{"as_of":"2026-08-08T14:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2b5218381d2191dba73505207ee385391d5e966b0f8460a9d19bde9013ec8be2","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T12:26:37.966867Z","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":"2026-05-15T20:21:57.995580Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2309.15785","last_updated":"2024-06-27T12:05:48Z","snapshot_observed_at":"2026-08-03T13:55:11.770435Z","submitted_at":"2023-09-27T16:58:35Z","title":"BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning","version":2},"cited_work":{"arxiv_id":"2309.15785","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2309.15785","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"One for all: Video conversation is feasible without video instruction tuning","venue":null,"work_id":"2cb5b9a2-e141-4207-ae64-3b1252b851d9","year":2023},"citing_paper":{"arxiv_id":"2404.16994","last_updated":"2024-04-29T14:52:02Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-04-25T19:29:55Z","title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-15T20:21:57.873354Z"},"links":{"cited_paper":"/paper/2309.15785","citing_paper":"/paper/2404.16994"},"observation_digest":"sha256:07f8f3bcaf58ae6c949b25b8c7348701fcf8331f991e1b956f7fed51f2cf993c","observation_id":"2c18829c-482a-4a61-8c12-3e5b88644105","resolution":{"observed_at":"2026-05-15T20:21:57.998742Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2309.15785","last_updated":"2024-06-27T12:05:48Z","snapshot_observed_at":"2026-08-03T13:55:11.770435Z","submitted_at":"2023-09-27T16:58:35Z","title":"BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.15785","snapshot_observed_at":"2026-08-07T12:26:37.966867Z","title":"One for all: Video conversation is fea- sible without video instruction tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.24476","last_updated":"2025-05-30T11:23:21Z","snapshot_observed_at":"2026-08-07T12:19:09.982746Z","submitted_at":"2025-05-30T11:23:21Z","title":"Period-LLM: Extending the Periodic Capability of Multimodal Large Language Model","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T12:26:37.966867Z"},"links":{"cited_paper":"/paper/2309.15785","citing_paper":"/paper/2505.24476"},"observation_digest":"sha256:e40dd45f1ebcb7db7b6935a548955d1efa3ba9e9fca21fb048921c45a6ae75c9","observation_id":"610e1dfd-bbd6-458f-b3f3-251567ad856b","resolution":{"observed_at":"2026-08-07T12:26:37.966867Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.15785","last_updated":"2024-06-27T12:05:48Z","snapshot_observed_at":"2026-08-03T13:55:11.770435Z","submitted_at":"2023-09-27T16:58:35Z","title":"BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.15785","snapshot_observed_at":"2026-08-04T12:43:26.262167Z","title":"Ruipu Luo, Ziwang Zhao, Min Yang, Junwei Dong, Minghui Qiu, Pengcheng Lu, Tao Wang, and Zhongyu Wei","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2510.02561","last_updated":"2026-06-21T19:30:46Z","snapshot_observed_at":"2026-08-04T12:43:24.511280Z","submitted_at":"2025-10-02T20:57:10Z","title":"Oracle-RLAIF: An Improved Fine-Tuning Framework for Multi-modal Video Models using Reinforcement Learning from Ranking Feedback","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-04T12:43:26.262167Z"},"links":{"cited_paper":"/paper/2309.15785","citing_paper":"/paper/2510.02561"},"observation_digest":"sha256:921c7bb7fa5b67fae93fb7c51708ef68e83a512255975de52539c46182d84dbf","observation_id":"4b5a927f-3563-448b-b4f1-cbf3e29cf05d","resolution":{"observed_at":"2026-08-04T12:43:26.262167Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2309.15785/citation-record","integrity":"/paper/2309.15785/integrity","json":"/paper/2309.15785/citation-record.json","paper":"/paper/2309.15785"},"outbound":[],"paper":{"arxiv_id":"2309.15785","last_updated":"2024-06-27T12:05:48Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-03T13:55:11.770435Z","submitted_at":"2023-09-27T16:58:35Z","title":"BT-Adapter: Video Conversation is Feasible Without Video Instruction Tuning"},"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 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2309.15785."}