{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:JBRCEG2BV4T27CK2ESUCP5BB4X","short_pith_number":"pith:JBRCEG2B","schema_version":"1.0","canonical_sha256":"4862221b41af27af895a24a827f421e5e4734ba2d62455e9e312ba4ed183e149","source":{"kind":"arxiv","id":"2007.02375","version":1},"attestation_state":"computed","paper":{"title":"Auto-captions on GIF: A Large-scale Video-sentence Dataset for Vision-language Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Jianjie Luo, Jun Xu, Tao Mei, Ting Yao, Yehao Li, Yingwei Pan","submitted_at":"2020-07-05T16:11:57Z","abstract_excerpt":"In this work, we present Auto-captions on GIF, which is a new large-scale pre-training dataset for generic video understanding. All video-sentence pairs are created by automatically extracting and filtering video caption annotations from billions of web pages. Auto-captions on GIF dataset can be utilized to pre-train the generic feature representation or encoder-decoder structure for video captioning, and other downstream tasks (e.g., sentence localization in videos, video question answering, etc.) as well. We present a detailed analysis of Auto-captions on GIF dataset in comparison to existin"},"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":"2007.02375","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-05T16:11:57Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"29e629b984427b535d0c4e852d30e7c8ddadcc02f0ec2a834fbded728358bdb0","abstract_canon_sha256":"0d2d715e04fc03f728497cd2403aad212a0c657c5c9d5973ef23c327344ef8c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:16:21.705704Z","signature_b64":"OBndGwflCnW5r0cgX7TXgmemdEC1wk20xPbzjh+keTkLbTsT7c5/2bvsQjd9nLHuqAUleyga9JwJobgFSQQFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4862221b41af27af895a24a827f421e5e4734ba2d62455e9e312ba4ed183e149","last_reissued_at":"2026-07-05T01:16:21.705191Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:16:21.705191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Auto-captions on GIF: A Large-scale Video-sentence Dataset for Vision-language Pre-training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Jianjie Luo, Jun Xu, Tao Mei, Ting Yao, Yehao Li, Yingwei Pan","submitted_at":"2020-07-05T16:11:57Z","abstract_excerpt":"In this work, we present Auto-captions on GIF, which is a new large-scale pre-training dataset for generic video understanding. All video-sentence pairs are created by automatically extracting and filtering video caption annotations from billions of web pages. Auto-captions on GIF dataset can be utilized to pre-train the generic feature representation or encoder-decoder structure for video captioning, and other downstream tasks (e.g., sentence localization in videos, video question answering, etc.) as well. We present a detailed analysis of Auto-captions on GIF dataset in comparison to existin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.02375","kind":"arxiv","version":1},"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/2007.02375/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":"2007.02375","created_at":"2026-07-05T01:16:21.705266+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.02375v1","created_at":"2026-07-05T01:16:21.705266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.02375","created_at":"2026-07-05T01:16:21.705266+00:00"},{"alias_kind":"pith_short_12","alias_value":"JBRCEG2BV4T2","created_at":"2026-07-05T01:16:21.705266+00:00"},{"alias_kind":"pith_short_16","alias_value":"JBRCEG2BV4T27CK2","created_at":"2026-07-05T01:16:21.705266+00:00"},{"alias_kind":"pith_short_8","alias_value":"JBRCEG2B","created_at":"2026-07-05T01:16:21.705266+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JBRCEG2BV4T27CK2ESUCP5BB4X","json":"https://pith.science/pith/JBRCEG2BV4T27CK2ESUCP5BB4X.json","graph_json":"https://pith.science/api/pith-number/JBRCEG2BV4T27CK2ESUCP5BB4X/graph.json","events_json":"https://pith.science/api/pith-number/JBRCEG2BV4T27CK2ESUCP5BB4X/events.json","paper":"https://pith.science/paper/JBRCEG2B"},"agent_actions":{"view_html":"https://pith.science/pith/JBRCEG2BV4T27CK2ESUCP5BB4X","download_json":"https://pith.science/pith/JBRCEG2BV4T27CK2ESUCP5BB4X.json","view_paper":"https://pith.science/paper/JBRCEG2B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.02375&json=true","fetch_graph":"https://pith.science/api/pith-number/JBRCEG2BV4T27CK2ESUCP5BB4X/graph.json","fetch_events":"https://pith.science/api/pith-number/JBRCEG2BV4T27CK2ESUCP5BB4X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JBRCEG2BV4T27CK2ESUCP5BB4X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JBRCEG2BV4T27CK2ESUCP5BB4X/action/storage_attestation","attest_author":"https://pith.science/pith/JBRCEG2BV4T27CK2ESUCP5BB4X/action/author_attestation","sign_citation":"https://pith.science/pith/JBRCEG2BV4T27CK2ESUCP5BB4X/action/citation_signature","submit_replication":"https://pith.science/pith/JBRCEG2BV4T27CK2ESUCP5BB4X/action/replication_record"}},"created_at":"2026-07-05T01:16:21.705266+00:00","updated_at":"2026-07-05T01:16:21.705266+00:00"}