{"as_of":"2026-08-11T02:30:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:da70cf1780311dda3ab4e7d5ea47bdf5c3b997933283ad061a7b16deeca0b549","coverage":[{"denominator":105,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T10:37:52.750500Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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/2509.03893/citation-record","integrity":"/paper/2509.03893/integrity","json":"/paper/2509.03893/citation-record.json","paper":"/paper/2509.03893"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2112.05814","last_updated":"2022-10-15T21:18:49Z","snapshot_observed_at":"2026-08-07T13:01:28.667448Z","submitted_at":"2021-12-10T20:15:03Z","title":"Deep ViT Features as Dense Visual Descriptors","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.05814","snapshot_observed_at":"2026-08-05T10:37:51.275765Z","title":"Deep vit features as dense visual descriptors","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:51.275765Z"},"links":{"cited_paper":"/paper/2112.05814","citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:674d09f7a01603f1a8feb110bfe98708ee364c279bbdf2371a489391fbb642f5","observation_id":"9dda9dd1-18d5-4c1b-b42f-e0fba1e583e1","resolution":{"observed_at":"2026-08-05T10:37:51.275765Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:37:51.396555Z","title":"Contactdb: Analyzing and predicting grasp contact via thermal imaging","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:51.396555Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:312d25da05f55f38e00bd311c6f7d0e1b5f29a6136f72b0a02e0bec954425d5c","observation_id":"08e178fb-d8fc-4cad-8a93-df4b88c4258c","resolution":{"observed_at":"2026-08-05T10:37:51.396555Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:37:51.504213Z","title":"Emerg- ing properties in self-supervised vision transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:51.504213Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:f753b959e7d336d7ae0c102ca7b16d4656fce8c7e5246b768dcbe5308f67b774","observation_id":"6ba0b3cb-94c5-45c7-8f6f-e6fd42d24874","resolution":{"observed_at":"2026-08-05T10:37:51.504213Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:37:51.642023Z","title":"A simple framework for contrastive learning of visual representations","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:51.642023Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:f6d17cb058931a3c5edf05f25a697279ac32ce321f04eb7d1722e51ee80809b2","observation_id":"a4bbc058-0cd8-4126-a622-c64b9d9389c5","resolution":{"observed_at":"2026-08-05T10:37:51.642023Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:37:51.752871Z","title":"Learning to act properly: Predicting and explaining affordances from images","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:51.752871Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:417c3eb4b8617826fa7d74159d80819cab214a72a2837141ff5ee8da4b606751","observation_id":"3b6e9e88-64d6-4646-8a2c-6631d25ca806","resolution":{"observed_at":"2026-08-05T10:37:51.752871Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:37:51.933809Z","title":"Blender - a 3D modelling and rendering package","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:51.933809Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:bafad91ce979a8645e5181024c46bd40966208da6a166868177f1a1eaed0c0ef","observation_id":"3f62d68c-c342-4e39-89af-6696f2767b91","resolution":{"observed_at":"2026-08-05T10:37:51.933809Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:37:52.144440Z","title":"Objaverse: A universe of annotated 3d objects","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.144440Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:ff83c933c3b44d3c04403878cf5b30ad7ddf0ea2114b8a82b728cac519423676","observation_id":"22c4983a-7d26-4fd5-8da3-5f8600716f77","resolution":{"observed_at":"2026-08-05T10:37:52.144440Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.17146","last_updated":"2024-12-05T14:28:40Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-09-25T17:59:51Z","title":"Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.17146","snapshot_observed_at":"2026-08-05T10:37:52.209256Z","title":"Molmo and pixmo: Open weights and open data for state-of-the-art multimodal models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.209256Z"},"links":{"cited_paper":"/paper/2409.17146","citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:ca440d290a78709f13785c1e0919a4b75ff417d4a8b2e93f60d13f2ccb941f6e","observation_id":"44068fd0-5849-4e91-bf7d-b33f4cf17e88","resolution":{"observed_at":"2026-08-05T10:37:52.209256Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:37:52.331812Z","title":"Objaverse-xl: A universe of 10m+ 3d objects","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.331812Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:7f4a2045c42d8d90dc7f21abd29286e5c2ea2928a87ddcce0034985def648d8b","observation_id":"54e1d0d6-4cf6-4396-89ee-d2bb07d2db17","resolution":{"observed_at":"2026-08-05T10:37:52.331812Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:37:52.339490Z","title":"3d affordancenet: A benchmark for visual object af- fordance understanding","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.339490Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:7ab48f8405eb0ac11ccedc2937e3054ed039e7451706aff218b0fdf7b7375e16","observation_id":"24082b48-8c5b-4786-b547-896300122c83","resolution":{"observed_at":"2026-08-05T10:37:52.339490Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.04805","last_updated":"2019-05-24T20:37:26Z","snapshot_observed_at":"2026-07-30T09:12:38.100527Z","submitted_at":"2018-10-11T00:50:01Z","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.04805","snapshot_observed_at":"2026-08-05T10:37:52.345773Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.345773Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:23bf9342b98e7f805f045d90711b2698ce5934f7ccf5fa89692a6fe842aa1901","observation_id":"3e65a991-4eed-4815-89e5-6c1cdd46efc5","resolution":{"observed_at":"2026-08-05T10:37:52.345773Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:37:52.354561Z","title":"On the effectiveness of retrieval, alignment, and replay in manipulation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.354561Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:3315a8dd2c3c12ae33ddf1a6166c39c65ede67fff426b306c2d398c20f5b3c1d","observation_id":"6cfad7e9-33ce-46a7-9f69-c77931230f17","resolution":{"observed_at":"2026-08-05T10:37:52.354561Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.03634","last_updated":"2024-08-23T12:36:18Z","snapshot_observed_at":"2026-07-06T17:55:49.302964Z","submitted_at":"2024-04-04T17:54:12Z","title":"PreAfford: Universal Affordance-Based Pre-Grasping for Diverse Objects and Environments","version":3},"cited_work":{"arxiv_id":"2404.03634","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.03634","snapshot_observed_at":"2026-08-05T10:37:53.160364Z","title":"PreAfford: Universal Affordance-Based Pre-Grasping for Diverse Objects and