{"as_of":"2026-08-08T04:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:29cade0da7481a3b4416530a77c8dd44c98cb43e57fa58cbc042a44d23274005","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":"2026-08-07T06:34:17.273281+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":"2026-08-07T12:37:50.658662Z","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":"2026-05-11T19:16:08.251671Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.04670","last_updated":"2025-07-09T08:04:21Z","snapshot_observed_at":"2026-08-02T10:38:59.539887Z","submitted_at":"2025-01-08T18:30:53Z","title":"Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.04670","snapshot_observed_at":"2026-08-07T12:37:50.658662Z","title":"Are they the same? exploring visual correspondence shortcomings of multimodal llms.arXiv preprint arXiv:2501.04670, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.24164","last_updated":"2025-05-30T03:11:46Z","snapshot_observed_at":"2026-08-07T12:29:46.881822Z","submitted_at":"2025-05-30T03:11:46Z","title":"Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:50.658662Z"},"links":{"cited_paper":"/paper/2501.04670","citing_paper":"/paper/2505.24164"},"observation_digest":"sha256:4139a615468d5a32efc0a20dc105d4c45d196c365bdf86c7e257fb0b5ad60b83","observation_id":"b1c18b3a-35d8-48a1-9128-c02701f41d19","resolution":{"observed_at":"2026-08-07T12:37:50.658662Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.04670","last_updated":"2025-07-09T08:04:21Z","snapshot_observed_at":"2026-08-02T10:38:59.539887Z","submitted_at":"2025-01-08T18:30:53Z","title":"Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.04670","snapshot_observed_at":"2026-08-07T00:23:56.252708Z","title":"Are they the same? exploring visual correspondence shortcomings of multimodal llms.arXiv preprint arXiv:2501.04670, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.14471","last_updated":"2025-06-17T12:35:23Z","snapshot_observed_at":"2026-08-07T09:15:22.290008Z","submitted_at":"2025-06-17T12:35:23Z","title":"Dense360: Dense Understanding from Omnidirectional Panoramas","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-07T00:23:56.252708Z"},"links":{"cited_paper":"/paper/2501.04670","citing_paper":"/paper/2506.14471"},"observation_digest":"sha256:321a1a3cdaba8630acdde71b6b4643df036c1ab0dab178b77fb54f9227d7f0a4","observation_id":"cd2f3850-3373-487a-b4ea-3993548ed273","resolution":{"observed_at":"2026-08-07T00:23:56.252708Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.04670","last_updated":"2025-07-09T08:04:21Z","snapshot_observed_at":"2026-08-02T10:38:59.539887Z","submitted_at":"2025-01-08T18:30:53Z","title":"Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.04670","snapshot_observed_at":"2026-08-06T22:10:23.293868Z","title":"Are image1 and image2 the same?","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.22434","last_updated":"2025-06-27T17:59:27Z","snapshot_observed_at":"2026-08-06T22:01:48.405215Z","submitted_at":"2025-06-27T17:59:27Z","title":"MiCo: Multi-image Contrast for Reinforcement Visual Reasoning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T22:10:23.293868Z"},"links":{"cited_paper":"/paper/2501.04670","citing_paper":"/paper/2506.22434"},"observation_digest":"sha256:aa94bfe43df41895636ae81cd651d5802023e871b644df614eda1a2ab21a830e","observation_id":"cab53f23-af9c-4c36-83a5-25d31c6b7cc9","resolution":{"observed_at":"2026-08-06T22:10:23.293868Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.04670","last_updated":"2025-07-09T08:04:21Z","snapshot_observed_at":"2026-08-02T10:38:59.539887Z","submitted_at":"2025-01-08T18:30:53Z","title":"Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs","version":3},"cited_work":{"arxiv_id":"2501.04670","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.04670","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"60562179-276a-4072-895b-0e831838780e","year":2025},"citing_paper":{"arxiv_id":"2604.22498","last_updated":"2026-04-24T12:26:49Z","snapshot_observed_at":"2026-07-06T23:08:51.913995Z","submitted_at":"2026-04-24T12:26:49Z","title":"CGC: Compositional Grounded Contrast for Fine-Grained Multi-Image Understanding","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-05-08T12:26:01.568507Z"},"links":{"cited_paper":"/paper/2501.04670","citing_paper":"/paper/2604.22498"},"observation_digest":"sha256:f6ffedd73a95032a7458b81ffef09165beef83af74e093ca6d1ff3fff6934d8b","observation_id":"b8a408e2-9f44-4a31-952e-edf973f705e3","resolution":{"observed_at":"2026-05-11T19:16:08.254158Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2501.04670/citation-record","integrity":"/paper/2501.04670/integrity","json":"/paper/2501.04670/citation-record.json","paper":"/paper/2501.04670"},"outbound":[],"paper":{"arxiv_id":"2501.04670","last_updated":"2025-07-09T08:04:21Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-02T10:38:59.539887Z","submitted_at":"2025-01-08T18:30:53Z","title":"Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2501.04670."}