668-a6c3-793228ac3456","year":2018},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.376974Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:4ddf8e46f21f495111e33bb7604b782244ef7bfcc4f3edf49eb550b9d6c19773","observation_id":"27e3189d-ea2a-40a2-ac78-8ffa183f88cf","resolution":{"observed_at":"2026-08-07T05:11:17.882640Z","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":"2026-08-07T05:11:17.863502Z","title":"Unsupervised learning of visual features by contrasting cluster assignments.NeurIPS, 33:9912–9924, 2020","venue":null,"work_id":"a3462b57-4c5f-4507-91f6-0342a7bd4a23","year":2020},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.381113Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:5999cf9bb0f72e846dafcf637c1bc2440302ce8c5c1577a83529a5426b4753d4","observation_id":"6bb67962-346e-422d-8ba9-08e228204557","resolution":{"observed_at":"2026-08-07T05:11:17.867845Z","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":"2026-08-07T05:11:17.848460Z","title":"Emerg- ing properties in self-supervised vision transformers","venue":null,"work_id":"f94fd75b-7913-4d64-a0c6-6e0843ca379e","year":null},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.385355Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:0aec6c612887949649d8929b529db5439595def561cb981757650806f8b031ec","observation_id":"bd9fa9c9-c936-4917-8a25-829f13db9323","resolution":{"observed_at":"2026-08-07T05:11:17.853459Z","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":"2412.15212","last_updated":"2025-07-09T16:58:07Z","snapshot_observed_at":"2026-08-06T10:25:48.518948Z","submitted_at":"2024-12-19T18:59:51Z","title":"Scaling 4D Representations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.15212","snapshot_observed_at":"2026-08-07T05:11:16.394161Z","title":"Scaling 4d representations","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.394161Z"},"links":{"cited_paper":"/paper/2412.15212","citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:e3907c8b0c7e021e52a47c3affd8e0dc06b5c0d9dd3f1fe1e74353fd6c6fe4f3","observation_id":"6cadd0b9-0116-42a5-a924-64ae95092733","resolution":{"observed_at":"2026-08-07T05:11:16.394161Z","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":"2026-08-07T05:11:17.817141Z","title":"Learning from one continuous video stream","venue":null,"work_id":"4e9dfcaf-cb5a-4569-95e1-69c40a4c5e5e","year":2024},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.398634Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:7df3485298a63ee584cbe0bd9b8fb438c27b4afc7af3fdabe4b0c85188c495ba","observation_id":"17c52c79-fbe9-4d4f-a47d-c08096a1b860","resolution":{"observed_at":"2026-08-07T05:11:17.821616Z","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":"1704.04081","last_updated":"2017-04-13T11:54:53Z","snapshot_observed_at":"2026-07-06T05:37:42.496434Z","submitted_at":"2017-04-13T11:54:53Z","title":"Learning to Estimate Pose by Watching Videos","version":1},"cited_work":{"arxiv_id":"1704.04081","doi":null,"metadata_source":"pith","pith_arxiv_id":"1704.04081","snapshot_observed_at":"2026-08-07T05:11:16.937929Z","title":"Learning to Estimate Pose by Watching Videos","venue":"cs.CV","work_id":"844cfe54-3825-4aa9-831a-d066619618da","year":2017},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.402572Z"},"links":{"cited_paper":"/paper/1704.04081","citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:64a370794ce3a069d7cec592277c3f8207a161be4675c7953cab5747642dbd7f","observation_id":"182bfc68-da98-4d00-a92e-cccd108142c4","resolution":{"observed_at":"2026-08-07T05:11:16.942354Z","resolver_source":"local_arxiv","status":"verified_exact"},"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":"2026-08-07T05:11:17.802703Z","title":"A simple framework for contrastive learning of visual representations","venue":null,"work_id":"a65ad32c-ebed-4f08-b1ab-5344ea986ffe","year":2020},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.406975Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:756d2b37e502415df57f1e32458e15c3df77c45e36bb49527bea9c1ab82fca1b","observation_id":"18665462-73c9-4b25-a70b-9114599154f4","resolution":{"observed_at":"2026-08-07T05:11:17.807148Z","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":"2026-08-07T05:11:17.788095Z","title":"Sinkhorn distances: Lightspeed computation of optimal transport","venue":null,"work_id":"77d92101-9713-4534-9f2f-4019fb0a0b88","year":2013},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.411805Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:8c2f48f83fea06a21ee20d38864f2708e7e96d04333674ef0234ea5f1f9ba306","observation_id":"e4968f67-54c4-4ff3-8cd5-49f9246e4267","resolution":{"observed_at":"2026-08-07T05:11:17.792399Z","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":"2026-08-07T05:11:17.773549Z","title":"Vision transformers need