{"as_of":"2026-08-08T08:48:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a3262c7f762e55651bd32612a0fce0b158aaae071323f722c0c8200c335fbde0","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T15:15:12.354668Z","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":"2026-08-06T13:18:06.796995Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.00556","last_updated":"2024-12-08T04:41:32Z","snapshot_observed_at":"2026-08-08T00:43:47.244767Z","submitted_at":"2024-11-30T18:54:32Z","title":"Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.00556","snapshot_observed_at":"2026-08-07T15:15:12.354668Z","title":"N., and Yu, L","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.15816","last_updated":"2025-05-21T17:59:52Z","snapshot_observed_at":"2026-08-08T00:44:22.305190Z","submitted_at":"2025-05-21T17:59:52Z","title":"Streamline Without Sacrifice -- Squeeze out Computation Redundancy in LMM","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T15:15:12.354668Z"},"links":{"cited_paper":"/paper/2412.00556","citing_paper":"/paper/2505.15816"},"observation_digest":"sha256:5f401b57f073857d073b3e620c3167c00336b9d77d405799f01dd9509cb9f81c","observation_id":"709f18f3-12eb-4ec6-8bff-aff98e463c23","resolution":{"observed_at":"2026-08-07T15:15:12.354668Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.00556","last_updated":"2024-12-08T04:41:32Z","snapshot_observed_at":"2026-08-08T00:43:47.244767Z","submitted_at":"2024-11-30T18:54:32Z","title":"Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.00556","snapshot_observed_at":"2026-08-07T00:42:53.738046Z","title":"N.; and Yu, L","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.13166","last_updated":"2025-06-16T07:21:11Z","snapshot_observed_at":"2026-08-08T08:38:39.497266Z","submitted_at":"2025-06-16T07:21:11Z","title":"GreedyPrune: Retenting Critical Visual Token Set for Large Vision Language Models","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-07T00:42:53.738046Z"},"links":{"cited_paper":"/paper/2412.00556","citing_paper":"/paper/2506.13166"},"observation_digest":"sha256:12071a66963d2a7a09d8477f94fdc0f08aef32e715112bcce480417061b94070","observation_id":"3f8c6000-e94e-4211-804f-d21e7746ec13","resolution":{"observed_at":"2026-08-07T00:42:53.738046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.00556","last_updated":"2024-12-08T04:41:32Z","snapshot_observed_at":"2026-08-08T00:43:47.244767Z","submitted_at":"2024-11-30T18:54:32Z","title":"Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.00556","snapshot_observed_at":"2026-08-06T18:03:03.544777Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09334","last_updated":"2025-07-12T16:29:02Z","snapshot_observed_at":"2026-08-08T00:12:13.692263Z","submitted_at":"2025-07-12T16:29:02Z","title":"Fast3D: Accelerating 3D Multi-modal Large Language Models for Efficient 3D Scene Understanding","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-06T18:03:03.544777Z"},"links":{"cited_paper":"/paper/2412.00556","citing_paper":"/paper/2507.09334"},"observation_digest":"sha256:9d08d8038f4d7a2407c272583c187c5de65e4c9004a4f19d9871dec2342d2f4c","observation_id":"35ef04ae-baf7-481c-b4bf-7ee6ea162144","resolution":{"observed_at":"2026-08-06T18:03:03.544777Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.00556","last_updated":"2024-12-08T04:41:32Z","snapshot_observed_at":"2026-08-08T00:43:47.244767Z","submitted_at":"2024-11-30T18:54:32Z","title":"Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction","version":2},"cited_work":{"arxiv_id":"2412.00556","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.00556","snapshot_observed_at":"2026-08-06T13:18:06.796995Z","title":"Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction","venue":"cs.CV","work_id":"5af86bac-23dd-4312-96e6-4d493afa70b0","year":2024},"citing_paper":{"arxiv_id":"2507.20842","last_updated":"2025-07-28T13:50:53Z","snapshot_observed_at":"2026-08-07T09:17:15.026471Z","submitted_at":"2025-07-28T13:50:53Z","title":"METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:06.236925Z"},"links":{"cited_paper":"/paper/2412.00556","citing_paper":"/paper/2507.20842"},"observation_digest":"sha256:6c4c353a75c657d9d2999711fb142fb2de7bb56a1a381877e371b7c31e7522c2","observation_id":"3ceeb469-71fe-446b-85ce-77e1fbf36a68","resolution":{"observed_at":"2026-08-06T13:18:06.881928Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2412.00556/citation-record","integrity":"/paper/2412.00556/integrity","json":"/paper/2412.00556/citation-record.json","paper":"/paper/2412.00556"},"outbound":[],"paper":{"arxiv_id":"2412.00556","last_updated":"2024-12-08T04:41:32Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-08T00:43:47.244767Z","submitted_at":"2024-11-30T18:54:32Z","title":"Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction"},"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 4 inbound Pith citation observations for arXiv:2412.00556."}