{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ETO5LWJNGEOJYL3SZLOPTHD5K4","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":"f1fc337dd81ded43f701179aaa4dba46427c76ae89b30fec150c8876f098e443","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-17T19:15:53Z","title_canon_sha256":"91798e3cd5d94a014e396acf2a3a1ccd202ed66ba6c8e4d86677b955cee9c34d"},"schema_version":"1.0","source":{"id":"2102.08981","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.08981","created_at":"2026-07-05T02:27:42Z"},{"alias_kind":"arxiv_version","alias_value":"2102.08981v2","created_at":"2026-07-05T02:27:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.08981","created_at":"2026-07-05T02:27:42Z"},{"alias_kind":"pith_short_12","alias_value":"ETO5LWJNGEOJ","created_at":"2026-07-05T02:27:42Z"},{"alias_kind":"pith_short_16","alias_value":"ETO5LWJNGEOJYL3S","created_at":"2026-07-05T02:27:42Z"},{"alias_kind":"pith_short_8","alias_value":"ETO5LWJN","created_at":"2026-07-05T02:27:42Z"}],"graph_snapshots":[{"event_id":"sha256:75209ecce4557a18fed1ace6e2ce823db9ef043c8276ec8772bd599daa049407","target":"graph","created_at":"2026-07-05T02:27:42Z","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/2102.08981/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Nan Ding, Piyush Sharma, Radu Soricut, Soravit Changpinyo","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-17T19:15:53Z","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.08981","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:da650a8db6615538356c375d3f3c6726cab447dc0203031f9d26c0a7ab829b16","target":"record","created_at":"2026-07-05T02:27:42Z","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":"f1fc337dd81ded43f701179aaa4dba46427c76ae89b30fec150c8876f098e443","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-02-17T19:15:53Z","title_canon_sha256":"91798e3cd5d94a014e396acf2a3a1ccd202ed66ba6c8e4d86677b955cee9c34d"},"schema_version":"1.0","source":{"id":"2102.08981","kind":"arxiv","version":2}},"canonical_sha256":"24ddd5d92d311c9c2f72cadcf99c7d5705606b1cbc8a1c3d2132acf2777df88d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24ddd5d92d311c9c2f72cadcf99c7d5705606b1cbc8a1c3d2132acf2777df88d","first_computed_at":"2026-07-05T02:27:42.019524Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:27:42.019524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PMzuklBe6kyX1CQKfS0Kwu6lb4cPUt2flHuvVkHLRgjA4jlKRjamGtFwbFinEDiSP2K/AldzAF168ftRaY+/Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:27:42.020027Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.08981","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da650a8db6615538356c375d3f3c6726cab447dc0203031f9d26c0a7ab829b16","sha256:75209ecce4557a18fed1ace6e2ce823db9ef043c8276ec8772bd599daa049407"],"state_sha256":"168c7a9abda5e280cd88055b3311f2bfe7943f055c6f456270779072d2be3c8f"}