Environments","venue":"cs.RO","work_id":"76092096-cdb2-4e2f-abf6-a71ef95e5d5e","year":2024},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.360980Z"},"links":{"cited_paper":"/paper/2404.03634","citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:d832115c3ca4bff21afaf8cbcabc8b0cec041c615720b705d2735b8ae37bd119","observation_id":"4da627cc-66e5-409c-bd66-4908da3934eb","resolution":{"observed_at":"2026-08-05T10:37:53.166175Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:37:52.366228Z","title":"Affordancenet: An end-to-end deep learning approach for object affordance detection","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.366228Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:b92ed875a20a41708ecdfdf2c54806a37b4cdf92d979aa12e6ba6d1c15c7bcc9","observation_id":"c292a0bd-355c-4cb6-9976-41659cdf370f","resolution":{"observed_at":"2026-08-05T10:37:52.366228Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-08-10T16:40:37.411115Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-05T10:37:52.372382Z","title":"The llama 3 herd of models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.372382Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:a9b149df836cd1eedb323171c1f3247343385356ea0cc2aaf7bb91e6400e9b07","observation_id":"4cf07218-f03d-4b56-aa83-eeaecf64fcdf","resolution":{"observed_at":"2026-08-05T10:37:52.372382Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:37:52.379104Z","title":"Graspnet-1billion: A large-scale benchmark for general ob- ject grasping","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.379104Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:8b02635e198d6c35ee8a0e708b94eb1dab4b418c148cc470042f151cd4f74fcd","observation_id":"5ad74b88-7cd5-4ac3-b5be-dfb9c302342a","resolution":{"observed_at":"2026-08-05T10:37:52.379104Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:37:52.383939Z","title":"Dense object nets: Learning dense visual object descriptors by and for robotic manipulation","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.383939Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:5784fb3e8df3fa73423221f23c13cd9022acfa0c4f2df796962f64a65dda6161","observation_id":"805e4eed-8128-42bd-8c9f-e7c0ddab8d5c","resolution":{"observed_at":"2026-08-05T10:37:52.383939Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:37:52.388486Z","title":"The ecological approach to visual percep- tion: Classic edition","venue":null,"work_id":null,"year":1979},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.388486Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:afe495cc89bfec5bd764f8ba808b4d662ffa8bcfac119fe6184f97a8ec4a258f","observation_id":"11335ea5-530d-4126-8e5f-97503cd6eeb3","resolution":{"observed_at":"2026-08-05T10:37:52.388486Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:37:52.393534Z","title":"Videoswap: Customized video subject swapping with interactive semantic point cor- respondence","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.393534Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:65c547c3ed7917fde3230c86a222e320473073971cb4010a715cc97e5af8f73f","observation_id":"252f9c99-9dae-4ab4-b010-47599daa734d","resolution":{"observed_at":"2026-08-05T10:37:52.393534Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:37:52.398799Z","title":"Handal: A dataset of real-world manipulable object categories with pose annotations, affordances, and reconstructions","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.398799Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:64ee36f513d6a9087068f68fa278e6d89703d5bc29d89c59b16906eb2cd6f0a3","observation_id":"774cdb51-38b9-4097-a3be-2099f0e906ac","resolution":{"observed_at":"2026-08-05T10:37:52.398799Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:37:52.402949Z","title":"Hdri haven","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.402949Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:ff30f062ccf8d2ed0fd1b9f015ed5487c2d9494a1ccce243df8d1ba3d2e04d39","observation_id":"2e9acd83-2075-411c-9246-1d72a3eeccb4","resolution":{"observed_at":"2026-08-05T10:37:52.402949Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:37:52.407108Z","title":"Momentum contrast for unsupervised visual rep- resentation learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.407108Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:07e74ca3c38bed3ce669797281664e60ecdc53ef9481b53da2403902fb469340","observation_id":"64ff4210-52f0-41f5-bdb6-5e4487196025","resolution":{"observed_at":"2026-08-05T10:37:52.407108Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:37:52.412396Z","title":"Ditto: Demonstration imitation by trajectory transformation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.412396Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:f55a5e8a178fd68712f4e329fb13470b237ddc53b6b46b83e691af416e4db759","observation_id":"4c324b92-e024-4ee6-8562-c5df60189a38","resolution":{"observed_at":"2026-08-05T10:37:52.412396Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:37:52.417089Z","title":"Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen- Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.417089Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:0e21af74a603b31d3bb6e8c96ff4d7fa5f9988e8d47ab9ff1d2c93c230636d76","observation_id":"5e1f652f-91ac-4bf0-9ed4-eefeb14cde8c","resolution":{"observed_at":"2026-08-05T10:37:52.417089Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.11289","last_updated":"2024-08-22T13:58:56Z","snapshot_observed_at":"2026-08-02T17:32:59.098649Z","submitted_at":"2024-03-17T17:59:59Z","title":"ManipVQA: Injecting Robotic Affordance and Physically Grounded Information into Multi-Modal Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.11289","snapshot_observed_at":"2026-08-05T10:37:52.421164Z","title":"Manipvqa: Injecting robotic affordance and physi- cally grounded information into multi-modal large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.421164Z"},"links":{"cited_paper":"/paper/2403.11289","citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:96655fdf0473116346ba49db66828304c1399bd2dc441382837c741608a48728","observation_id":"c0421c3f-3c1c-4cbf-bc3e-900d0d8c6ad3","resolution":{"observed_at":"2026-08-05T10:37:52.421164Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:37:52.425353Z","title":"Flowformer: A transformer architecture for optical flow","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.425353Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:4fea04b5f06c5a3a68531996e426605d05091755ce70c843cc48fbc3082401e1","observation_id":"ae6e6a7f-4a1b-4f0d-854f-d82c2bea4d69","resolution":{"observed_at":"2026-08-05T10:37:52.425353Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:37:52.431043Z","title":"Flownet 2.0: Evolu- tion of optical flow estimation with deep networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.431043Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:35013f9d2e788088bfd117b281efe3d5908985c55d49d6c9338fdf6c8af0f42e","observation_id":"141b1507-215e-4661-9582-b85cf47102cd","resolution":{"observed_at":"2026-08-05T10:37:52.431043Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:37:52.435140Z","title":"Cotr: