{"as_of":"2026-08-09T03:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5af9811c9f5b307c985a035375e237ff2587839c7139c2b55bd4c1d8ff3669b9","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T17:29:03.621820Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-10T00:59:49.433708Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2401.11649","last_updated":"2024-01-22T02:03:31Z","snapshot_observed_at":"2026-07-06T17:18:32.330256Z","submitted_at":"2024-01-22T02:03:31Z","title":"M2-CLIP: A Multimodal, Multi-task Adapting Framework for Video Action Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.11649","snapshot_observed_at":"2026-08-05T17:29:03.621820Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.16207","last_updated":"2025-08-25T05:44:22Z","snapshot_observed_at":"2026-08-09T01:27:29.968037Z","submitted_at":"2025-08-22T08:27:35Z","title":"T-MASK: Temporal Masking for Probing Foundation Models across Camera Views in Driver Monitoring","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-05T17:29:03.621820Z"},"links":{"cited_paper":"/paper/2401.11649","citing_paper":"/paper/2508.16207"},"observation_digest":"sha256:5645905b0d88a5c25ef47da5c5fddcd30f793bdd5810c04ac6a7df8abf61f57c","observation_id":"e9827af1-f49c-4da7-938b-8980f2bdd957","resolution":{"observed_at":"2026-08-05T17:29:03.621820Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.11649","last_updated":"2024-01-22T02:03:31Z","snapshot_observed_at":"2026-07-06T17:18:32.330256Z","submitted_at":"2024-01-22T02:03:31Z","title":"M2-CLIP: A Multimodal, Multi-task Adapting Framework for Video Action Recognition","version":1},"cited_work":{"arxiv_id":"2401.11649","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2401.11649","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2401.11649 (2024)","venue":null,"work_id":"72a0cda9-5301-40a7-9c89-ecb7f837a53f","year":2024},"citing_paper":{"arxiv_id":"2604.20760","last_updated":"2026-04-22T16:48:43Z","snapshot_observed_at":"2026-08-04T10:29:14.353844Z","submitted_at":"2026-04-22T16:48:43Z","title":"Exploring High-Order Self-Similarity for Video Understanding","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-05-10T00:59:03.890135Z"},"links":{"cited_paper":"/paper/2401.11649","citing_paper":"/paper/2604.20760"},"observation_digest":"sha256:96885602aee013785ffa4826e533c40a129cf9f6a5699074beb9fc38acbb7415","observation_id":"620a054c-980e-4a27-9761-ab3d94a91b98","resolution":{"observed_at":"2026-05-10T00:59:49.434862Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2401.11649/citation-record","integrity":"/paper/2401.11649/integrity","json":"/paper/2401.11649/citation-record.json","paper":"/paper/2401.11649"},"outbound":[],"paper":{"arxiv_id":"2401.11649","last_updated":"2024-01-22T02:03:31Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T17:18:32.330256Z","submitted_at":"2024-01-22T02:03:31Z","title":"M2-CLIP: A Multimodal, Multi-task Adapting Framework for Video Action Recognition"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2401.11649."}