{"as_of":"2026-08-10T08:27:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a154f2c44e267284d5eb822adb2a28fb0fad541ae6f3f6eaf4874ed8f491fa75","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":"2026-08-10T06:31:04.303077+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":"2026-08-01T06:08:22.246100Z","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":"2026-05-19T20:28:39.290146Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2305.14985","last_updated":"2026-06-18T04:46:43Z","snapshot_observed_at":"2026-07-06T15:32:25.931739Z","submitted_at":"2023-05-24T10:19:57Z","title":"IdealGPT: Iteratively Decomposing Vision and Language Reasoning via Large Language Models","version":3},"cited_work":{"arxiv_id":"2305.14985","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.14985","snapshot_observed_at":"2026-06-19T17:11:28.576965Z","title":"Idealgpt: Iteratively decompos- ing vision and language reasoning via large language models","venue":null,"work_id":"0f1d5624-83b9-4f7b-be37-644dbad8444b","year":2023},"citing_paper":{"arxiv_id":"2306.13549","last_updated":"2024-11-29T15:51:23Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-06-23T15:21:52Z","title":"A Survey on Multimodal Large Language Models","version":4},"reference_index":198,"source":"pdf_text","source_observed_at":"2026-05-16T02:56:41.658658Z"},"links":{"cited_paper":"/paper/2305.14985","citing_paper":"/paper/2306.13549"},"observation_digest":"sha256:8a124100ce67a74bc41776f8675f59f7decc07abb8445fb45ac01e0f0581551c","observation_id":"7464d219-9c4a-48e7-a6a6-da47115615aa","resolution":{"observed_at":"2026-06-19T17:11:28.576965Z","resolver_source":"arxiv_id","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"}},{"citation":{"cited_paper":{"arxiv_id":"2305.14985","last_updated":"2026-06-18T04:46:43Z","snapshot_observed_at":"2026-07-06T15:32:25.931739Z","submitted_at":"2023-05-24T10:19:57Z","title":"IdealGPT: Iteratively Decomposing Vision and Language Reasoning via Large Language Models","version":3},"cited_work":{"arxiv_id":"2305.14985","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.14985","snapshot_observed_at":"2026-06-19T17:11:28.576965Z","title":"Idealgpt: Iteratively decompos- ing vision and language reasoning via large language models","venue":null,"work_id":"0f1d5624-83b9-4f7b-be37-644dbad8444b","year":2023},"citing_paper":{"arxiv_id":"2307.06435","last_updated":"2024-10-17T01:10:40Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-07-12T20:01:52Z","title":"A Comprehensive Overview of Large Language Models","version":10},"reference_index":296,"source":"pdf_text","source_observed_at":"2026-05-19T20:28:38.900026Z"},"links":{"cited_paper":"/paper/2305.14985","citing_paper":"/paper/2307.06435"},"observation_digest":"sha256:355b8404569ab0f27cf0a470f525f3cc9b8d01e37c465e02ff974bb1fe12059e","observation_id":"4a6f1d00-b984-4744-b690-d72d40881a7a","resolution":{"observed_at":"2026-06-19T17:11:28.576965Z","resolver_source":"arxiv_id","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"}},{"citation":{"cited_paper":{"arxiv_id":"2305.14985","last_updated":"2026-06-18T04:46:43Z","snapshot_observed_at":"2026-07-06T15:32:25.931739Z","submitted_at":"2023-05-24T10:19:57Z","title":"IdealGPT: Iteratively Decomposing Vision and Language Reasoning via Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.14985","snapshot_observed_at":"2026-08-01T06:08:22.246100Z","title":"Idealgpt: Iteratively decomposing vision and language reasoning via large language mod- els,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.22013","last_updated":"2026-07-24T06:22:40Z","snapshot_observed_at":"2026-08-07T11:15:26.226893Z","submitted_at":"2026-07-24T06:22:40Z","title":"Visual Saliency Steering Distillation for Multimodal Chain-of-Thought Reasoning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T06:08:22.246100Z"},"links":{"cited_paper":"/paper/2305.14985","citing_paper":"/paper/2607.22013"},"observation_digest":"sha256:295d0684bbe55979b4a20431cc81eebe427276a62b0487426d48be8536b604bc","observation_id":"3a77c7c5-ada7-437b-91a1-9d8aa1a48739","resolution":{"observed_at":"2026-08-01T06:08:22.246100Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2305.14985/citation-record","integrity":"/paper/2305.14985/integrity","json":"/paper/2305.14985/citation-record.json","paper":"/paper/2305.14985"},"outbound":[],"paper":{"arxiv_id":"2305.14985","last_updated":"2026-06-18T04:46:43Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T15:32:25.931739Z","submitted_at":"2023-05-24T10:19:57Z","title":"IdealGPT: Iteratively Decomposing Vision and Language Reasoning via Large Language Models"},"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 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2305.14985."}