registers","venue":null,"work_id":"6ee75af7-780b-4248-9440-9683d2b603d2","year":null},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.416040Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:23040eee4380f04c942ef02d498fc0f7076b2c00a1a6a87bfc43d157c490cccc","observation_id":"c8baf89f-31ea-4a73-885c-fffa72619fc8","resolution":{"observed_at":"2026-08-07T05:11:17.778070Z","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":"2026-08-07T05:11:17.758181Z","title":"An image is worth 16x16 words: Trans- formers for image recognition at scale","venue":null,"work_id":"88fea7c2-b376-4a07-ae74-d9428d8b492b","year":2021},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.420598Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:fdfc395ecc8373e8d2fc15494f25f119032ea85a37cffda94662083c2b775724","observation_id":"fe81c31a-30a0-4439-99e6-5e0372cc285d","resolution":{"observed_at":"2026-08-07T05:11:17.763155Z","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":"2026-08-07T05:11:16.424820Z","title":"Everingham, L","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.424820Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:cabe6bb9bbccc36681e1fdefae735c4ff03f9e834c33ffe07bb3c9a026926ab3","observation_id":"b0b26563-c672-4d4d-9082-8d1708d63281","resolution":{"observed_at":"2026-08-07T05:11:16.424820Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.07990","last_updated":"2020-05-07T17:23:14Z","snapshot_observed_at":"2026-07-06T09:05:25.887402Z","submitted_at":"2020-03-18T00:07:21Z","title":"Watching the World Go By: Representation Learning from Unlabeled Videos","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.07990","snapshot_observed_at":"2026-08-07T05:11:16.428803Z","title":"Watching the world go by: Representation learning from unlabeled videos","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.428803Z"},"links":{"cited_paper":"/paper/2003.07990","citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:a13194c6864b3ad9cdce280beef41a085c824022630c5ad36cff05c477b8e0de","observation_id":"f38531b7-bc40-47a9-a12c-2de4514047d6","resolution":{"observed_at":"2026-08-07T05:11:16.428803Z","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":"2026-08-07T05:11:17.731111Z","title":"Bootstrap your own latent-a new approach to self-supervised learning","venue":null,"work_id":"9b20df21-db13-45d3-87cd-68ed6c51b9e0","year":2020},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.433274Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:684835650506ae164078438dd56d1bd1d312ffbc34f86b6bcad783c3e43f0a4d","observation_id":"ad1bffd2-bc59-4783-bff7-eb3dc005edb8","resolution":{"observed_at":"2026-08-07T05:11:17.735454Z","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":"2026-08-07T05:11:17.716370Z","title":"Accelerating large- scale inference with anisotropic vector quantization","venue":null,"work_id":"b4a5c720-da99-4562-9beb-03c59cec0986","year":null},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.437200Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:8014cb25ca930b5c9ae231072ee1bfa8ddc04b0d3ae068d9b9c95e3f7fadbd9a","observation_id":"a4b75d5e-bc46-46e6-be33-e51189ca23f9","resolution":{"observed_at":"2026-08-07T05:11:17.720995Z","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":"2026-08-07T05:11:17.702385Z","title":"Stego: Unsupervised se- mantic segmentation by distilling feature correspondences","venue":null,"work_id":"2de3a8b7-80e3-4f75-96d4-8448c7d017c4","year":2022},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.441210Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:613c3efaa650546e85e10adc011aa4a6886f3e2e802aefccefc8faf038d28c67","observation_id":"a53d7706-bbb8-465c-ac96-063c5214b8e6","resolution":{"observed_at":"2026-08-07T05:11:17.706719Z","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":"2026-08-07T05:11:17.689075Z","title":"Masked autoencoders are scalable vision learners","venue":null,"work_id":"31854f9c-1b71-436f-af7a-64ed69c5f357","year":2022},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.553434Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:6e8d72b4a4d4d227b91849b0ce3959dfe39642d0eec78fd3d4321e1fd5b69384","observation_id":"4c850888-06f7-404e-b62a-ffc452de6766","resolution":{"observed_at":"2026-08-07T05:11:17.693105Z","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":"2026-08-07T05:11:17.674790Z","title":"Effi- cient visual pretraining with contrastive detection","venue":null,"work_id":"c76e5116-cb63-41f2-a6ea-cff83371fb06","year":null},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.558077Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:ab9b5bbf0104f8a837fa14a7dc5e1594f88a92e386ab572592b039153ddb838e","observation_id":"c2b85fad-14f8-4cda-8c4b-86327cb6f434","resolution":{"observed_at":"2026-08-07T05:11:17.679458Z","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":"1606.08415","last_updated":"2023-06-06T01:53:32Z","snapshot_observed_at":"2026-07-06T05:01:27.910364Z","submitted_at":"2016-06-27T19:20:40Z","title":"Gaussian Error Linear Units (GELUs)","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.08415","snapshot_observed_at":"2026-08-07T05:11:16.562592Z","title":"Gaussian error linear units (gelus)","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.562592Z"},"links":{"cited_paper":"/paper/1606.08415","citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:13110c612c659beb7ee8da27d1b2a7fbadc9c791f0ddd6de942db1287edc681b","observation_id":"a5c58e92-00c2-48f8-9742-110a5eee2ff2","resolution":{"observed_at":"2026-08-07T05:11:16.562592Z","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":"2026-08-07T05:11:17.660914Z","title":"Learning image representations tied to ego-motion","venue":null,"work_id":"d47c5801-c898-4739-a4a0-815a0c725fc3","year":2015},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.566901Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:4165217d17d3bc1abefb48c44ff569352dcecb16e0f956e80bc0e0d1773ec351","observation_id":"ca019319-7844-459f-8274-314d9d032ae8","resolution":{"observed_at":"2026-08-07T05:11:17.665606Z","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":"2026-08-07T05:11:17.646712Z","title":"Invariant information clustering for unsupervised image classification and segmentation","venue":null,"work_id":"e92bc76f-3164-4f6d-9bd2-d3fed8c991e1","year":2019},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.570932Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:f5da5f691fe72dacfbfb56e084c851cfedd9c422df4ea65ed5ba098a6852d065","observation_id":"f511e82b-8247-40e2-9e46-300a8da736e2","resolution":{"observed_at":"2026-08-07T05:11:17.651367Z","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":"2026-08-07T05:11:17.631856Z","title":"Billion-scale similarity search with gpus","venue":null,"work_id":"3e2c0c31-2685-4816-bb7e-357a44b19b31","year":null},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.574922Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:1ef14657a039c541791d694276b1a980837997db48374fba43033414d166eab1","observation_id":"a7711d1b-bfe8-4c1f-adb6-05a36ae1dd27","resolution":{"observed_at":"2026-08-07T05:11:17.637157Z","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":"2410.11831","last_updated":"2024-10-15T17:56:32Z","snapshot_observed_at":"2026-08-03T21:35:04.144048Z","submitted_at":"2024-10-15T17:56:32Z","title":"CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.11831","snapshot_observed_at":"2026-08-07T05:11:16.579883Z","title":"Co- tracker3: Simpler and better point tracking by pseudo- labelling real videos","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.579883Z"},"links":{"cited_paper":"/paper/2410.11831","citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:3de02b8653efadc2880ef5141f05f600a7d90b1bbfd0da2a68ab9085b7f3e051","observation_id":"e59e5412-cf0c-4f2b-98a6-2bbef57d5354","resolution":{"observed_at":"2026-08-07T05:11:16.579883Z","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":"2026-08-07T05:11:17.617359Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":"e4edca30-3845-4350-8cbd-ea0c7c622878","year":2014},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.584233Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:81ce1642a634e07a32c8adff15d0a4a85a6cab8c2250e0e9c33d7ef0001343e7","observation_id":"d7516c09-0e53-41d9-a207-54cbe2550047","resolution":{"observed_at":"2026-08-07T05:11:17.622060Z","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":"2026-08-07T05:11:17.602840Z","title":"Panoptic segmentation","venue":null,"work_id":"a998bc9d-e390-4fd9-bd4c-9bdbffb80525","year":null},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.588575Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:3600b3537b60837ffeae2aad44fc19770d582a9591f6913caa0fc0a04309fa84","observation_id":"024ba598-71be-44b2-9acf-026854c0f055","resolution":{"observed_at":"2026-08-07T05:11:17.606974Z","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":"2026-08-07T05:11:17.588539Z","title":"Principles of Gestalt psychology","venue":null,"work_id":"7e7fdd43-81f4-4567-b697-1c8ac601c292","year":null},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.592610Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:5c8d5cd11d491d8654927fccd7507b73c6d78bcf93af54de1832644e8c293e20","observation_id":"80e8bb61-0d9a-4f2b-8e0e-d8bb0a6c9be8","resolution":{"observed_at":"2026-08-07T05:11:17.593014Z","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":"2026-08-07T05:11:17.574515Z","title":"The hungarian method for the assignment