Correspondence transformer for matching across images","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.435140Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:8842ccddd1b04773ae4854e0d3c07a3b739ee2aa65f09550233233df9f348218","observation_id":"e6bf1e14-8e5e-420a-91ea-7c700c496f3e","resolution":{"observed_at":"2026-08-05T10:37:52.435140Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:37:52.439048Z","title":"Doduo: Learning dense visual correspondence from unsupervised semantic-aware flow","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.439048Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:6854d2e3a26dd30adbe11df38c1376802ef0e05e8f529dc77fb48ab7dc8daf64","observation_id":"a830a10a-467b-47d2-8053-e1e92cb5f87d","resolution":{"observed_at":"2026-08-05T10:37:52.439048Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.07487","last_updated":"2024-01-15T06:02:30Z","snapshot_observed_at":"2026-07-06T17:15:27.375387Z","submitted_at":"2024-01-15T06:02:30Z","title":"Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.07487","snapshot_observed_at":"2026-08-05T10:37:52.443071Z","title":"Robo-abc: Affordance gener- alization beyond categories via semantic correspondence for robot manipulation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.443071Z"},"links":{"cited_paper":"/paper/2401.07487","citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:b534d16e0dcf768490b7f35a4da1060d601e77352776289c69dab1572ed170e5","observation_id":"74b4b54d-6b60-4cf7-ad31-e95662366bf5","resolution":{"observed_at":"2026-08-05T10:37:52.443071Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:37:52.448936Z","title":"Segment anything in high qual- ity","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.448936Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:4e575e2af531e1d4a43ffdaf61434da317b57249c6e657632d13ec4fd084e9ff","observation_id":"45b9f8d8-23f4-40d4-97a2-7002450c8c2e","resolution":{"observed_at":"2026-08-05T10:37:52.448936Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:37:52.453143Z","title":"Two-year-olds will name artifacts by their func- tions","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.453143Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:f098f7f4833b3ff8e3570582f669100bc264478bbaabc5c099d91358ef2c84c2","observation_id":"c819f948-fc97-400b-a30c-aea042966300","resolution":{"observed_at":"2026-08-05T10:37:52.453143Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T10:37:52.457205Z","title":"Kingma and Jimmy Ba","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.457205Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:f5c3bf5d0719ad4d319a1e4ad013f4dc88fac55813f1f5f2fbe4a61368ffd378","observation_id":"f11b49e1-c60c-462d-ab03-d8fd3f196070","resolution":{"observed_at":"2026-08-05T10:37:52.457205Z","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":"2026-08-05T10:37:54.256048Z","title":"Segment any- thing","venue":null,"work_id":"f7635fb6-c52e-4353-8024-1c9f6279753d","year":2023},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.461697Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:29c685d90dbc65fb217b0684bfa07884d6dc3e4e03912a85074d18603ae53f26","observation_id":"7b98dd0b-47c0-481e-84ef-49afa68667fa","resolution":{"observed_at":"2026-08-05T10:37:54.262867Z","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":"2407.08711","last_updated":"2024-07-11T17:49:05Z","snapshot_observed_at":"2026-08-06T12:57:12.376484Z","submitted_at":"2024-07-11T17:49:05Z","title":"OmniNOCS: A unified NOCS dataset and model for 3D lifting of 2D objects","version":1},"cited_work":{"arxiv_id":"2407.08711","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.08711","snapshot_observed_at":"2026-08-05T10:37:53.084576Z","title":"OmniNOCS: A unified NOCS dataset and model for 3D lifting of 2D objects","venue":"cs.CV","work_id":"1af2d9cf-0062-4d6a-b9c3-5b8dd93eadde","year":2024},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.465978Z"},"links":{"cited_paper":"/paper/2407.08711","citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:600f451d8847dfc63333596e56b215afe00f514f73a46f1e51688cb946ece281","observation_id":"ac6f7933-b605-49a4-809e-6dbe25049322","resolution":{"observed_at":"2026-08-05T10:37:53.089894Z","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":{"arxiv_id":"2407.04689","last_updated":"2024-07-05T17:50:38Z","snapshot_observed_at":"2026-08-10T04:59:08.356040Z","submitted_at":"2024-07-05T17:50:38Z","title":"RAM: Retrieval-Based Affordance Transfer for Generalizable Zero-Shot Robotic Manipulation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.04689","snapshot_observed_at":"2026-08-05T10:37:52.470376Z","title":"Ram: Retrieval-based affordance transfer for gen- eralizable zero-shot robotic manipulation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.470376Z"},"links":{"cited_paper":"/paper/2407.04689","citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:b4a1e370531410d13d0be1a8e0f556754f20cf95dd46971e8fdd38ed2ce503bd","observation_id":"26903194-4257-48b8-847a-924037ce4209","resolution":{"observed_at":"2026-08-05T10:37:52.470376Z","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":"2026-08-05T10:37:54.239523Z","title":"Ge- ometry and context for semantic correspondences and func- tionality recognition in man-made 3d shapes","venue":null,"work_id":"c1d9e0ac-ce4d-4c3b-9356-98e6734252ab","year":2013},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.474671Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:7ab3607c19918648be35bd3468bee3352e75222781849ef6832547f74b2529a5","observation_id":"e7650c9c-57f8-4fbb-a43e-056cd93c296f","resolution":{"observed_at":"2026-08-05T10:37:54.244173Z","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":"2026-08-05T10:37:54.226179Z","title":"The functional correspondence problem","venue":null,"work_id":"dbc141fd-9d90-450d-ad1e-dc331af9cdec","year":2021},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.479070Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:ee11404e211316db100c8557fa2b78838c57834f48318a30b44208753c8d52e0","observation_id":"9c3a4e6c-ff63-4c49-a184-7fb517408a71","resolution":{"observed_at":"2026-08-05T10:37:54.230326Z","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":"2026-08-05T10:37:54.211681Z","title":"Object shape, object function, and object name","venue":null,"work_id":"e2337d78-b320-4887-9bda-b07f918e1d80","year":1998},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.484782Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:c77083d52b09b5051fbac968e7f780aa893cebed961cd1460fdb9ece3bb691ed","observation_id":"48515953-055f-46cc-af0f-f889393e3da7","resolution":{"observed_at":"2026-08-05T10:37:54.215998Z","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":"2026-08-05T10:37:54.196953Z","title":"Corresnerf: Image correspondence priors for neural radiance