{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SLQNQOQ4QNWP5CM2C54HPOAL5D","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":"cd3d7d9de49dec4b39b46941c366ec6b59154c7c3c7572700af7dd247703c192","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-22T17:59:57Z","title_canon_sha256":"7b12bdefa19075c63cbd99c478a06bf4bf9e64272dfb9e339defa68ac1b90798"},"schema_version":"1.0","source":{"id":"2410.17251","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.17251","created_at":"2026-07-05T09:54:47Z"},{"alias_kind":"arxiv_version","alias_value":"2410.17251v3","created_at":"2026-07-05T09:54:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17251","created_at":"2026-07-05T09:54:47Z"},{"alias_kind":"pith_short_12","alias_value":"SLQNQOQ4QNWP","created_at":"2026-07-05T09:54:47Z"},{"alias_kind":"pith_short_16","alias_value":"SLQNQOQ4QNWP5CM2","created_at":"2026-07-05T09:54:47Z"},{"alias_kind":"pith_short_8","alias_value":"SLQNQOQ4","created_at":"2026-07-05T09:54:47Z"}],"graph_snapshots":[{"event_id":"sha256:e6a864e60efda977d3a963e584bc656beafd3bdd43e6e025c3f90d1f3bc219da","target":"graph","created_at":"2026-07-05T09:54:47Z","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/2410.17251/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper focuses on creating synthetic data to improve the quality of image captions. Existing works typically have two shortcomings. First, they caption images from scratch, ignoring existing alt-text metadata, and second, lack transparency if the captioners' training data (e.g. GPT) is unknown. In this paper, we study a principled approach Altogether based on the key idea to edit and re-align existing alt-texts associated with the images. To generate training data, we perform human annotation where annotators start with the existing alt-text and re-align it to the image content in multiple","authors_text":"Ching-Feng Yeh, Christine Jou, Christoph Feichtenhofer, Gargi Ghosh, Hu Xu, Jacob Kahn, Luke Zettlemoyer, Omer Levy, Po-Yao Huang, Saining Xie, Shang-Wen Li, Wen-tau Yih, Xiaoqing Ellen Tan","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-22T17:59:57Z","title":"Altogether: Image Captioning via Re-aligning Alt-text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17251","kind":"arxiv","version":3},"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:f7ee41a9ad4f88d5e80a26ca2e6197d4e832f553d8cecdeb15e76e8429a1465a","target":"record","created_at":"2026-07-05T09:54:47Z","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":"cd3d7d9de49dec4b39b46941c366ec6b59154c7c3c7572700af7dd247703c192","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-22T17:59:57Z","title_canon_sha256":"7b12bdefa19075c63cbd99c478a06bf4bf9e64272dfb9e339defa68ac1b90798"},"schema_version":"1.0","source":{"id":"2410.17251","kind":"arxiv","version":3}},"canonical_sha256":"92e0d83a1c836cfe899a177877b80be8cbdfb8148a6d19feb905f86fc6909894","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92e0d83a1c836cfe899a177877b80be8cbdfb8148a6d19feb905f86fc6909894","first_computed_at":"2026-07-05T09:54:47.982388Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:47.982388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JQtLTvXiy4SNukjp7B+LvcZzEh8kdeBlFAzwaMJc92+mJLCn6N3e4hrjM6Sn7OwRG6XRikGQ5KKCGdZeGbMRCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:47.982804Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.17251","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f7ee41a9ad4f88d5e80a26ca2e6197d4e832f553d8cecdeb15e76e8429a1465a","sha256:e6a864e60efda977d3a963e584bc656beafd3bdd43e6e025c3f90d1f3bc219da"],"state_sha256":"8b9c0af71fbcd0b978e9e217846cf402171e29beb94bc1f0fed754d8de57a285"}