problem","venue":null,"work_id":"022857fc-be5d-46d8-83bb-30c1c6eb04d3","year":1955},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.596880Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:f708dca74342c2c3a1bf1f2996384348fe31aeef6793c568629f5523b4b24081","observation_id":"bcbbafc5-6eba-4a87-87fc-48fee3b381f2","resolution":{"observed_at":"2026-08-07T05:11:17.578783Z","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":"2503.19904","last_updated":"2025-03-25T17:58:48Z","snapshot_observed_at":"2026-08-09T02:08:36.086587Z","submitted_at":"2025-03-25T17:58:48Z","title":"Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better","version":1},"cited_work":{"arxiv_id":"2503.19904","doi":null,"metadata_source":"pith","pith_arxiv_id":"2503.19904","snapshot_observed_at":"2026-08-07T05:11:16.867078Z","title":"Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better","venue":"cs.CV","work_id":"a081ed71-6c4c-4193-af26-1e0a6e1f70fc","year":2025},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.600869Z"},"links":{"cited_paper":"/paper/2503.19904","citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:e2b3592e8534e7ade51fcd26bf8d2297300f7d5b769832ef09bc91a777a78fe1","observation_id":"a473c0fd-6825-48e6-873a-627d4f313e00","resolution":{"observed_at":"2026-08-07T05:11:16.873751Z","resolver_source":"local_arxiv","status":"verified_exact"},"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":"2026-08-07T05:11:17.560078Z","title":"Smooseg: smoothness prior for unsupervised semantic segmentation","venue":null,"work_id":"da247ccf-7ab7-4b1d-b746-9155379b5251","year":2023},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.605423Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:47ef2fdba772ded222ff46ed7b271662ed28dc7c3e5ef793c62c9f03d6ea09eb","observation_id":"eba137e3-08b7-4609-9903-f14dcb06d56e","resolution":{"observed_at":"2026-08-07T05:11:17.564248Z","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":"2026-08-07T05:11:17.545739Z","title":"Cribo: Self-supervised learning via cross-image object-level bootstrapping","venue":null,"work_id":"ce0b5ef4-332c-4231-ab22-13b49da37689","year":null},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.609514Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:688c03b815cae7ff858d4228ef0906e59d44011758f5c07f8167fa5adaa9b504","observation_id":"d3ba9632-e338-4eb8-9358-d6bb24c3e14b","resolution":{"observed_at":"2026-08-07T05:11:17.550456Z","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":"2026-08-07T05:11:17.531154Z","title":"Joint-task self-supervised learning for temporal correspondence","venue":null,"work_id":"6223f132-e5ce-4a4a-ae1f-44e0aee73b54","year":2019},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.613296Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:0c335cbef77b2c9c58cb10cf2423fb1009d5ec99cedd7ab6ddc26190535d2ef1","observation_id":"a3546f6f-fe97-4ece-ad83-fa57bc57fe95","resolution":{"observed_at":"2026-08-07T05:11:17.535958Z","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":"2026-08-07T05:11:17.516160Z","title":"Exploring plain vision transformer backbones for object de- tection","venue":null,"work_id":"af17f59e-413e-46fa-b165-b03da438f26f","year":2022},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.617246Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:f2ef52f1f4fecc503c3de1e1944669e52b9d6955e9d2a1cb30ab5f901b07f4e6","observation_id":"8f6aae2f-212e-48fc-856d-e06f2c018bab","resolution":{"observed_at":"2026-08-07T05:11:17.520544Z","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":"2026-08-07T05:11:17.502309Z","title":"Cross pixel optical-flow similarity for self-supervised learn- ing","venue":null,"work_id":"83c4723b-88be-4cca-8f2b-7888c2737fa1","year":2019},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.621244Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:d6b17dbec478b5478afe08b47feef8c9dd3c6dbc4fae8e6283e084e6a03418a9","observation_id":"20d892ed-61fd-41a7-abed-1acf18153e02","resolution":{"observed_at":"2026-08-07T05:11:17.506619Z","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":"2026-08-07T05:11:17.488361Z","title":"Deep spectral methods: A surprisingly strong baseline for unsupervised semantic segmentation and local- ization","venue":null,"work_id":"b9f90df6-91aa-4b96-a790-08667fd2e813","year":2022},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.625170Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:03300c6b39be097177ec2404f99e2abf12fd49d0d5f6705930db5ad56cdf7bab","observation_id":"ca90867e-2199-49ba-97b0-76f5acbcaa51","resolution":{"observed_at":"2026-08-07T05:11:17.492663Z","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":"2026-08-07T05:11:17.474635Z","title":"You don’t need domain- specific data augmentations when scaling self-supervised learning","venue":null,"work_id":"9079de25-f78c-4a7c-9957-25244c0bf53f","year":2025},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.629073Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:2fdae64064280df7e08d805663e74694bf24b3caa1e416e8b94bff8bf9ebb8d7","observation_id":"06307d59-bc5f-47e5-bb58-1fb7be2b470a","resolution":{"observed_at":"2026-08-07T05:11:17.479018Z","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":"2026-08-07T05:11:17.460666Z","title":"Dinov2: Learning robust visual features without supervision","venue":null,"work_id":"25a1438c-447d-420d-bc0f-fd2dbca8ba7f","year":null},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.633053Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:bed19079652d68229b98875825a388168a3eed72f358b87f71842b42ef63b030","observation_id":"40c384e9-c58a-4f27-8fa2-c8fadf61cc07","resolution":{"observed_at":"2026-08-07T05:11:17.465064Z","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":"2026-08-07T05:11:17.429869Z","title":"Hummingbird