fields","venue":null,"work_id":"5d8e78ae-0c25-43fa-818a-555d04339121","year":2023},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.490095Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:ff61f992b333a743ee06cee563c5d81ab08e42b3c9167eccdbcc15f483b00ea9","observation_id":"ef4ff880-1dec-49a5-bfec-10fc7e0e18ea","resolution":{"observed_at":"2026-08-05T10:37:54.201420Z","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":"2026-08-05T10:37:54.182546Z","title":"Locate: Localize and transfer object parts for weakly supervised affordance grounding","venue":null,"work_id":"e29de7a6-cf82-4d36-8be8-2c82e9100346","year":2023},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.494336Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:acf60866d261e596331335dd8989ff9e0171ed0067c2b24935e014aeeafb48c4","observation_id":"7c54634e-5fbe-4730-963b-049ad5fb5463","resolution":{"observed_at":"2026-08-05T10:37:54.187127Z","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":"2026-08-05T10:37:52.498291Z","title":"Learning precise affordances from egocentric videos for robotic manipulation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.498291Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:6cb4e9925f1d4cca74749378c5d9f96716430205062b9a0f43c3a5094bd39c63","observation_id":"d8bdbe93-329c-41ad-a4b1-9b7dcde16ba6","resolution":{"observed_at":"2026-08-05T10:37:52.498291Z","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":"2026-08-05T10:37:54.166020Z","title":"Surface and edge detection for primitive fitting of point clouds","venue":null,"work_id":"88072523-a0b7-4298-9297-36f59cf0215c","year":2023},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.503362Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:a6d0ac2d2534360eec71d10fb7ca79fea562f2a982119c4ccc1626c7099f07d9","observation_id":"befb1564-9e7e-4735-af7f-6cd35392db8b","resolution":{"observed_at":"2026-08-05T10:37:54.170477Z","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":"2311.07575","last_updated":"2023-11-13T18:59:47Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-11-13T18:59:47Z","title":"SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.07575","snapshot_observed_at":"2026-08-05T10:37:52.507891Z","title":"Sphinx: The joint mixing of weights, tasks, and visual embeddings for multi-modal large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.507891Z"},"links":{"cited_paper":"/paper/2311.07575","citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:af13fbcd954aa920e56aa471348d61151ef357a7fc7491cd905810babed47abf","observation_id":"863f1169-3aa7-4cc0-9381-5c02537b344f","resolution":{"observed_at":"2026-08-05T10:37:52.507891Z","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":"2026-08-05T10:37:54.151758Z","title":"Pixel-perfect structure-from- motion with featuremetric refinement","venue":null,"work_id":"9d4c325d-c868-40b0-be63-f35da5d77d82","year":2021},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.512398Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:30b59837a3b1205f4e15b392b7164fd1ca744838c750a5307fd8aa1433394272","observation_id":"e0655ab1-e9eb-4292-ad58-fc849fe152aa","resolution":{"observed_at":"2026-08-05T10:37:54.156193Z","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":"2026-08-05T10:37:54.133813Z","title":"Learning affordance grounding from exocen- tric images","venue":null,"work_id":"863197d1-6cdd-413a-83c1-4bf566a2ec06","year":null},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.516724Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:e02020413e67e6e1c968ed54e27216ca1a0ca840d3c4ba3e6cbab53485a7cb4c","observation_id":"445ad572-1fa9-4d83-a4d3-c7697279f620","resolution":{"observed_at":"2026-08-05T10:37:54.139179Z","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":"2026-08-05T10:37:54.116793Z","title":"Scalable 3d captioning with pretrained models","venue":null,"work_id":"3b4efdac-6902-4f0c-a5f0-12e93006b792","year":2024},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.521042Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:2dc9437764a5912fe884d99e3ddd965178eafdcc7692710caa1d1c79f269328a","observation_id":"2e503d6a-a5c0-4600-9af1-9a9786ed454b","resolution":{"observed_at":"2026-08-05T10:37:54.121357Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.10739","last_updated":"2024-08-20T11:14:23Z","snapshot_observed_at":"2026-08-05T07:32:42.596199Z","submitted_at":"2024-08-20T11:14:23Z","title":"TrackNeRF: Bundle Adjusting NeRF from Sparse and Noisy Views via Feature Tracks","version":1},"cited_work":{"arxiv_id":"2408.10739","doi":null,"metadata_source":"pith","pith_arxiv_id":"2408.10739","snapshot_observed_at":"2026-08-05T10:37:52.951765Z","title":"TrackNeRF: Bundle Adjusting NeRF from Sparse and Noisy Views via Feature Tracks","venue":"cs.CV","work_id":"8255bc3e-dea5-4aba-ae50-3893b5586c90","year":2024},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.525288Z"},"links":{"cited_paper":"/paper/2408.10739","citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:db1741bcb94a96b82672815a183e4fa5285c109b76cc5d8d53e5d82e9dcaccd3","observation_id":"6f275994-9109-446b-af6a-bcc2a9de1545","resolution":{"observed_at":"2026-08-05T10:37:52.957396Z","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":{"arxiv_id":"1908.10543","last_updated":"2019-08-28T04:16:52Z","snapshot_observed_at":"2026-08-04T12:35:10.027979Z","submitted_at":"2019-08-28T04:16:52Z","title":"SPair-71k: A Large-scale Benchmark for Semantic Correspondence","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.10543","snapshot_observed_at":"2026-08-05T10:37:52.529822Z","title":"Spair-71k: A large-scale benchmark for semantic correspon- dence","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.529822Z"},"links":{"cited_paper":"/paper/1908.10543","citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:dabe52a9cbac8611eef76f2de1f3584f96f956ffed97e166806b82c100500a7c","observation_id":"f0354f1f-47b7-4142-bfd0-501b48ffd234","resolution":{"observed_at":"2026-08-05T10:37:52.529822Z","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":"2026-08-05T10:37:54.101153Z","title":"6-dof graspnet: Variational grasp generation for object manipula- tion","venue":null,"work_id":"174c78be-c57e-47c5-b2d5-30754488eaa2","year":2019},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.534838Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:a0f8a822d3ea29d348bb4fb6bd90e84c019fbd6152b24b42f989402a7ee70ebf","observation_id":"dd55169b-7539-4978-ba90-fde14e3f5e59","resolution":{"observed_at":"2026-08-05T10:37:54.106266Z","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":"2026-08-05T10:37:54.082946Z","title":"Same object, differ- ent grasps: Data and semantic knowledge for task-oriented grasping","venue":null,"work_id":"c40f472c-46ae-4dab-9589-ea83fd128c9f","year":null},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.540990Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:237f3611abc38cc9f2ef9c1b8773e9d98ba1c3001e8b285b7781bc307e3b1bec","observation_id":"60bc4d76-4c09-4dc9-91cf-bf8b89bf10ab","resolution":{"observed_at":"2026-08-05T10:37:54.089555Z","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":"2026-08-05T10:37:54.041911Z","title":"Affordance