{"as_of":"2026-08-09T18:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ecfd56cc549120e3b043310842dcb81a84ab02446970adba789ff88b4cb15da5","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":"2026-08-09T06:31:02.800959+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":"2026-08-07T12:50:47.074049Z","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":"2026-05-21T11:10:02.368241Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2312.05278","last_updated":"2024-04-12T10:26:01Z","snapshot_observed_at":"2026-08-05T05:02:51.320588Z","submitted_at":"2023-12-08T09:02:45Z","title":"Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.05278","snapshot_observed_at":"2026-08-07T12:50:47.074049Z","title":"Lyrics: Boosting fine-grained language-vision alignment and comprehension via semantic-aware visual objects,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.23386","last_updated":"2025-05-29T12:11:28Z","snapshot_observed_at":"2026-08-07T12:44:29.368945Z","submitted_at":"2025-05-29T12:11:28Z","title":"VModA: An Effective Framework for Adaptive NSFW Image Moderation","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T12:50:47.074049Z"},"links":{"cited_paper":"/paper/2312.05278","citing_paper":"/paper/2505.23386"},"observation_digest":"sha256:cb838c1d10658d916b0270313d4970e2fd596e8614f1f66977921ba6aba53b94","observation_id":"00026dee-e404-40f1-8214-4e932b35e34c","resolution":{"observed_at":"2026-08-07T12:50:47.074049Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.05278","last_updated":"2024-04-12T10:26:01Z","snapshot_observed_at":"2026-08-05T05:02:51.320588Z","submitted_at":"2023-12-08T09:02:45Z","title":"Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects","version":2},"cited_work":{"arxiv_id":"2312.05278","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2312.05278","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"426f69a7-026d-41af-9750-871ba2729fab","year":2024},"citing_paper":{"arxiv_id":"2603.25120","last_updated":"2026-03-26T07:45:29Z","snapshot_observed_at":"2026-07-06T22:50:37.468743Z","submitted_at":"2026-03-26T07:45:29Z","title":"DFLOP: A Data-driven Framework for Multimodal LLM Training Pipeline Optimization","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-21T11:05:07.336827Z"},"links":{"cited_paper":"/paper/2312.05278","citing_paper":"/paper/2603.25120"},"observation_digest":"sha256:cad950282519e53b058ef1524339370b9f6d823ac5fc1e9d10507fe8992c03ac","observation_id":"ec4507db-6f9d-4bfd-9647-eec124ec6c8b","resolution":{"observed_at":"2026-05-21T11:10:02.370223Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2312.05278/citation-record","integrity":"/paper/2312.05278/integrity","json":"/paper/2312.05278/citation-record.json","paper":"/paper/2312.05278"},"outbound":[],"paper":{"arxiv_id":"2312.05278","last_updated":"2024-04-12T10:26:01Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-05T05:02:51.320588Z","submitted_at":"2023-12-08T09:02:45Z","title":"Lyrics: Boosting Fine-grained Language-Vision Alignment and Comprehension via Semantic-aware Visual Objects"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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:2312.05278."}