evaluation for vision encoders, 2024","venue":null,"work_id":"179dcef4-d5d6-496e-833d-c9dcb78d1152","year":2024},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.641131Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:b6dde2478d16b62a1f7269cc2ec63d0cf00364daf6137f44376b13328841987f","observation_id":"46c00e33-9e1b-4793-87bd-72e64ab2ec32","resolution":{"observed_at":"2026-08-07T05:11:17.434584Z","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":"2026-08-07T05:11:17.414911Z","title":"Burgh- outs, Francesco Locatello, and Yuki M Asano","venue":null,"work_id":"2f37cf22-edea-4a8c-b470-b127a3ecbfb6","year":2025},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.645059Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:cca2f53aa03fdecc523da3d7c42dbbfcb326c0f9c0860966c090f908956d0b15","observation_id":"f08d6650-5ddb-4927-981d-e3bf9a6188b0","resolution":{"observed_at":"2026-08-07T05:11:17.419663Z","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":"2026-08-07T05:11:17.400180Z","title":"Self-supervised video pretraining yields human- aligned visual representations","venue":null,"work_id":"92e91a0d-c37f-4def-a139-e56df0ed005b","year":2023},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.649059Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:0a1a8f0cc52868ca2b0d0223f40afb55a2841fb8d878ae1570c5bfa02cb34345","observation_id":"06c25c65-b837-4448-8265-3baa32594d19","resolution":{"observed_at":"2026-08-07T05:11:17.404662Z","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":"2026-08-07T05:11:17.385448Z","title":"Pytorch: An imperative style, high-performance deep learning library","venue":null,"work_id":"bec87be8-40c6-4398-9dce-fb2424145cf8","year":2019},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.653253Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:413ad03de75eb798338a02b8a788a48ed20709cc40b2b4276f9a768df0d2553c","observation_id":"6e76cce3-ab46-4354-8e92-9760274fbb34","resolution":{"observed_at":"2026-08-07T05:11:17.390213Z","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":"2026-08-07T05:11:17.371048Z","title":"Learning features by watching objects move","venue":null,"work_id":"d206c110-c088-48b2-b0ff-d5e3da76edc5","year":2017},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.657169Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:0830e7b1756a5c68c1f0bd863f687c39c3b60c5572e5a6f2c727eb344bd64fc3","observation_id":"018a3f0d-b30a-4bb2-a9b1-684f116bd56d","resolution":{"observed_at":"2026-08-07T05:11:17.375299Z","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":"1704.00675","last_updated":"2018-03-01T17:50:08Z","snapshot_observed_at":"2026-08-02T10:51:13.194643Z","submitted_at":"2017-04-03T16:44:46Z","title":"The 2017 DAVIS Challenge on Video Object Segmentation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.00675","snapshot_observed_at":"2026-08-07T05:11:16.661333Z","title":"The 2017 davis challenge on video object segmentation","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.661333Z"},"links":{"cited_paper":"/paper/1704.00675","citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:e56f0070471fe5302e745ad6408e3747c4e68de13132c16d51fdcf84f3cf6193","observation_id":"91bbeeca-c0cc-4a4f-8551-29af1a54bbe1","resolution":{"observed_at":"2026-08-07T05:11:16.661333Z","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":"2026-08-07T05:11:17.352498Z","title":"Imagenet large scale visual recognition challenge","venue":null,"work_id":"82dfa2fd-70bf-4c08-962b-ed669c3c36ca","year":2015},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.665561Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:84b7599c895f42fb43d7815a81423d23bfcc6e706aa3b7c27e7a2dfa1e844591","observation_id":"f9bd6061-3bd2-4189-9278-069e379df342","resolution":{"observed_at":"2026-08-07T05:11:17.356844Z","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":"2026-08-07T05:11:17.338696Z","title":"Time does tell: Self-supervised time- tuning of dense image representations","venue":null,"work_id":"649680e0-db68-4bc5-bafa-301d0e53b12f","year":2023},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.669556Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:29e6efdff739ca7aba5e66ce102044f31d186e76a1bdcb3839b6a0d6b2090ad0","observation_id":"54768e16-f69b-4530-a2aa-7265f4dd5a78","resolution":{"observed_at":"2026-08-07T05:11:17.343071Z","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":"2026-08-07T05:11:17.324395Z","title":"Sigma: Sinkhorn-guided masked video modeling","venue":null,"work_id":"306009a9-e40b-4741-97c9-5924e7ac02f2","year":2024},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.673297Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:4f0ac03a2d7d83366a4395e401012ec53e1748e5cc442315829dc3fd7f596783","observation_id":"468c1c08-c59d-4f4b-b3ca-95faf364629a","resolution":{"observed_at":"2026-08-07T05:11:17.328752Z","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":"2026-08-07T05:11:17.310016Z","title":"Bridging