detection of tool parts from ge- ometric features","venue":null,"work_id":"538e8803-abe2-4965-98d4-c5987bc9052f","year":2015},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.552496Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:35ebe75f1f6bb02b290c2075dce8164c5113f36865fb3499130bff01d25b8600","observation_id":"a27c0b81-770e-486a-8e1e-b0dd24c88804","resolution":{"observed_at":"2026-08-05T10:37:54.050508Z","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":"2026-08-05T10:37:54.024578Z","title":"Grounded human-object interaction hotspots from video","venue":null,"work_id":"ffbd8040-5cc9-43db-9e4e-aa2fcba8c231","year":2019},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.556338Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:8c98576f21751548b8d56a7472362bd70deeefb5b2390569bde9f910788761e3","observation_id":"dffa9ede-c556-42fb-aafa-268e210b95f4","resolution":{"observed_at":"2026-08-05T10:37:54.031080Z","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":"2026-08-05T10:37:54.001997Z","title":"Caldwell, and Nikos G","venue":null,"work_id":"3ab70bc7-ccdb-4dde-9b12-52adb2eef091","year":2017},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.560754Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:b054e72fdd18d4164f62ce4717fd6078d6ea2c131be68b260e22ad9ba8ea4603","observation_id":"414cce45-2e43-4059-bdda-07755a652132","resolution":{"observed_at":"2026-08-05T10:37:54.009593Z","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":"2026-08-05T10:37:53.982538Z","title":null,"venue":null,"work_id":"a9d7c4bb-d64e-4466-aa81-90a6c77b37f6","year":2024},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.565180Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:8e9c6a0e5740f85434da2b660e890351c261cf234a57d1ad2af1c3ee2b155cf0","observation_id":"6116c1ce-d137-4eca-bdbf-399cfdbba579","resolution":{"observed_at":"2026-08-05T10:37:53.988252Z","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":{"arxiv_id":"2304.07193","last_updated":"2024-02-02T10:24:09Z","snapshot_observed_at":"2026-08-09T18:02:17.307812Z","submitted_at":"2023-04-14T15:12:19Z","title":"DINOv2: Learning Robust Visual Features without Supervision","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.07193","snapshot_observed_at":"2026-08-05T10:37:52.569311Z","title":"Dinov2: Learning robust visual features without supervision","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.569311Z"},"links":{"cited_paper":"/paper/2304.07193","citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:316552757570ec8476c00183307cade305a0c69b4c7b27145481367272a6adc0","observation_id":"e62f489d-0586-4292-b808-84b58c130e63","resolution":{"observed_at":"2026-08-05T10:37:52.569311Z","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":"2026-08-05T10:37:53.966988Z","title":"A threshold selection method from gray-level histograms","venue":null,"work_id":"6be2c93e-a053-49ea-8fb6-14d132b66f0f","year":null},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.573264Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:b6f935372daa09344fb0c6502d41981ad724e00a411822c0def2c20ad8e59d7e","observation_id":"156d82b5-b672-4545-92af-9859dd106ded","resolution":{"observed_at":"2026-08-05T10:37:53.971583Z","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":"2026-08-05T10:37:53.949351Z","title":"Dinobot: Robot ma- nipulation via retrieval and alignment with vision foundation models","venue":null,"work_id":"40e3c68f-96c5-487a-a06f-0e4da11e1c5f","year":2024},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.577730Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:19c90b175776c59bd500a2c66e3283abbdded32e09e7411573b27885eff27a9c","observation_id":"ba857c8b-fe11-4fe6-9f43-f17896f923de","resolution":{"observed_at":"2026-08-05T10:37:53.956189Z","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":"2026-08-05T10:37:53.933455Z","title":"Miles: Making imitation learning easy with self-supervision","venue":null,"work_id":"ae572f37-7003-49c9-a157-cfdb98199385","year":2024},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.582001Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:50fc8cf2d300f5ae63e40a12eacb189093a07b01f2591145c146ff60b4726123","observation_id":"3ff3061a-53d8-4a63-8e8a-327295ed6e5f","resolution":{"observed_at":"2026-08-05T10:37:53.938034Z","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":"2026-08-05T10:37:53.918505Z","title":"Film: Visual reasoning with a general conditioning layer, 2017","venue":null,"work_id":"8a48b8b2-b92c-4366-9488-f1c8c7c756c8","year":2017},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.586147Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:8dc80452a5e9a1298e4e278dbbd2201cd7b2949a622e1b256587a462c6396739","observation_id":"11d20068-4d25-47f4-9284-7fbcc3399a3d","resolution":{"observed_at":"2026-08-05T10:37:53.923043Z","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":"2026-08-05T10:37:53.901686Z","title":"Affordancellm: Grounding affordance from vision language models","venue":null,"work_id":"ec7fc4ed-973f-4913-a98b-d02d040b809b","year":2024},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.590058Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:c2ac270fbe43709f9366bcc89bd1dc90ba1c0dd8c4ee3d7010226262fa3eed58","observation_id":"6d48566b-1954-42ae-a044-6da3a5db9e78","resolution":{"observed_at":"2026-08-05T10:37:53.907173Z","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":"2026-08-05T10:37:53.883948Z","title":"Keto: Learning keypoint representations for tool manipulation","venue":null,"work_id":"ce941a69-74da-4fc0-bdfa-0715e0fcbdb1","year":2020},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.595522Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:849071e840ccaf9597d2b51a66d2a5d48610ec3c610289f452dac169854f84ac","observation_id":"00dde4c0-7462-4aed-b7ee-8b63a61285b7","resolution":{"observed_at":"2026-08-05T10:37:53.888885Z","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":"2026-08-05T10:37:52.599482Z","title":"Learning transferable visual models from natural language supervi- sion","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.599482Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:089181acc31df4b6f9fd7e3cd80725330dc07acbc478162393f8d8f3502eb2a8","observation_id":"2e61bec9-cf25-4592-ad34-0fb9f9580942","resolution":{"observed_at":"2026-08-05T10:37:52.599482Z","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":"2026-08-05T10:37:53.857029Z","title":null,"venue":null,"work_id":"ccf6f32c-efe3-44e7-b7c4-051e2ece5b6f","year":2020},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.603263Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:8744992cc36abc147b324c8139d6502bef5792994940ac4b5fa2c4bf6f2c336e","observation_id":"adef183f-a389-456b-a2c6-11c3b91f7726","resolution":{"observed_at":"2026-08-05T10:37:53.862528Z","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":"2026-08-05T10:37:53.840190Z","title":"Com- mon