{"as_of":"2026-08-11T22:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4657f906fd65a818a5d36022e4e13621e5fc2ff9320e8937a588d3050cb3ee4a","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T12:40:08.111870Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-07T06:00:59.067766Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2404.05603","last_updated":"2024-04-08T15:22:38Z","snapshot_observed_at":"2026-08-11T17:41:06.889641Z","submitted_at":"2024-04-08T15:22:38Z","title":"Self-Explainable Affordance Learning with Embodied Caption","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.05603","snapshot_observed_at":"2026-08-07T12:40:08.111870Z","title":"Self-explainable affordance learning with embodied caption","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24103","last_updated":"2025-05-30T01:12:39Z","snapshot_observed_at":"2026-08-11T17:44:24.364766Z","submitted_at":"2025-05-30T01:12:39Z","title":"Weakly-Supervised Affordance Grounding Guided by Part-Level Semantic Priors","version":1},"reference_index":82,"source":"arxiv_source","source_observed_at":"2026-08-07T12:40:08.111870Z"},"links":{"cited_paper":"/paper/2404.05603","citing_paper":"/paper/2505.24103"},"observation_digest":"sha256:a521ce100fdfeb5aae83c9a5c6d5aab3355be0b969dacf0abeffddc70153ebd5","observation_id":"0c94f27f-6d38-4b28-b4cb-53447e6f1983","resolution":{"observed_at":"2026-08-07T12:40:08.111870Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.05603","last_updated":"2024-04-08T15:22:38Z","snapshot_observed_at":"2026-08-11T17:41:06.889641Z","submitted_at":"2024-04-08T15:22:38Z","title":"Self-Explainable Affordance Learning with Embodied Caption","version":1},"cited_work":{"arxiv_id":"2404.05603","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.05603","snapshot_observed_at":"2026-08-07T06:00:59.067766Z","title":"Self-Explainable Affordance Learning with Embodied Caption","venue":"cs.CV","work_id":"db64ebfc-8505-49a6-88bb-8495e3cd8afb","year":2024},"citing_paper":{"arxiv_id":"2506.06253","last_updated":"2025-06-06T17:25:48Z","snapshot_observed_at":"2026-08-09T07:19:17.693738Z","submitted_at":"2025-06-06T17:25:48Z","title":"Bridging Perspectives: A Survey on Cross-view Collaborative Intelligence with Egocentric-Exocentric Vision","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-07T06:00:58.199398Z"},"links":{"cited_paper":"/paper/2404.05603","citing_paper":"/paper/2506.06253"},"observation_digest":"sha256:666400d1830bc264832c7dea9482923f6693a4f8fafd07fa22518103309a30b1","observation_id":"1d382b46-5e47-4bb9-a930-9a0df140e584","resolution":{"observed_at":"2026-08-07T06:00:59.071229Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.05603","last_updated":"2024-04-08T15:22:38Z","snapshot_observed_at":"2026-08-11T17:41:06.889641Z","submitted_at":"2024-04-08T15:22:38Z","title":"Self-Explainable Affordance Learning with Embodied Caption","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.05603","snapshot_observed_at":"2026-08-02T23:34:00.107212Z","title":"Self-explainable affordance learning with embodied caption","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.04419","last_updated":"2026-07-11T22:36:19Z","snapshot_observed_at":"2026-08-10T12:44:41.818416Z","submitted_at":"2026-02-14T04:22:00Z","title":"Context-Dependent Affordance Computation in Vision-Language Models","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-02T23:34:00.107212Z"},"links":{"cited_paper":"/paper/2404.05603","citing_paper":"/paper/2603.04419"},"observation_digest":"sha256:b3e51ebed0dd077ae4c1752b0d21ef725231968d3f6b9bf74174a035efc4f0c4","observation_id":"7833994d-049f-48ac-98a2-d65844aef536","resolution":{"observed_at":"2026-08-02T23:34:00.107212Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.05603","last_updated":"2024-04-08T15:22:38Z","snapshot_observed_at":"2026-08-11T17:41:06.889641Z","submitted_at":"2024-04-08T15:22:38Z","title":"Self-Explainable Affordance Learning with Embodied Caption","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.05603","snapshot_observed_at":"2026-08-01T22:04:56.496885Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15890","last_updated":"2026-08-05T10:06:27Z","snapshot_observed_at":"2026-08-08T23:10:28.476997Z","submitted_at":"2026-07-17T12:05:07Z","title":"Exo2EgoPose: Leveraging Exocentric Demonstrations for Vision-Language guided Egocentric 3D Hand Pose Forecasting","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-01T22:04:56.496885Z"},"links":{"cited_paper":"/paper/2404.05603","citing_paper":"/paper/2607.15890"},"observation_digest":"sha256:09cacb15ea7ad842bdd059c9fd60e48ae3c888b93e73ea9d6e88f714df7d2dd4","observation_id":"15544281-315b-4fc9-8ded-13b02a3bedcb","resolution":{"observed_at":"2026-08-01T22:04:56.496885Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2404.05603/citation-record","integrity":"/paper/2404.05603/integrity","json":"/paper/2404.05603/citation-record.json","paper":"/paper/2404.05603"},"outbound":[],"paper":{"arxiv_id":"2404.05603","last_updated":"2024-04-08T15:22:38Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-11T17:41:06.889641Z","submitted_at":"2024-04-08T15:22:38Z","title":"Self-Explainable Affordance Learning with Embodied Caption"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2404.05603."}