the gap to real-world object-centric learning","venue":null,"work_id":"d46f93b2-7d12-498d-b57f-89a389e1d6ad","year":2023},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.677084Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:b9dbedd591acf84f5e7f151e0d0924288225b032203963d9fb314689e787c4eb","observation_id":"58d97206-d89e-4e56-95fb-01237eec1668","resolution":{"observed_at":"2026-08-07T05:11:17.314533Z","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":"2026-08-07T05:11:17.291541Z","title":"Unsupervised object local- ization: Observing the background to discover objects","venue":null,"work_id":"edf88a51-9d50-4bf3-9349-a2b505bb485c","year":2023},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.680768Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:827aed1ddb7c097724645058afa012756ae0db31e15f1fc40b6b224bdcba3df5","observation_id":"84a28121-699e-468a-a265-9a5eedb1135c","resolution":{"observed_at":"2026-08-07T05:11:17.299083Z","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":"2026-08-07T05:11:17.276506Z","title":"Croc: Cross-view on- line clustering for dense visual representation learning","venue":null,"work_id":"fe11f663-e408-4cc2-8a76-f492609491b1","year":2023},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.684843Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:16b0bae613b02a98da7a93dd7eb52687d6cfbef799748ba9da9dcc5e2faa6853","observation_id":"29f0f0e6-13b2-413d-81bd-9e6692d92d32","resolution":{"observed_at":"2026-08-07T05:11:17.281064Z","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":"2026-08-07T05:11:17.261145Z","title":"Segmenter: Transformer for semantic segmentation","venue":null,"work_id":"3f01f798-897c-4b7c-b083-4cb3c4b99a3b","year":2021},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.688822Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:b77b118e65903ed6470a67bed3df5208af8b9acd0e5bb6ef3cc8dbb672c86d13","observation_id":"d07bea08-8e97-4173-8ef5-9f879ca9314c","resolution":{"observed_at":"2026-08-07T05:11:17.265682Z","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":"2026-08-07T05:11:16.692890Z","title":"Eva-clip: Improved training techniques for clip at scale","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.692890Z"},"links":{"cited_paper":"/paper/2303.15389","citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:6efd0e09b281c6cdef661b15115a96182d4e22f3bb9468e76442aa4aec286747","observation_id":"bc506c39-e77a-4291-b75a-640141d90e7d","resolution":{"observed_at":"2026-08-07T05:11:16.692890Z","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":"2026-08-07T05:11:17.245021Z","title":"Video- mae: Masked autoencoders are data-efficient learners for self-supervised video pre-training","venue":null,"work_id":"ac356fa9-41fa-4780-83b8-654d63623e46","year":2022},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.697224Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:6966e0a675b221a64035d5318184ac6b19af8815fa5f47d61b15a916bddd4eb9","observation_id":"8ec3ecf2-11ed-4123-b604-6677ea209f6a","resolution":{"observed_at":"2026-08-07T05:11:17.250126Z","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":"2026-08-07T05:11:17.229825Z","title":"Self-supervised learning of video-induced visual invariances","venue":null,"work_id":"140c707f-1dcd-4ee4-a882-331e45a37911","year":2020},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.701298Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:effea2ce3583f6e5647ad05f5345dab05ccdedc6f26e9275c3de7a905b804aa5","observation_id":"7d6e75bf-e87b-41e7-a7c4-6e54e20b44ec","resolution":{"observed_at":"2026-08-07T05:11:17.234231Z","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":"2026-08-07T05:11:17.215007Z","title":"Unsupervised semantic segmenta- tion by contrasting object mask proposals","venue":null,"work_id":"e403a87f-b869-4b51-9ac4-53679c62aad3","year":2021},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.705200Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:d7d852f2a252c624c69fbd729dc0f4bd59864043273f7df8f2d50cc283769e0a","observation_id":"5a1b87ad-2b2a-4e72-a57f-bbe85675bc0d","resolution":{"observed_at":"2026-08-07T05:11:17.219664Z","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":"2026-08-07T05:11:17.199088Z","title":"Moving off-the- grid: Scene-grounded video representations","venue":null,"work_id":"9a820dc7-d56d-4872-9f8d-47f683a5d15e","year":2025},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.709089Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:c541ead68a58bd3c83cb2f0e89e67ec9a68998fa7eece2f49af5d3f967f27424","observation_id":"edc435a1-3596-40cf-9ec0-7c1dbda3fb45","resolution":{"observed_at":"2026-08-07T05:11:17.203721Z","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":"2026-08-07T05:11:17.183263Z","title":"Is imagenet worth 1 video? learning strong image encoders from 1 long unlabelled