{"as_of":"2026-08-07T16:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:621ebfaa028026b716b79c2e10bcff5b49795f3d0c78a9984b765128fedfe541","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":"2026-08-07T11:26:58.485939Z","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":"2026-05-20T11:45:17.617405Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2404.15100","last_updated":"2024-04-23T14:53:15Z","snapshot_observed_at":"2026-08-01T21:34:06.143524Z","submitted_at":"2024-04-23T14:53:15Z","title":"Multimodal Large Language Model is a Human-Aligned Annotator for Text-to-Image Generation","version":1},"cited_work":{"arxiv_id":"2404.15100","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.15100","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"52825252-7b09-4e53-bfcd-80362d3b9dcf","year":2024},"citing_paper":{"arxiv_id":"2501.09732","last_updated":"2025-01-16T18:30:37Z","snapshot_observed_at":"2026-07-06T20:22:04.328179Z","submitted_at":"2025-01-16T18:30:37Z","title":"Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-05-20T11:45:17.473970Z"},"links":{"cited_paper":"/paper/2404.15100","citing_paper":"/paper/2501.09732"},"observation_digest":"sha256:9f6927587d5672b6cabc9cfdb75edd7db7e476d499f13cdb2615bca7e04a2cf1","observation_id":"1646c3ce-daef-4067-8ea8-84b068fe7451","resolution":{"observed_at":"2026-05-20T11:45:17.618935Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2404.15100","last_updated":"2024-04-23T14:53:15Z","snapshot_observed_at":"2026-08-01T21:34:06.143524Z","submitted_at":"2024-04-23T14:53:15Z","title":"Multimodal Large Language Model is a Human-Aligned Annotator for Text-to-Image Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.15100","snapshot_observed_at":"2026-08-07T11:26:58.485939Z","title":"Multimodal large language model is a human-aligned annotator for text-to-image generation.ArXiv, abs/2404.15100,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.02698","last_updated":"2025-06-06T03:14:26Z","snapshot_observed_at":"2026-08-07T11:15:42.841737Z","submitted_at":"2025-06-03T09:47:22Z","title":"Smoothed Preference Optimization via ReNoise Inversion for Aligning Diffusion Models with Varied Human Preferences","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T11:26:58.485939Z"},"links":{"cited_paper":"/paper/2404.15100","citing_paper":"/paper/2506.02698"},"observation_digest":"sha256:19b18fab4df88142248bf3ae11364a9ce34501e4e36426aae3c5884787bc470e","observation_id":"c1c3c3fc-88bb-4ecf-860f-413d10b0ec8b","resolution":{"observed_at":"2026-08-07T11:26:58.485939Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.15100","last_updated":"2024-04-23T14:53:15Z","snapshot_observed_at":"2026-08-01T21:34:06.143524Z","submitted_at":"2024-04-23T14:53:15Z","title":"Multimodal Large Language Model is a Human-Aligned Annotator for Text-to-Image Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.15100","snapshot_observed_at":"2026-08-06T18:48:45.322166Z","title":"Multimodal large language model is a human-aligned annotator for text-to- image generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.07317","last_updated":"2025-07-28T17:21:56Z","snapshot_observed_at":"2026-08-06T18:41:29.945236Z","submitted_at":"2025-07-09T22:29:47Z","title":"ADIEE: Automatic Dataset Creation and Scorer for Instruction-Guided Image Editing Evaluation","version":2},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-06T18:48:45.322166Z"},"links":{"cited_paper":"/paper/2404.15100","citing_paper":"/paper/2507.07317"},"observation_digest":"sha256:eeb0accc32890832ec6d623d4b4633680da2e446c0574d8a33e66f433db3561d","observation_id":"f2883f65-6823-4ff0-ae40-905a7a59639b","resolution":{"observed_at":"2026-08-06T18:48:45.322166Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2404.15100/citation-record","integrity":"/paper/2404.15100/integrity","json":"/paper/2404.15100/citation-record.json","paper":"/paper/2404.15100"},"outbound":[],"paper":{"arxiv_id":"2404.15100","last_updated":"2024-04-23T14:53:15Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-01T21:34:06.143524Z","submitted_at":"2024-04-23T14:53:15Z","title":"Multimodal Large Language Model is a Human-Aligned Annotator for Text-to-Image Generation"},"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:2404.15100."}