{"as_of":"2026-08-07T22:27:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e9670eb4035a79c8aaa2f3794c52fba54f2370e84e6a7c2b359abec3b186f675","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":"2026-08-07T06:34:17.273281+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":"2026-08-06T18:03:03.566081Z","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":"2026-07-04T08:29:41.872790Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.20105","last_updated":"2024-12-28T10:17:29Z","snapshot_observed_at":"2026-07-06T20:14:03.824268Z","submitted_at":"2024-12-28T10:17:29Z","title":"ST$^3$: Accelerating Multimodal Large Language Model by Spatial-Temporal Visual Token Trimming","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.20105","snapshot_observed_at":"2026-08-06T18:03:03.566081Z","title":"arXiv preprint arXiv:2412.20105 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09334","last_updated":"2025-07-12T16:29:02Z","snapshot_observed_at":"2026-08-06T17:56:14.969465Z","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":96,"source":"pdf_text","source_observed_at":"2026-08-06T18:03:03.566081Z"},"links":{"cited_paper":"/paper/2412.20105","citing_paper":"/paper/2507.09334"},"observation_digest":"sha256:05aba8429a5432fc88e70c4e516ed9010cd1dca91e8bcdf817797bf7a0ba1baf","observation_id":"b6237571-f163-467e-89ff-16f506e8ad34","resolution":{"observed_at":"2026-08-06T18:03:03.566081Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.20105","last_updated":"2024-12-28T10:17:29Z","snapshot_observed_at":"2026-07-06T20:14:03.824268Z","submitted_at":"2024-12-28T10:17:29Z","title":"ST$^3$: Accelerating Multimodal Large Language Model by Spatial-Temporal Visual Token Trimming","version":1},"cited_work":{"arxiv_id":"2412.20105","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.20105","snapshot_observed_at":"2026-07-04T08:29:41.872790Z","title":"FreeCodec: A disentangled neural speech codec with fewer tokens,","venue":null,"work_id":"03566c97-0d91-4931-97ba-c086a5a4b569","year":2025},"citing_paper":{"arxiv_id":"2606.21893","last_updated":"2026-06-20T05:58:50Z","snapshot_observed_at":"2026-08-06T08:56:11.950592Z","submitted_at":"2026-06-20T05:58:50Z","title":"AugCodec: A Low-Bitrate Disentangled Neural Speech Codec via Data Augmentation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-26T11:37:39.960212Z"},"links":{"cited_paper":"/paper/2412.20105","citing_paper":"/paper/2606.21893"},"observation_digest":"sha256:2b8dab86f77694646b5e8ad5ef6b6de501a029ffe35f3142a770ced4dc144684","observation_id":"8e90e4e0-9655-49a0-b360-2dbe2b102f3d","resolution":{"observed_at":"2026-07-04T08:29:41.874757Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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/2412.20105/citation-record","integrity":"/paper/2412.20105/integrity","json":"/paper/2412.20105/citation-record.json","paper":"/paper/2412.20105"},"outbound":[],"paper":{"arxiv_id":"2412.20105","last_updated":"2024-12-28T10:17:29Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T20:14:03.824268Z","submitted_at":"2024-12-28T10:17:29Z","title":"ST$^3$: Accelerating Multimodal Large Language Model by Spatial-Temporal Visual Token Trimming"},"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 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2412.20105."}