video","venue":null,"work_id":"37674c0a-0ef5-4cc6-9098-18be566ef15e","year":2024},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.712994Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:9035edd4dfcdc3b508d531d6857cf8c97b8da46548888eae746a0a49b0bacb64","observation_id":"6f02235c-047f-462f-a6c3-2df10c888b85","resolution":{"observed_at":"2026-08-07T05:11:17.188029Z","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":"2026-08-07T05:11:17.167932Z","title":"Unsupervised learning of visual representations using videos","venue":null,"work_id":"f4747219-cd3d-4cc9-973e-41b8edaaddc9","year":2015},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.717156Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:c52bc786879e717f2917648a5eee2b528d1f2ea91790e69732f4a69bc28086c7","observation_id":"9ce87669-ef66-4924-acbe-c785d8f3a862","resolution":{"observed_at":"2026-08-07T05:11:17.172796Z","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":"2026-08-07T05:11:16.721038Z","title":"Learning correspondence from the cycle-consistency of time","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.721038Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:5af1e52b115fe6ff82f95a4029c0953157b65c3c2ad5df222c58aad390123e57","observation_id":"57dbde63-7b0a-4e9c-b83f-030675d1f989","resolution":{"observed_at":"2026-08-07T05:11:16.721038Z","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":"2026-08-07T05:11:17.142148Z","title":"Self-supervised representation learning from flow equivariance","venue":null,"work_id":"1a554d0c-0d72-408b-bf55-7f484fcf34e3","year":2021},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.725194Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:afc95544eb3fe56b44bfdc0fd89fed453b50e59719783583c37e97088b6b6069","observation_id":"d741a926-4f58-4c2e-bb4e-74e61a587d0b","resolution":{"observed_at":"2026-08-07T05:11:17.146856Z","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":"1809.03327","last_updated":"2018-09-06T04:19:45Z","snapshot_observed_at":"2026-07-06T07:00:12.122241Z","submitted_at":"2018-09-06T04:19:45Z","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.03327","snapshot_observed_at":"2026-08-07T05:11:16.729330Z","title":"Youtube-vos: 11 A large-scale video object segmentation benchmark","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.729330Z"},"links":{"cited_paper":"/paper/1809.03327","citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:0a0673a159a8b5b1e7a6599088792853560960d71dd0df403a4b87b138c7ba67","observation_id":"cfdfe01c-8a54-4f66-95bb-e22002ecb1c1","resolution":{"observed_at":"2026-08-07T05:11:16.729330Z","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":"2026-08-07T05:11:17.126216Z","title":"Patch-level representation learning for self-supervised vision transformers","venue":null,"work_id":"11738e6c-b37d-4497-a2fe-e0254003dc68","year":2022},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.733665Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:28cb1bc152444084e0970a8551e95611e4440f12e041e360368c4831a70fb534","observation_id":"39565b16-58ad-464d-8ce1-0407abde39f1","resolution":{"observed_at":"2026-08-07T05:11:17.131030Z","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":"2026-08-07T05:11:17.111014Z","title":"Unsupervised se- mantic segmentation with self-supervised object-centric rep- resentations","venue":null,"work_id":"e4170c0c-7ab0-4ee1-8e5a-623a36c9303b","year":2023},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.737804Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:6743450519e17a787fcbaad9b4cdaa95ad665e1c665518811008064d54d89d21","observation_id":"555cff07-47cf-4183-b3c5-5a08fde2fefb","resolution":{"observed_at":"2026-08-07T05:11:17.115443Z","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":"2026-08-07T05:11:17.095779Z","title":"Object-centric learning for real-world videos by predicting temporal feature similarities","venue":null,"work_id":"5d2317e7-b68b-4018-b0d4-5b34b4273a33","year":2023},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.741794Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:ed2855c2cf1be9f29bd780b4e12ce341966a1719158424e2c8339f889b5a6432","observation_id":"89c4e8e3-3614-49ee-bc27-bd963e8ac1d1","resolution":{"observed_at":"2026-08-07T05:11:17.100881Z","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":"2026-08-07T05:11:17.081141Z","title":"Scene parsing through ade20k dataset","venue":null,"work_id":"d188c9d8-bf94-4bc8-8a1c-334393763729","year":2017},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.746286Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:3b86beebd8da6f50718bf82890cef363a3f5b26555efb40f63ddef4a14557be4","observation_id":"cb1c8b9f-500d-4f0b-b08a-4fcfd1972e4c","resolution":{"observed_at":"2026-08-07T05:11:17.085705Z","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":"2026-08-07T05:11:17.066394Z","title":"ibot: Image bert pre-training with online