objects in 3d: Large-scale learning and evaluation of real-life 3d category reconstruction","venue":null,"work_id":"ca7eb536-189c-4943-941f-b45754adcddf","year":2021},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.607318Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:df228dff9c13b26a7d1a73e50320c56c0e44f385f18508fcc440bb4a901985e9","observation_id":"e8e320f1-62d8-44f4-9e41-a7972b447a30","resolution":{"observed_at":"2026-08-05T10:37:53.846206Z","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":"2026-08-05T10:37:53.825684Z","title":"High-resolution image synthesis with latent diffusion models","venue":null,"work_id":"96dc66ba-6093-44c3-adfb-bf00adf488a6","year":2022},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.611404Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:37e1601a106b51ac00b27fae8d9bea43ab417c7ecd66ede5e28740b547123bce","observation_id":"19778d75-ae1e-4202-9d17-9a8a2a3334e3","resolution":{"observed_at":"2026-08-05T10:37:53.830662Z","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":"2026-08-05T10:37:53.810325Z","title":"Superglue: Learning feature matching with graph neural networks","venue":null,"work_id":"2b68bedb-2a26-4a67-bfc4-71870bd48f44","year":2020},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.615061Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:c757052cdbc39f52d341aca638102bf74c42926922d5d3fc3dfb9e11cae62a3f","observation_id":"cf8c2dcd-3829-4db9-9deb-caf3c4c73a55","resolution":{"observed_at":"2026-08-05T10:37:53.815886Z","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":"2026-08-05T10:37:53.796642Z","title":"Learning dense object descriptors from multiple views for low-shot category generalization","venue":null,"work_id":"f8d38232-fb2f-49a4-a2f3-43f53cb82b64","year":2022},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.619260Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:50d597c1af6ba06d75a56b4d840d0805c5d77f2ee42d204f911bcfc2a046ca72","observation_id":"49891fc6-66b8-4965-9572-9623936f7c57","resolution":{"observed_at":"2026-08-05T10:37:53.801070Z","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":"2026-08-05T10:37:53.782920Z","title":"Loftr: Detector-free local feature matching with transformers","venue":null,"work_id":"3c5caaf0-51b5-4bc6-9d59-e42215476133","year":2021},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.623151Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:6d7993c678cba9647b3596c4bab0c3b2785fb5ae54ea05efd286245a5479d98c","observation_id":"3936c8e0-37b4-4dd1-a4d6-12e50ace7511","resolution":{"observed_at":"2026-08-05T10:37:53.787455Z","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":"2026-08-05T10:37:53.764770Z","title":"Misc210k: A large-scale dataset for multi-instance seman- tic correspondence","venue":null,"work_id":"d14c7cca-9321-43e0-8584-4bf3d2df58bc","year":2023},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.627160Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:f286610c89c8099a0ed3401e8fb95d3a5d46052dde0ca02832af3743de6aeef5","observation_id":"0df06f4d-5956-42b6-96b0-262f4d841fc0","resolution":{"observed_at":"2026-08-05T10:37:53.769660Z","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":"2026-08-05T10:37:53.750317Z","title":"Emergent correspondence from image diffusion","venue":null,"work_id":"fbdbdfaf-dd06-4aba-8121-536519573da6","year":2023},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.631142Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:1518c4f595270e8da0ec86d39d69d1611eb0150274b211dde9f1c4dd575253ff","observation_id":"3600e6a1-1023-49a7-a473-86fa01fbe90b","resolution":{"observed_at":"2026-08-05T10:37:53.754669Z","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":"2026-08-05T10:37:53.736363Z","title":"Joint re- covery of dense correspondence and cosegmentation in two images","venue":null,"work_id":"def3b709-1f4e-420b-8404-68b8dabfba5d","year":2016},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.635064Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:cce1def0c7cc6ffd226d4ba0ca7274b3374d7c93d60db19edc76da58c988c280","observation_id":"1aa0ab32-e8cb-417e-8bfe-d1b0c30c762e","resolution":{"observed_at":"2026-08-05T10:37:53.741014Z","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":"2026-08-05T10:37:53.720325Z","title":"Raft: Recurrent all-pairs field transforms for optical flow","venue":null,"work_id":"7b966f69-e729-4c0a-9ee1-81f838abbad7","year":2020},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.639161Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:a303934820d9d50a93e6ae321138b9b6fc8a49c1fe3ce15b5f839f5427f887e6","observation_id":"d3359896-4eff-4007-b37a-6d08c590e6c8","resolution":{"observed_at":"2026-08-05T10:37:53.725721Z","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":"2026-08-05T10:37:53.699955Z","title":"Shape-based transfer of generic skills","venue":null,"work_id":"f860352e-7fa9-47a6-8fca-c8b7193cfbd9","year":2021},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.643479Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:e85012718f72e814b9ec4f54276d7c21e9a0ac5758cd9ac409bc96f3332b6e19","observation_id":"c8b627d9-d2d1-4326-929e-16ac7b168656","resolution":{"observed_at":"2026-08-05T10:37:53.706169Z","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":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-05T10:37:52.647487Z","title":"Llama: Open and efficient foundation language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.647487Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:67cec9df2d60c8f0b422da1f19d0c33441d2498201367a0675462e1979f73436","observation_id":"bfb6c430-c124-4ad3-be10-5c98fdd0ab1f","resolution":{"observed_at":"2026-08-05T10:37:52.647487Z","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":"2026-08-05T10:37:53.685775Z","title":"Sparf: Neural radiance fields from sparse and noisy poses","venue":null,"work_id":"e97d6900-7c49-4994-91b2-2b6486946951","year":2023},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.651625Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:896bafb34aeb09119bfab762db7411a54f20d94f18577a96f46e64c2231e9c3c","observation_id":"057bb059-07ce-4d63-8f82-71f859fe7b25","resolution":{"observed_at":"2026-08-05T10:37:53.690609Z","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":"2106.14973","last_updated":"2021-06-28T20:43:35Z","snapshot_observed_at":"2026-07-06T11:23:56.887244Z","submitted_at":"2021-06-28T20:43:35Z","title":"GIFT: Generalizable Interaction-aware Functional Tool Affordances without Labels","version":1},"cited_work":{"arxiv_id":"2106.14973","doi":null,"metadata_source":"pith","pith_arxiv_id":"2106.14973","snapshot_observed_at":"2026-08-05T10:37:52.857311Z","title":"GIFT: Generalizable Interaction-aware Functional Tool Affordances without