{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BTNBKLKGBC5WQ6OASRDFUAGLBK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7100333a9aa7c0262c523eeb84e4c5b5f2f92e8f3ea512b001771d9f30d348aa","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-05T02:15:11Z","title_canon_sha256":"1d95c508ad1d57f302ca92917a8631e5c9433473da7abf7d5be08594743d8715"},"schema_version":"1.0","source":{"id":"2405.02793","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.02793","created_at":"2026-07-05T09:27:21Z"},{"alias_kind":"arxiv_version","alias_value":"2405.02793v2","created_at":"2026-07-05T09:27:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02793","created_at":"2026-07-05T09:27:21Z"},{"alias_kind":"pith_short_12","alias_value":"BTNBKLKGBC5W","created_at":"2026-07-05T09:27:21Z"},{"alias_kind":"pith_short_16","alias_value":"BTNBKLKGBC5WQ6OA","created_at":"2026-07-05T09:27:21Z"},{"alias_kind":"pith_short_8","alias_value":"BTNBKLKG","created_at":"2026-07-05T09:27:21Z"}],"graph_snapshots":[{"event_id":"sha256:ab4bc8eaa6363957221daa207e922ced5f8865664e9ec42f2963258f5fc5c9ad","target":"graph","created_at":"2026-07-05T09:27:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2405.02793/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the longstanding adage \"an image is worth a thousand words,\" generating accurate hyper-detailed image descriptions remains unsolved. Trained on short web-scraped image text, vision-language models often generate incomplete descriptions with visual inconsistencies. We address this via a novel data-centric approach with ImageInWords (IIW), a carefully designed human-in-the-loop framework for curating hyper-detailed image descriptions. Human evaluations on IIW data show major gains compared to recent datasets (+66%) and GPT4V (+48%) across comprehensiveness, specificity, hallucinations, a","authors_text":"Andrea Burns, Andrew Bunner, Burcu Karagol Ayan, Ceslee Montgomery, Jason Baldridge, Radu Soricut, Ranjay Krishna, Roopal Garg, Yasumasa Onoe, Yonatan Bitton","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-05T02:15:11Z","title":"ImageInWords: Unlocking Hyper-Detailed Image Descriptions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02793","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:56be19365ae5b26d3cb87e97c7bc60dea4d5ae2794fd12f769225df7f7f166c2","target":"record","created_at":"2026-07-05T09:27:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7100333a9aa7c0262c523eeb84e4c5b5f2f92e8f3ea512b001771d9f30d348aa","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-05T02:15:11Z","title_canon_sha256":"1d95c508ad1d57f302ca92917a8631e5c9433473da7abf7d5be08594743d8715"},"schema_version":"1.0","source":{"id":"2405.02793","kind":"arxiv","version":2}},"canonical_sha256":"0cda152d4608bb6879c094465a00cb0a9f121f24ce3d9acc639745158c6dcaf9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0cda152d4608bb6879c094465a00cb0a9f121f24ce3d9acc639745158c6dcaf9","first_computed_at":"2026-07-05T09:27:21.724751Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:27:21.724751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qiotNaYBv+mv079PN1cKeZj29ZfvEncY9h1QvyIJClZhLKzWJaJ96fEpHWJmcCcFAVuB+BbHWe7v1fxKsemMCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:27:21.725282Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.02793","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56be19365ae5b26d3cb87e97c7bc60dea4d5ae2794fd12f769225df7f7f166c2","sha256:ab4bc8eaa6363957221daa207e922ced5f8865664e9ec42f2963258f5fc5c9ad"],"state_sha256":"75347efc6e9e9ce9822c68d9c54492025fa029f130dcd38c549669465329b155"}