{"as_of":"2026-08-07T18:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:df3f9b00495c94e7ac294d9435cc40205cae7a16850cea9684fd0a251f471b78","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T14:46:44.356720Z","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":"2026-07-03T20:18:57.664359Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.16863","last_updated":"2025-04-02T06:19:46Z","snapshot_observed_at":"2026-07-06T19:56:52.724589Z","submitted_at":"2024-11-25T19:01:03Z","title":"Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.16863","snapshot_observed_at":"2026-08-07T14:46:44.356720Z","title":"Augmenting multimodal llms with self-reflective tokens for knowledge-based visual question answering.arXiv preprint arXiv:2411.16863, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.17670","last_updated":"2025-07-07T20:01:47Z","snapshot_observed_at":"2026-08-07T14:40:37.272877Z","submitted_at":"2025-05-23T09:36:53Z","title":"Towards General Continuous Memory for Vision-Language Models","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T14:46:44.356720Z"},"links":{"cited_paper":"/paper/2411.16863","citing_paper":"/paper/2505.17670"},"observation_digest":"sha256:9cefee8e751a2f984ecdd0bd548e416f02322be3da59594881edb2f086527958","observation_id":"8109059b-35dd-4671-8911-22da5803b3ed","resolution":{"observed_at":"2026-08-07T14:46:44.356720Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.16863","last_updated":"2025-04-02T06:19:46Z","snapshot_observed_at":"2026-07-06T19:56:52.724589Z","submitted_at":"2024-11-25T19:01:03Z","title":"Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.16863","snapshot_observed_at":"2026-08-06T17:55:45.258885Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09693","last_updated":"2025-07-13T16:09:58Z","snapshot_observed_at":"2026-08-06T19:46:33.050466Z","submitted_at":"2025-07-13T16:09:58Z","title":"ExpStar: Towards Automatic Commentary Generation for Multi-discipline Scientific Experiments","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T17:55:45.258885Z"},"links":{"cited_paper":"/paper/2411.16863","citing_paper":"/paper/2507.09693"},"observation_digest":"sha256:1bd123beafc078c86ba65d6e02bd63d8d3ab5b4209190540e59be5bf15b2144b","observation_id":"da91c099-b84d-4551-8bd6-523da596ae4e","resolution":{"observed_at":"2026-08-06T17:55:45.258885Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.16863","last_updated":"2025-04-02T06:19:46Z","snapshot_observed_at":"2026-07-06T19:56:52.724589Z","submitted_at":"2024-11-25T19:01:03Z","title":"Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering","version":2},"cited_work":{"arxiv_id":"2411.16863","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.16863","snapshot_observed_at":"2026-07-03T20:18:57.664359Z","title":"arXiv preprint arXiv:2411.16863 , year=","venue":null,"work_id":"6ffb23ca-21bc-4ad1-bc88-8fd6190ab161","year":null},"citing_paper":{"arxiv_id":"2606.17888","last_updated":"2026-06-16T13:09:32Z","snapshot_observed_at":"2026-08-04T07:49:41.211792Z","submitted_at":"2026-06-16T13:09:32Z","title":"MathVis-Fine: Aligning Visual Supervision with Necessity via Progressive Dependency-Guided Training for Multimodal Mathematical Reasoning","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-06-27T01:23:40.564561Z"},"links":{"cited_paper":"/paper/2411.16863","citing_paper":"/paper/2606.17888"},"observation_digest":"sha256:cff6c87878542fad08103dbdcc820144584347bccb9b15df67871b255077ea47","observation_id":"4882e389-ddcf-4108-8eca-840a641f684d","resolution":{"observed_at":"2026-07-03T20:18:57.667225Z","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/2411.16863/citation-record","integrity":"/paper/2411.16863/integrity","json":"/paper/2411.16863/citation-record.json","paper":"/paper/2411.16863"},"outbound":[],"paper":{"arxiv_id":"2411.16863","last_updated":"2025-04-02T06:19:46Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T19:56:52.724589Z","submitted_at":"2024-11-25T19:01:03Z","title":"Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering"},"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 3 inbound Pith citation observations for arXiv:2411.16863."}