Labels","venue":"cs.RO","work_id":"a6ed7b20-7526-48a6-8e99-0932bf600c97","year":2021},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.655676Z"},"links":{"cited_paper":"/paper/2106.14973","citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:da97b505c8ca6f8bbfecb8ec188adbb5558bfcc1804b517e61df9203aba5748d","observation_id":"b1d4f96b-b3fa-4515-8ea1-5d9d9e202847","resolution":{"observed_at":"2026-08-05T10:37:52.864330Z","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":"2026-08-05T10:37:53.670764Z","title":"Repre- sentation learning with contrastive predictive coding, 2019","venue":null,"work_id":"d3e103d7-cefc-4395-a458-e4d31849b2e0","year":2019},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.660008Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:de4129a4db70d6f4b09ca60927eb053aec3992fa228827b75ccfe0f9f935506d","observation_id":"5d681bf2-74ff-47a0-b360-7b799fed21a5","resolution":{"observed_at":"2026-08-05T10:37:53.675117Z","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":"2026-08-05T10:37:53.655591Z","title":"Knowledge transfer from vision foundation models for efficient training of small task-specific models","venue":null,"work_id":"9048de84-2fe2-4ddd-9467-99c41a76df74","year":null},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.663887Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:c5a75758c79907cc8f177861feff5d43e59377b99976304ee0904c50fa242a7d","observation_id":"c5bb8dca-4a3f-4670-ae34-beef66388a08","resolution":{"observed_at":"2026-08-05T10:37:53.660013Z","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":"2026-08-05T10:37:53.632195Z","title":"Socs: Semantically- aware object coordinate space for category-level 6d object pose estimation under large shape variations","venue":null,"work_id":"5e909e0f-5a83-49d4-8d5a-72d381cb38fb","year":2023},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.668153Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:2d2242a4d5b05c696d4ea71431406a6d33e0484b1d4456785f434522c4616188","observation_id":"aa12bbd5-ce77-4120-9f25-22e709f3612d","resolution":{"observed_at":"2026-08-05T10:37:53.643381Z","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":"2026-08-05T10:37:53.615307Z","title":"Normalized object coordinate space for category-level 6d object pose and size estimation","venue":null,"work_id":"b5f7b80b-75c5-4b1f-aef8-d0ed122b4fe5","year":2019},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.672303Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:eff68ac73ed2bddf54437ec6be05f0509bb41b4e387c73358d18740d0ef0655a","observation_id":"7e83b1b7-842e-4eb3-a0e5-320d989149c0","resolution":{"observed_at":"2026-08-05T10:37:53.619800Z","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":"2311.03079","last_updated":"2024-02-04T08:23:04Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-11-06T13:04:39Z","title":"CogVLM: Visual Expert for Pretrained Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.03079","snapshot_observed_at":"2026-08-05T10:37:52.676543Z","title":"Cogvlm: Visual expert for pretrained language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.676543Z"},"links":{"cited_paper":"/paper/2311.03079","citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:7d5c49133532312888d6a98b5b0fd19d237aad2293e7e41c6d1b81b20855d2a0","observation_id":"09969101-a23d-42d7-af53-c1a8064571d9","resolution":{"observed_at":"2026-08-05T10:37:52.676543Z","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":"2026-08-05T10:37:53.595543Z","title":"Form follows function: Learning about function helps children learn about shape","venue":null,"work_id":"2ddf6aef-d142-4dee-8139-c7fdf2f1785d","year":2010},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.680773Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:38a8d4e4e0eaa07299d62314c54e7ea9f27f1b882f7783ef6c795be07c5f54ff","observation_id":"ce382009-6a1f-4144-94bd-16631a9819bd","resolution":{"observed_at":"2026-08-05T10:37:53.603208Z","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":"2026-08-05T10:37:53.571538Z","title":"Omniobject3d: Large-vocabulary 3d object dataset for realistic perception, reconstruction and generation","venue":null,"work_id":"eca66460-af6f-4ceb-b3e9-3f7cb6c29861","year":2023},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.685863Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:54a63740cee8ab6f9a5e3399910f5f9593d4d00ead9fd1127afdd5d851c14378","observation_id":"13dfdab1-4c15-4cc6-8dde-dd3818173f95","resolution":{"observed_at":"2026-08-05T10:37:53.580653Z","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":"2026-08-05T10:37:53.555435Z","title":"An affordance keypoint detection network for robot manipulation","venue":null,"work_id":"95cdac52-46c2-42bf-8c1c-1abf874b75dd","year":2021},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.689869Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:13181aa557ebe05a017414807f95086cf698f4c2a83cc8d89d651454c45039a9","observation_id":"1e10108a-7c7c-4f68-83d7-6192feeb670d","resolution":{"observed_at":"2026-08-05T10:37:53.560203Z","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":"2026-08-05T10:37:53.533688Z","title":"Depth anything: Unleashing the power of large-scale unlabeled data","venue":null,"work_id":"fb87af99-1020-414b-a48e-ba90660bd3c5","year":2024},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.694408Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:8deae591ab7c50928a56a4c873be98eb9b4b5ef6471fe218d9fb040a7bba0fa3","observation_id":"319be8d4-9162-4c3d-93a7-3e8d8ffa7620","resolution":{"observed_at":"2026-08-05T10:37:53.538657Z","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":"2026-08-05T10:37:53.519473Z","title":"Grounding 3d object affordance from 2d interactions in images","venue":null,"work_id":"75efb11c-3673-4dd0-9970-a8418ecf7780","year":2023},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.698519Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:305de556ef50a8584acb5b38b7c8933e5d2bd968834a06857691a135cddae152","observation_id":"aff55648-00e4-4d82-b26e-f5f7cc19fad9","resolution":{"observed_at":"2026-08-05T10:37:53.523771Z","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":"2026-08-05T10:37:53.500171Z","title":"Mvimgnet: A large-scale dataset of multi-view images","venue":null,"work_id":"f6c98cd6-e2db-4bf5-be74-384fa46b374a","year":2023},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.702383Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:f3d1aebab1a470c305d6ebe10bcd7be966bcb8e0dd5e8874352b116963f4ca7a","observation_id":"14408208-d319-4a35-8cc3-460ff8778de3","resolution":{"observed_at":"2026-08-05T10:37:53.507689Z","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":"2406.10721","last_updated":"2024-06-15T19:22:51Z","snapshot_observed_at":"2026-08-10T12:41:05.968400Z","submitted_at":"2024-06-15T19:22:51Z","title":"RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.10721","snapshot_observed_at":"2026-08-05T10:37:52.706273Z","title":"Robopoint: A vision-language model for spatial affordance prediction for robotics","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.706273Z"},"links":{"cited_paper":"/paper/2406.10721","citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:1b7058a7c451d9358a0ad2c09a6dbc6dd25525b158a5f715eeb4af488ded6e44","observation_id":"edd14926-7aa5-46c8-882f-ee5306c133e8","resolution":{"observed_at":"2026-08-05T10:37:52.706273Z","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":"2026-08-05T10:37:53.482102Z","title":"Sigmoid