{"as_of":"2026-08-11T00:30:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:62c1bdb4a73630875ea75efe57d6850204a71ea7f00a66bb5085102e366239ed","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":"2026-08-10T06:31:04.303077+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":"2026-08-10T23:39:18.129942Z","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":"2026-08-09T21:39:22.346160Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.17815","last_updated":"2024-11-04T09:03:31Z","snapshot_observed_at":"2026-07-06T18:21:01.419111Z","submitted_at":"2024-05-28T04:23:00Z","title":"Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.17815","snapshot_observed_at":"2026-08-10T23:39:18.129942Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.20105","last_updated":"2024-12-28T10:17:29Z","snapshot_observed_at":"2026-08-10T23:30:14.051344Z","submitted_at":"2024-12-28T10:17:29Z","title":"ST$^3$: Accelerating Multimodal Large Language Model by Spatial-Temporal Visual Token Trimming","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-10T23:39:18.129942Z"},"links":{"cited_paper":"/paper/2405.17815","citing_paper":"/paper/2412.20105"},"observation_digest":"sha256:68c072b0ef65d1e08bfa1190f11e1621a3779f205889dd763b6e58659af13662","observation_id":"58fb2e2a-cc0e-4ffb-b83a-60c22a6a1e66","resolution":{"observed_at":"2026-08-10T23:39:18.129942Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.17815","last_updated":"2024-11-04T09:03:31Z","snapshot_observed_at":"2026-07-06T18:21:01.419111Z","submitted_at":"2024-05-28T04:23:00Z","title":"Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model","version":2},"cited_work":{"arxiv_id":"2405.17815","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.17815","snapshot_observed_at":"2026-08-09T21:39:22.346160Z","title":"Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model","venue":"cs.CV","work_id":"1e42192a-5c43-4467-a40b-01448081c48f","year":2024},"citing_paper":{"arxiv_id":"2501.19036","last_updated":"2025-05-30T12:26:44Z","snapshot_observed_at":"2026-08-10T12:01:17.734125Z","submitted_at":"2025-01-31T11:09:16Z","title":"RedundancyLens: Revealing and Exploiting Visual Token Processing Redundancy for Efficient Decoder-Only MLLMs","version":3},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-09T21:39:21.732229Z"},"links":{"cited_paper":"/paper/2405.17815","citing_paper":"/paper/2501.19036"},"observation_digest":"sha256:127d09396b667d03e220edadcec8affe3ff1e25db16101da34a29c8beac41e58","observation_id":"c2915a8a-18f5-4106-8305-89651466dcec","resolution":{"observed_at":"2026-08-09T21:39:22.353394Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2405.17815/citation-record","integrity":"/paper/2405.17815/integrity","json":"/paper/2405.17815/citation-record.json","paper":"/paper/2405.17815"},"outbound":[],"paper":{"arxiv_id":"2405.17815","last_updated":"2024-11-04T09:03:31Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T18:21:01.419111Z","submitted_at":"2024-05-28T04:23:00Z","title":"Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2405.17815."}