{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:JBRCEG2BV4T27CK2ESUCP5BB4X","short_pith_number":"pith:JBRCEG2B","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"},"canonical_sha256":"4862221b41af27af895a24a827f421e5e4734ba2d62455e9e312ba4ed183e149","source":{"kind":"arxiv","id":"2007.02375","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.02375","created_at":"2026-07-05T01:16:21Z"},{"alias_kind":"arxiv_version","alias_value":"2007.02375v1","created_at":"2026-07-05T01:16:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.02375","created_at":"2026-07-05T01:16:21Z"},{"alias_kind":"pith_short_12","alias_value":"JBRCEG2BV4T2","created_at":"2026-07-05T01:16:21Z"},{"alias_kind":"pith_short_16","alias_value":"JBRCEG2BV4T27CK2","created_at":"2026-07-05T01:16:21Z"},{"alias_kind":"pith_short_8","alias_value":"JBRCEG2B","created_at":"2026-07-05T01:16:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:JBRCEG2BV4T27CK2ESUCP5BB4X","target":"record","payload":{"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"},"canonical_sha256":"4862221b41af27af895a24a827f421e5e4734ba2d62455e9e312ba4ed183e149","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"},"source_kind":"arxiv","source_id":"2007.02375","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:16:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9WuBYEHlHn57pHrOaGo5z5QajijQ2H6YCyT6shoq56AJqeUwLi90hxnnKo6jMfYB4nKniDpgKyj7RWwB3Ck5BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:46:00.189317Z"},"content_sha256":"1f287208f4c520c0549e29167df955bfbdf9d40ed7701b07c2a90c2ea7425057","schema_version":"1.0","event_id":"sha256:1f287208f4c520c0549e29167df955bfbdf9d40ed7701b07c2a90c2ea7425057"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:JBRCEG2BV4T27CK2ESUCP5BB4X","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:16:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sSatwJxDd6VFlW9TUwRuZkNN73HAA7ePGqyPgTPeU7pdvHUn6jR7WoBCoFD5hrTEG8CprJ/EErVh4vUkuh8bBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:46:00.189832Z"},"content_sha256":"9bbfe5db1cd171b4b90f7663189d444dd23b34c928eb0c1d5a483db808c358c3","schema_version":"1.0","event_id":"sha256:9bbfe5db1cd171b4b90f7663189d444dd23b34c928eb0c1d5a483db808c358c3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JBRCEG2BV4T27CK2ESUCP5BB4X/bundle.json","state_url":"https://pith.science/pith/JBRCEG2BV4T27CK2ESUCP5BB4X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JBRCEG2BV4T27CK2ESUCP5BB4X/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T01:46:00Z","links":{"resolver":"https://pith.science/pith/JBRCEG2BV4T27CK2ESUCP5BB4X","bundle":"https://pith.science/pith/JBRCEG2BV4T27CK2ESUCP5BB4X/bundle.json","state":"https://pith.science/pith/JBRCEG2BV4T27CK2ESUCP5BB4X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JBRCEG2BV4T27CK2ESUCP5BB4X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:JBRCEG2BV4T27CK2ESUCP5BB4X","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":"0d2d715e04fc03f728497cd2403aad212a0c657c5c9d5973ef23c327344ef8c4","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-05T16:11:57Z","title_canon_sha256":"29e629b984427b535d0c4e852d30e7c8ddadcc02f0ec2a834fbded728358bdb0"},"schema_version":"1.0","source":{"id":"2007.02375","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.02375","created_at":"2026-07-05T01:16:21Z"},{"alias_kind":"arxiv_version","alias_value":"2007.02375v1","created_at":"2026-07-05T01:16:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.02375","created_at":"2026-07-05T01:16:21Z"},{"alias_kind":"pith_short_12","alias_value":"JBRCEG2BV4T2","created_at":"2026-07-05T01:16:21Z"},{"alias_kind":"pith_short_16","alias_value":"JBRCEG2BV4T27CK2","created_at":"2026-07-05T01:16:21Z"},{"alias_kind":"pith_short_8","alias_value":"JBRCEG2B","created_at":"2026-07-05T01:16:21Z"}],"graph_snapshots":[{"event_id":"sha256:9bbfe5db1cd171b4b90f7663189d444dd23b34c928eb0c1d5a483db808c358c3","target":"graph","created_at":"2026-07-05T01:16:21Z","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/2007.02375/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jianjie Luo, Jun Xu, Tao Mei, Ting Yao, Yehao Li, Yingwei Pan","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-05T16:11:57Z","title":"Auto-captions on GIF: A Large-scale Video-sentence Dataset for Vision-language Pre-training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.02375","kind":"arxiv","version":1},"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":"sha256:1f287208f4c520c0549e29167df955bfbdf9d40ed7701b07c2a90c2ea7425057","target":"record","created_at":"2026-07-05T01:16:21Z","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":"0d2d715e04fc03f728497cd2403aad212a0c657c5c9d5973ef23c327344ef8c4","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-07-05T16:11:57Z","title_canon_sha256":"29e629b984427b535d0c4e852d30e7c8ddadcc02f0ec2a834fbded728358bdb0"},"schema_version":"1.0","source":{"id":"2007.02375","kind":"arxiv","version":1}},"canonical_sha256":"4862221b41af27af895a24a827f421e5e4734ba2d62455e9e312ba4ed183e149","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4862221b41af27af895a24a827f421e5e4734ba2d62455e9e312ba4ed183e149","first_computed_at":"2026-07-05T01:16:21.705191Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:16:21.705191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OBndGwflCnW5r0cgX7TXgmemdEC1wk20xPbzjh+keTkLbTsT7c5/2bvsQjd9nLHuqAUleyga9JwJobgFSQQFBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:16:21.705704Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.02375","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f287208f4c520c0549e29167df955bfbdf9d40ed7701b07c2a90c2ea7425057","sha256:9bbfe5db1cd171b4b90f7663189d444dd23b34c928eb0c1d5a483db808c358c3"],"state_sha256":"a7a7fc784827a4f95aa2e2bf7e2e9f6dbae3969018259401981f230128679d21"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JhEcHgStUKhN2DRmx8dHa6qrAVsZAD0jr7cEKSUfVTmAHuubxg43zve8V/4AKzJocaDuY9B3aRuO2B/W+G73DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T01:46:00.193438Z","bundle_sha256":"a7029d1e5b327c027d8c2d3401df9fa3f059d083db885db6bfb8f76b1ddd4b59"}}