{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ETO5LWJNGEOJYL3SZLOPTHD5K4","short_pith_number":"pith:ETO5LWJN","schema_version":"1.0","canonical_sha256":"24ddd5d92d311c9c2f72cadcf99c7d5705606b1cbc8a1c3d2132acf2777df88d","source":{"kind":"arxiv","id":"2102.08981","version":2},"attestation_state":"computed","paper":{"title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Nan Ding, Piyush Sharma, Radu Soricut, Soravit Changpinyo","submitted_at":"2021-02-17T19:15:53Z","abstract_excerpt":"The availability of large-scale image captioning and visual question answering datasets has contributed significantly to recent successes in vision-and-language pre-training. However, these datasets are often collected with overrestrictive requirements inherited from their original target tasks (e.g., image caption generation), which limit the resulting dataset scale and diversity. We take a step further in pushing the limits of vision-and-language pre-training data by relaxing the data collection pipeline used in Conceptual Captions 3M (CC3M) [Sharma et al. 2018] and introduce the Conceptual "},"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":"2102.08981","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-17T19:15:53Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"91798e3cd5d94a014e396acf2a3a1ccd202ed66ba6c8e4d86677b955cee9c34d","abstract_canon_sha256":"f1fc337dd81ded43f701179aaa4dba46427c76ae89b30fec150c8876f098e443"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:27:42.020027Z","signature_b64":"PMzuklBe6kyX1CQKfS0Kwu6lb4cPUt2flHuvVkHLRgjA4jlKRjamGtFwbFinEDiSP2K/AldzAF168ftRaY+/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24ddd5d92d311c9c2f72cadcf99c7d5705606b1cbc8a1c3d2132acf2777df88d","last_reissued_at":"2026-07-05T02:27:42.019524Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:27:42.019524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Nan Ding, Piyush Sharma, Radu Soricut, Soravit Changpinyo","submitted_at":"2021-02-17T19:15:53Z","abstract_excerpt":"The availability of large-scale image captioning and visual question answering datasets has contributed significantly to recent successes in vision-and-language pre-training. However, these datasets are often collected with overrestrictive requirements inherited from their original target tasks (e.g., image caption generation), which limit the resulting dataset scale and diversity. We take a step further in pushing the limits of vision-and-language pre-training data by relaxing the data collection pipeline used in Conceptual Captions 3M (CC3M) [Sharma et al. 2018] and introduce the Conceptual "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.08981","kind":"arxiv","version":2},"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/2102.08981/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":"2102.08981","created_at":"2026-07-05T02:27:42.019575+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.08981v2","created_at":"2026-07-05T02:27:42.019575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.08981","created_at":"2026-07-05T02:27:42.019575+00:00"},{"alias_kind":"pith_short_12","alias_value":"ETO5LWJNGEOJ","created_at":"2026-07-05T02:27:42.019575+00:00"},{"alias_kind":"pith_short_16","alias_value":"ETO5LWJNGEOJYL3S","created_at":"2026-07-05T02:27:42.019575+00:00"},{"alias_kind":"pith_short_8","alias_value":"ETO5LWJN","created_at":"2026-07-05T02:27:42.019575+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.04996","citing_title":"Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2408.11039","citing_title":"Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ETO5LWJNGEOJYL3SZLOPTHD5K4","json":"https://pith.science/pith/ETO5LWJNGEOJYL3SZLOPTHD5K4.json","graph_json":"https://pith.science/api/pith-number/ETO5LWJNGEOJYL3SZLOPTHD5K4/graph.json","events_json":"https://pith.science/api/pith-number/ETO5LWJNGEOJYL3SZLOPTHD5K4/events.json","paper":"https://pith.science/paper/ETO5LWJN"},"agent_actions":{"view_html":"https://pith.science/pith/ETO5LWJNGEOJYL3SZLOPTHD5K4","download_json":"https://pith.science/pith/ETO5LWJNGEOJYL3SZLOPTHD5K4.json","view_paper":"https://pith.science/paper/ETO5LWJN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.08981&json=true","fetch_graph":"https://pith.science/api/pith-number/ETO5LWJNGEOJYL3SZLOPTHD5K4/graph.json","fetch_events":"https://pith.science/api/pith-number/ETO5LWJNGEOJYL3SZLOPTHD5K4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ETO5LWJNGEOJYL3SZLOPTHD5K4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ETO5LWJNGEOJYL3SZLOPTHD5K4/action/storage_attestation","attest_author":"https://pith.science/pith/ETO5LWJNGEOJYL3SZLOPTHD5K4/action/author_attestation","sign_citation":"https://pith.science/pith/ETO5LWJNGEOJYL3SZLOPTHD5K4/action/citation_signature","submit_replication":"https://pith.science/pith/ETO5LWJNGEOJYL3SZLOPTHD5K4/action/replication_record"}},"created_at":"2026-07-05T02:27:42.019575+00:00","updated_at":"2026-07-05T02:27:42.019575+00:00"}