{"as_of":"2026-08-08T07:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ce678ca55a2c76d7be9988d1b3d58fd25adc338126e096ad60b62b37dd194182","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":"2026-08-07T13:20:16.225698Z","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":"2026-08-07T10:16:56.891207Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.09291","last_updated":"2025-03-15T12:38:50Z","snapshot_observed_at":"2026-08-05T03:11:14.295782Z","submitted_at":"2025-01-16T04:53:29Z","title":"LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.09291","snapshot_observed_at":"2026-08-07T13:20:16.225698Z","title":"Lavcap: Llm-based audio-visual captioning using optimal transport,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.22045","last_updated":"2025-05-28T07:08:17Z","snapshot_observed_at":"2026-08-07T13:14:09.265446Z","submitted_at":"2025-05-28T07:08:17Z","title":"Mitigating Audiovisual Mismatch in Visual-Guide Audio Captioning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T13:20:16.225698Z"},"links":{"cited_paper":"/paper/2501.09291","citing_paper":"/paper/2505.22045"},"observation_digest":"sha256:5abc34ed894cf2a9e08dbd400e01f4640871595f3991ee5b707c8d0d9e4edbe0","observation_id":"21c84687-edff-4251-a172-5b1d6519ca57","resolution":{"observed_at":"2026-08-07T13:20:16.225698Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.09291","last_updated":"2025-03-15T12:38:50Z","snapshot_observed_at":"2026-08-05T03:11:14.295782Z","submitted_at":"2025-01-16T04:53:29Z","title":"LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport","version":2},"cited_work":{"arxiv_id":"2501.09291","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.09291","snapshot_observed_at":"2026-08-07T10:16:56.891207Z","title":"LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport","venue":"cs.MM","work_id":"08482a98-9bb9-4481-b462-647de195b437","year":2025},"citing_paper":{"arxiv_id":"2506.05899","last_updated":"2025-06-06T09:12:51Z","snapshot_observed_at":"2026-08-07T10:10:58.136271Z","submitted_at":"2025-06-06T09:12:51Z","title":"WhisQ: Cross-Modal Representation Learning for Text-to-Music MOS Prediction","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T10:16:56.175634Z"},"links":{"cited_paper":"/paper/2501.09291","citing_paper":"/paper/2506.05899"},"observation_digest":"sha256:a148e1554423896034d3f4bcf39abc222c1d663aab87cbe54d4d06cba167d5d1","observation_id":"0e99131c-60e1-43be-b897-8b27fd569fc6","resolution":{"observed_at":"2026-08-07T10:16:57.039584Z","resolver_source":"local_arxiv","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":"2501.09291","last_updated":"2025-03-15T12:38:50Z","snapshot_observed_at":"2026-08-05T03:11:14.295782Z","submitted_at":"2025-01-16T04:53:29Z","title":"LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.09291","snapshot_observed_at":"2026-07-13T01:06:45.040464Z","title":"LA VCap: LLM-based Audio-Visual Captioning using Optimal Transport,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.09001","last_updated":"2026-07-10T00:07:25Z","snapshot_observed_at":"2026-08-08T00:10:11.041744Z","submitted_at":"2026-07-10T00:07:25Z","title":"Optimal Transport-based Semantic Alignment for LLM-based Audio-Visual Speech Recognition","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-13T01:06:45.040464Z"},"links":{"cited_paper":"/paper/2501.09291","citing_paper":"/paper/2607.09001"},"observation_digest":"sha256:4b4b481280a8e5b06dd6313a70a8d5865e72c6dbb6ac1047a09c13fe249488ae","observation_id":"840821bc-8bd9-41ef-9568-2393b100d7b9","resolution":{"observed_at":"2026-07-13T01:06:45.040464Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2501.09291/citation-record","integrity":"/paper/2501.09291/integrity","json":"/paper/2501.09291/citation-record.json","paper":"/paper/2501.09291"},"outbound":[],"paper":{"arxiv_id":"2501.09291","last_updated":"2025-03-15T12:38:50Z","latest_version":2,"primary_category":"cs.MM","snapshot_observed_at":"2026-08-05T03:11:14.295782Z","submitted_at":"2025-01-16T04:53:29Z","title":"LAVCap: LLM-based Audio-Visual Captioning using Optimal Transport"},"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:2501.09291."}