{"as_of":"2026-08-14T18:02:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6ea5965eb5979dac9aa656396f22308ae63406b8f067fe070bb5e46a3280b41e","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":"2026-08-14T06:32:32.682623+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":"2026-08-12T17:07:00.889826Z","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":"2026-05-17T02:18:52.833818Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.14156","last_updated":"2024-10-06T09:51:25Z","snapshot_observed_at":"2026-08-13T00:01:00.777873Z","submitted_at":"2024-05-23T04:08:23Z","title":"Unveiling the Tapestry of Consistency in Large Vision-Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.14156","snapshot_observed_at":"2026-08-12T17:07:00.889826Z","title":"Unveiling the tapestry of con- sistency in large vision-language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.12951","last_updated":"2025-03-17T02:21:38Z","snapshot_observed_at":"2026-08-12T18:26:22.658520Z","submitted_at":"2024-11-20T00:47:17Z","title":"On the Consistency of Video Large Language Models in Temporal Comprehension","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T17:07:00.889826Z"},"links":{"cited_paper":"/paper/2405.14156","citing_paper":"/paper/2411.12951"},"observation_digest":"sha256:cc10ba337ede7d6e56c0037f329a12f2a42dc6dbc59dbc0e3179f706cd1ea60b","observation_id":"5f458d21-c5b7-4dbf-a0ca-533ea3693a1b","resolution":{"observed_at":"2026-08-12T17:07:00.889826Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.14156","last_updated":"2024-10-06T09:51:25Z","snapshot_observed_at":"2026-08-13T00:01:00.777873Z","submitted_at":"2024-05-23T04:08:23Z","title":"Unveiling the Tapestry of Consistency in Large Vision-Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.14156","snapshot_observed_at":"2026-08-12T15:03:24.493884Z","title":"Zhang, F","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.14725","last_updated":"2025-06-03T08:55:05Z","snapshot_observed_at":"2026-08-14T05:35:04.712225Z","submitted_at":"2024-11-22T04:41:20Z","title":"Evaluating and Advancing Multimodal Large Language Models in Perception Ability Lens","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-12T15:03:24.493884Z"},"links":{"cited_paper":"/paper/2405.14156","citing_paper":"/paper/2411.14725"},"observation_digest":"sha256:f9bafc9c2dba79fd56118206e124f5e384a45c3e23700b8266077ca3b27675f2","observation_id":"07c16031-c15b-45eb-8a98-14b19ba41a23","resolution":{"observed_at":"2026-08-12T15:03:24.493884Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.14156","last_updated":"2024-10-06T09:51:25Z","snapshot_observed_at":"2026-08-13T00:01:00.777873Z","submitted_at":"2024-05-23T04:08:23Z","title":"Unveiling the Tapestry of Consistency in Large Vision-Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.14156","snapshot_observed_at":"2026-08-11T23:54:23.219550Z","title":"Unveiling the tapestry of consistency in large vision-language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.02104","last_updated":"2024-12-03T02:54:31Z","snapshot_observed_at":"2026-08-13T18:59:32.206758Z","submitted_at":"2024-12-03T02:54:31Z","title":"Explainable and Interpretable Multimodal Large Language Models: A Comprehensive Survey","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T23:54:23.219550Z"},"links":{"cited_paper":"/paper/2405.14156","citing_paper":"/paper/2412.02104"},"observation_digest":"sha256:047047474bcc557fe10bb5cda56386610201a93be80f88cc0b80ecd2a184ab6f","observation_id":"1296e97a-dea7-40e7-bbe5-81181890416e","resolution":{"observed_at":"2026-08-11T23:54:23.219550Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.14156","last_updated":"2024-10-06T09:51:25Z","snapshot_observed_at":"2026-08-13T00:01:00.777873Z","submitted_at":"2024-05-23T04:08:23Z","title":"Unveiling the Tapestry of Consistency in Large Vision-Language Models","version":4},"cited_work":{"arxiv_id":"2405.14156","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2405.14156","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Unveiling the tapestry of consistency in large vision-language models","venue":null,"work_id":"1c6734ef-9638-4ec6-8ce5-6afe5f6e3d3b","year":2024},"citing_paper":{"arxiv_id":"2512.03992","last_updated":"2026-04-29T16:22:49Z","snapshot_observed_at":"2026-08-11T22:02:45.507847Z","submitted_at":"2025-12-03T17:22:29Z","title":"Value-Guided Iterative Refinement and the DIQ-H Benchmark for Evaluating VLM Robustness","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-17T02:13:55.284593Z"},"links":{"cited_paper":"/paper/2405.14156","citing_paper":"/paper/2512.03992"},"observation_digest":"sha256:e8b0bbd1ba8385eae0a6247f8ee851fae6f82e7738808dd1cea042bb11feb481","observation_id":"d78b58d9-4a81-4468-8160-4d7d6b3cec0c","resolution":{"observed_at":"2026-05-17T02:18:52.835893Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2405.14156/citation-record","integrity":"/paper/2405.14156/integrity","json":"/paper/2405.14156/citation-record.json","paper":"/paper/2405.14156"},"outbound":[],"paper":{"arxiv_id":"2405.14156","last_updated":"2024-10-06T09:51:25Z","latest_version":4,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-13T00:01:00.777873Z","submitted_at":"2024-05-23T04:08:23Z","title":"Unveiling the Tapestry of Consistency in Large Vision-Language Models"},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2405.14156."}