{"as_of":"2026-08-23T15:41:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6f5c49a484258393d475ea2753f75f158c6ae66ea9a7ba7b148b2b46dacf4b0a","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":"2026-08-23T06:30:58.430688+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":"2026-08-11T23:55:58.410638Z","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":"2026-06-29T17:23:44.936349Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2407.18908","last_updated":"2025-03-20T17:56:05Z","snapshot_observed_at":"2026-08-20T07:55:28.713615Z","submitted_at":"2024-07-26T17:59:09Z","title":"Wolf: Dense Video Captioning with a World Summarization Framework","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.18908","snapshot_observed_at":"2026-08-11T23:55:58.410638Z","title":"Wolf: Captioning everything with a world summariza- tion framework","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.02071","last_updated":"2025-03-26T02:26:56Z","snapshot_observed_at":"2026-08-15T15:38:26.650897Z","submitted_at":"2024-12-03T01:21:28Z","title":"Progress-Aware Video Frame Captioning","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T23:55:58.410638Z"},"links":{"cited_paper":"/paper/2407.18908","citing_paper":"/paper/2412.02071"},"observation_digest":"sha256:5a4366deee7c5877dd4cb5cac0285eb6cba895a619b29559020dbdc3d112b9cb","observation_id":"371880b3-982f-47c9-9921-f304e7dd12b5","resolution":{"observed_at":"2026-08-11T23:55:58.410638Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.18908","last_updated":"2025-03-20T17:56:05Z","snapshot_observed_at":"2026-08-20T07:55:28.713615Z","submitted_at":"2024-07-26T17:59:09Z","title":"Wolf: Dense Video Captioning with a World Summarization Framework","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.18908","snapshot_observed_at":"2026-08-10T23:55:17.555813Z","title":"Jacob Krantz","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.19794","last_updated":"2025-06-11T16:24:02Z","snapshot_observed_at":"2026-08-14T00:22:50.649312Z","submitted_at":"2024-12-27T18:47:05Z","title":"MVTamperBench: Evaluating Robustness of Vision-Language Models","version":5},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-10T23:55:17.555813Z"},"links":{"cited_paper":"/paper/2407.18908","citing_paper":"/paper/2412.19794"},"observation_digest":"sha256:9204091614c979286c995cbe6323cfc550a511f39ce6a9ac0b510d5dd48fa0c4","observation_id":"58441840-3484-4038-bb12-319dac818766","resolution":{"observed_at":"2026-08-10T23:55:17.555813Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.18908","last_updated":"2025-03-20T17:56:05Z","snapshot_observed_at":"2026-08-20T07:55:28.713615Z","submitted_at":"2024-07-26T17:59:09Z","title":"Wolf: Dense Video Captioning with a World Summarization Framework","version":2},"cited_work":{"arxiv_id":"2407.18908","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2407.18908","snapshot_observed_at":"2026-06-29T17:23:44.936349Z","title":"Wolf: Dense video captioning with a world summa- rization framework","venue":null,"work_id":"822d0a44-75e9-41fa-8ff8-730426fa3bae","year":2025},"citing_paper":{"arxiv_id":"2511.18373","last_updated":"2026-04-11T05:44:20Z","snapshot_observed_at":"2026-08-11T05:10:55.239779Z","submitted_at":"2025-11-23T09:43:44Z","title":"MASS: Motion-Aware Spatial-Temporal Grounding for Physics Reasoning and Comprehension in Vision-Language Models","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-17T05:55:11.495430Z"},"links":{"cited_paper":"/paper/2407.18908","citing_paper":"/paper/2511.18373"},"observation_digest":"sha256:70bdbbcc70d23ea65c784b0714dabaa3e7df0e4d7e39215c5e659404d972ec5b","observation_id":"298b7980-dea8-4297-8be3-aca7894a6bb8","resolution":{"observed_at":"2026-05-17T05:59:08.717796Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.18908","last_updated":"2025-03-20T17:56:05Z","snapshot_observed_at":"2026-08-20T07:55:28.713615Z","submitted_at":"2024-07-26T17:59:09Z","title":"Wolf: Dense Video Captioning with a World Summarization Framework","version":2},"cited_work":{"arxiv_id":"2407.18908","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2407.18908","snapshot_observed_at":"2026-06-29T17:23:44.936349Z","title":"Wolf: Dense video captioning with a world summa- rization framework","venue":null,"work_id":"822d0a44-75e9-41fa-8ff8-730426fa3bae","year":2025},"citing_paper":{"arxiv_id":"2605.27284","last_updated":"2026-05-26T17:01:10Z","snapshot_observed_at":"2026-08-15T12:22:02.585549Z","submitted_at":"2026-05-26T17:01:10Z","title":"FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-06-29T17:19:04.477325Z"},"links":{"cited_paper":"/paper/2407.18908","citing_paper":"/paper/2605.27284"},"observation_digest":"sha256:2f4079e56774ef40896e65c9697782e7c1fceaf8dcd18a54c699c3dcf648bce6","observation_id":"9f0d7d01-72f0-4063-90af-4daa7239d4d5","resolution":{"observed_at":"2026-06-29T17:23:44.937908Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2407.18908/citation-record","integrity":"/paper/2407.18908/integrity","json":"/paper/2407.18908/citation-record.json","paper":"/paper/2407.18908"},"outbound":[],"paper":{"arxiv_id":"2407.18908","last_updated":"2025-03-20T17:56:05Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-20T07:55:28.713615Z","submitted_at":"2024-07-26T17:59:09Z","title":"Wolf: Dense Video Captioning with a World Summarization Framework"},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2407.18908."}