{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SLQNQOQ4QNWP5CM2C54HPOAL5D","short_pith_number":"pith:SLQNQOQ4","schema_version":"1.0","canonical_sha256":"92e0d83a1c836cfe899a177877b80be8cbdfb8148a6d19feb905f86fc6909894","source":{"kind":"arxiv","id":"2410.17251","version":3},"attestation_state":"computed","paper":{"title":"Altogether: Image Captioning via Re-aligning Alt-text","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","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","submitted_at":"2024-10-22T17:59:57Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.17251","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-22T17:59:57Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7b12bdefa19075c63cbd99c478a06bf4bf9e64272dfb9e339defa68ac1b90798","abstract_canon_sha256":"cd3d7d9de49dec4b39b46941c366ec6b59154c7c3c7572700af7dd247703c192"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:47.982804Z","signature_b64":"JQtLTvXiy4SNukjp7B+LvcZzEh8kdeBlFAzwaMJc92+mJLCn6N3e4hrjM6Sn7OwRG6XRikGQ5KKCGdZeGbMRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92e0d83a1c836cfe899a177877b80be8cbdfb8148a6d19feb905f86fc6909894","last_reissued_at":"2026-07-05T09:54:47.982388Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:47.982388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Altogether: Image Captioning via Re-aligning Alt-text","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","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","submitted_at":"2024-10-22T17:59:57Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17251","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.17251/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.17251","created_at":"2026-07-05T09:54:47.982445+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.17251v3","created_at":"2026-07-05T09:54:47.982445+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17251","created_at":"2026-07-05T09:54:47.982445+00:00"},{"alias_kind":"pith_short_12","alias_value":"SLQNQOQ4QNWP","created_at":"2026-07-05T09:54:47.982445+00:00"},{"alias_kind":"pith_short_16","alias_value":"SLQNQOQ4QNWP5CM2","created_at":"2026-07-05T09:54:47.982445+00:00"},{"alias_kind":"pith_short_8","alias_value":"SLQNQOQ4","created_at":"2026-07-05T09:54:47.982445+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.16719","citing_title":"SAM 3: Segment Anything with Concepts","ref_index":143,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SLQNQOQ4QNWP5CM2C54HPOAL5D","json":"https://pith.science/pith/SLQNQOQ4QNWP5CM2C54HPOAL5D.json","graph_json":"https://pith.science/api/pith-number/SLQNQOQ4QNWP5CM2C54HPOAL5D/graph.json","events_json":"https://pith.science/api/pith-number/SLQNQOQ4QNWP5CM2C54HPOAL5D/events.json","paper":"https://pith.science/paper/SLQNQOQ4"},"agent_actions":{"view_html":"https://pith.science/pith/SLQNQOQ4QNWP5CM2C54HPOAL5D","download_json":"https://pith.science/pith/SLQNQOQ4QNWP5CM2C54HPOAL5D.json","view_paper":"https://pith.science/paper/SLQNQOQ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.17251&json=true","fetch_graph":"https://pith.science/api/pith-number/SLQNQOQ4QNWP5CM2C54HPOAL5D/graph.json","fetch_events":"https://pith.science/api/pith-number/SLQNQOQ4QNWP5CM2C54HPOAL5D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SLQNQOQ4QNWP5CM2C54HPOAL5D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SLQNQOQ4QNWP5CM2C54HPOAL5D/action/storage_attestation","attest_author":"https://pith.science/pith/SLQNQOQ4QNWP5CM2C54HPOAL5D/action/author_attestation","sign_citation":"https://pith.science/pith/SLQNQOQ4QNWP5CM2C54HPOAL5D/action/citation_signature","submit_replication":"https://pith.science/pith/SLQNQOQ4QNWP5CM2C54HPOAL5D/action/replication_record"}},"created_at":"2026-07-05T09:54:47.982445+00:00","updated_at":"2026-07-05T09:54:47.982445+00:00"}