loss for language image pre-training","venue":null,"work_id":"f3fb0a39-2caa-4d8a-b2eb-5c515d7731ae","year":2023},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.710800Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:755d776bdfe64dab4e127dd03143d0c42f3ca151644cc3018593b5cdf23c6c41","observation_id":"5d001b42-b607-4c70-acbc-e18784ca4487","resolution":{"observed_at":"2026-08-05T10:37:53.488567Z","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":"2026-08-05T10:37:53.463079Z","title":"A tale of two features: Stable diffusion complements dino for zero-shot semantic correspondence, 2023","venue":null,"work_id":"6debeca7-da9b-4b73-9523-d684f4134eb8","year":2023},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.714860Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:6977f30ed65f6f7a86138590c998552a608321d58ca72bf6d9f63c9f3c454332","observation_id":"814112bc-033c-41f9-b4b0-b26ccc74ca13","resolution":{"observed_at":"2026-08-05T10:37:53.469499Z","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":"2026-08-05T10:37:53.436096Z","title":"Egoobjects: A large-scale egocentric dataset for fine-grained object understanding","venue":null,"work_id":"05801078-2026-4596-a3c8-463a7248a0fa","year":2023},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.718807Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:55e1a4fef187d492eb9ced5217d5f7ca527950bd50aca5509bf741947b762c16","observation_id":"0d179c6e-e5d8-4831-88f9-f248570541e6","resolution":{"observed_at":"2026-08-05T10:37:53.441781Z","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":"2026-08-05T10:37:53.418224Z","title":"Understanding tools: Task-oriented object modeling, learning and recogni- tion","venue":null,"work_id":"f9e80af4-aaab-41b6-957c-72e2d5e0251c","year":2015},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.722770Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:1f74eebbb2f3c721a39ce0cd8fa8cab81fcf60128b4b975ae72a0b4f9fcbab34","observation_id":"7b688654-883f-4b38-ab34-2628b908ba3f","resolution":{"observed_at":"2026-08-05T10:37:53.423154Z","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":"2405.20321","last_updated":"2025-09-04T08:23:37Z","snapshot_observed_at":"2026-08-07T22:46:10.482452Z","submitted_at":"2024-05-30T17:56:54Z","title":"Vision-based Manipulation from Single Human Video with Open-World Object Graphs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.20321","snapshot_observed_at":"2026-08-05T10:37:52.726480Z","title":"Vision- based manipulation from single human video with open- world object graphs","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.726480Z"},"links":{"cited_paper":"/paper/2405.20321","citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:109b06525088ea0f0af78820e578e73600c43b0ab06bc0ec592e5f588db8652f","observation_id":"36dc9322-e1dd-407f-9e1c-463dc66d6069","resolution":{"observed_at":"2026-08-05T10:37:52.726480Z","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":"2026-08-05T10:37:53.392683Z","title":"Given this list of functions, generate more options for object func- tions","venue":null,"work_id":"0d779323-9051-4276-91df-eecfa5e64391","year":null},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.730535Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:fda06e95ec9db25a3adcde7d2ee21cf174373f8696a368e909c7c0bea1ba9f31","observation_id":"2e4bb08a-8ac2-40de-8331-eefd83cd63e0","resolution":{"observed_at":"2026-08-05T10:37:53.400304Z","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":"2026-08-05T10:37:53.365099Z","title":null,"venue":null,"work_id":"b5cec6aa-cb1f-484b-9d1c-d4cba5e78341","year":null},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.734733Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:ffb9824f3fa516575414ef3b2e2d1d51c95f901c0fd978402cc48dceb4645e44","observation_id":"7c3eac04-823e-41ba-bbf5-4d6c9a81521f","resolution":{"observed_at":"2026-08-05T10:37:53.373640Z","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":"2026-08-05T10:37:53.348455Z","title":"For small parts like points or tips, we do a second iteration that zooms into the initial bounding boxes to improve precision","venue":null,"work_id":"546eb4b7-58a9-4753-ab5f-e0289b5241a5","year":null},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.738482Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:3f45120b96a219855e5024ef68f5507574d074c0cb45684aa005becd82e54cea","observation_id":"9b8d4b22-e59f-45ed-a17f-4836a3957e7b","resolution":{"observed_at":"2026-08-05T10:37:53.352598Z","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":"2026-08-05T10:37:53.332490Z","title":"Ev- ery time a given point in the point cloud gets labeled by a bounding box in a different view, we increment its score","venue":null,"work_id":"6f00bb53-31f5-45cd-9957-586534b8961c","year":null},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.742689Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:163ec6949c240902cb9cb1236b5e619828c05adeb1e152cafbdbea9571625348","observation_id":"f54116b0-d2f4-4773-9d29-59f10317171b","resolution":{"observed_at":"2026-08-05T10:37:53.338351Z","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":"2026-08-05T10:37:53.317643Z","title":null,"venue":null,"work_id":"0760c38e-c803-4dc9-8989-8d2a633132b9","year":null},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.746705Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:7612f274e16a64ab819b132ff7f88a3f8731c3891c95fe0d128ff2406bc1858c","observation_id":"46701a53-6c6c-44c4-8ab3-aafaf3d4aec8","resolution":{"observed_at":"2026-08-05T10:37:53.321941Z","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":"2026-08-05T10:37:53.302075Z","title":"Example outputs of this procedure are shown in Figure 7","venue":null,"work_id":"d219a258-26fc-4f8b-9ce1-d007c41bd697","year":null},"citing_paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences","version":1},"reference_index":101,"source":"pdf_text","source_observed_at":"2026-08-05T10:37:52.750500Z"},"links":{"citing_paper":"/paper/2509.03893"},"observation_digest":"sha256:6ecb18dca09d4e48acaaadef160d936bdb3de19d111360cdab6354e24c10fcb1","observation_id":"a1963594-fb98-4dd8-9c05-948193a3c314","resolution":{"observed_at":"2026-08-05T10:37:53.306786Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2509.03893","last_updated":"2025-09-04T05:39:16Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T05:57:35.987262Z","submitted_at":"2025-09-04T05:39:16Z","title":"Weakly-Supervised Learning of Dense Functional Correspondences"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":46,"verified_exact":4,"verified_fuzzy":50},"total_outbound_references":105},"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 11 August 2026, this Paper Citation Record lists 100 of 105 outbound references and 0 inbound Pith citation observations for arXiv:2509.03893."}