tokenizer","venue":null,"work_id":"219bffca-0000-40f1-9406-f12fe9ea1063","year":2022},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.750680Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:6247a0cf547aa3b08c35324b677ce9c73e671a9cc4c7aee37e08008209d6e469","observation_id":"c96bf7d4-82c5-41c0-b6ec-0d19469efa9b","resolution":{"observed_at":"2026-08-07T05:11:17.071068Z","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":"2026-08-07T05:11:17.050296Z","title":"Self-supervised learning of object parts for semantic segmentation","venue":null,"work_id":"182632c2-9cc0-4b8e-afed-095b6c7c311c","year":2022},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.754693Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:6f749d16432a1f580d9a7a914e8f33288af7fb7b635ba749b45795b3d147ff60","observation_id":"58139f79-37c8-49cb-973a-4859850ba563","resolution":{"observed_at":"2026-08-07T05:11:17.055445Z","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":"2026-08-07T05:11:17.029586Z","title":"Additional Experiments Comparison to TimeT","venue":null,"work_id":"29b5f0b3-b68f-4097-afa9-1dd2405040b9","year":null},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.758631Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:cb736fd42c0040dec7095aecee3612c207de8b54f2970b2ac9f07f26c1738a67","observation_id":"6687d7c3-3bce-428c-99d0-4d8e5fdcb97f","resolution":{"observed_at":"2026-08-07T05:11:17.034189Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"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":"2026-08-07T05:11:17.014519Z","title":null,"venue":null,"work_id":"76cd4182-f78f-46df-a3b6-d806174aa367","year":null},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.763560Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:880cc6e5eba231f0947770341b12da69a90d86d390099589b6fd40cd54f0bddc","observation_id":"76863aef-2a0d-4715-9779-3f6b1a9b92f2","resolution":{"observed_at":"2026-08-07T05:11:17.018983Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-07T05:11:16.999415Z","title":"Unsupervised video semantic segmentation results for clustering and over-clustering on DA VIS [48] and Youtube-VOS (YTVOS) [65]","venue":null,"work_id":"6a04e045-8caa-4777-9f15-a4ea2b4ef648","year":null},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.767878Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:f0b4ec98410c7642b721e7bdb9bc18b7127bc89dcc596af8cff36181c2731421","observation_id":"ba5a31da-939c-4936-9678-2c4b9d6c8716","resolution":{"observed_at":"2026-08-07T05:11:17.004018Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"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":"2026-08-07T05:11:16.984001Z","title":"Since the original implementation by [5] is unavailable, we use the open-source implementation from [ 43]","venue":null,"work_id":"5716b58a-f1d1-4082-959f-0f9ec543b30d","year":2012},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.772495Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:636e89c51c615d4c880ca25d3b8af5d32f95edd9397bbf8f227be9204e23bb6a","observation_id":"10906272-b95b-4d3c-a356-d43e6ba570e4","resolution":{"observed_at":"2026-08-07T05:11:16.988800Z","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":"2026-08-07T05:11:16.967953Z","title":"stuff\" categories and 80","venue":null,"work_id":"d184bdc6-e41e-4c5a-a667-d2ac3c2a465a","year":2012},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.777182Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:54c8f258c339bac3e270c46a357d7d9bc4e9b2c00b4400e9934085ecc0648e0f","observation_id":"1d7791e0-af2f-46fd-a9a6-27acd6a7d124","resolution":{"observed_at":"2026-08-07T05:11:16.973690Z","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":"2026-08-07T05:11:17.832505Z","title":null,"venue":null,"work_id":"1281089b-f25b-4fe9-aeee-854afe75e52f","year":null},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.389926Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:d3dcffb680708406edffdc7a53b863a8af2b673b5e34af7cead742a1017df597","observation_id":"ee42fb40-d37d-4d2c-8c27-eaf6b39e8289","resolution":{"observed_at":"2026-08-07T05:11:17.836859Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-07T05:11:17.444582Z","title":null,"venue":null,"work_id":"03f7a872-8734-4ba0-9832-99b6f25bdcde","year":null},"citing_paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T05:11:16.637205Z"},"links":{"citing_paper":"/paper/2506.08694"},"observation_digest":"sha256:2066ca53953e134e9eca2c9ad5dc2fbda34c34f1017de17ae7480fc197db8580","observation_id":"97000146-40f9-406a-a199-cb26e262ef5a","resolution":{"observed_at":"2026-08-07T05:11:17.449822Z","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"}}],"paper":{"arxiv_id":"2506.08694","last_updated":"2025-07-10T08:39:59Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T22:05:15.968020Z","submitted_at":"2025-06-10T11:20:32Z","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning"},"reference_resolution":{"displayed":78,"state_counts":{"malformed_identifier":2,"metadata_mismatch":0,"parse_uncertain":1,"unresolved":11,"verified_exact":2,"verified_fuzzy":62},"total_outbound_references":78},"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 78 of 78 outbound references and 0 inbound Pith citation observations for arXiv:2506.08694."}