{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:FS4ZJK7B3CED7UHT4VRIEYJA2T","short_pith_number":"pith:FS4ZJK7B","canonical_record":{"source":{"id":"2109.14084","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-28T23:01:51Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"889299d8d78f474ee79c7e8991a1cafe322088745f26ec2670546023743ef379","abstract_canon_sha256":"fa32e0230e9d947bc9c0135fa9ce66b64e32ace2520ece4050a96259a0358c0e"},"schema_version":"1.0"},"canonical_sha256":"2cb994abe1d8883fd0f3e562826120d4f92e4a6d6cd1b471a6fd107cce897c17","source":{"kind":"arxiv","id":"2109.14084","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.14084","created_at":"2026-07-05T03:19:24Z"},{"alias_kind":"arxiv_version","alias_value":"2109.14084v2","created_at":"2026-07-05T03:19:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.14084","created_at":"2026-07-05T03:19:24Z"},{"alias_kind":"pith_short_12","alias_value":"FS4ZJK7B3CED","created_at":"2026-07-05T03:19:24Z"},{"alias_kind":"pith_short_16","alias_value":"FS4ZJK7B3CED7UHT","created_at":"2026-07-05T03:19:24Z"},{"alias_kind":"pith_short_8","alias_value":"FS4ZJK7B","created_at":"2026-07-05T03:19:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:FS4ZJK7B3CED7UHT4VRIEYJA2T","target":"record","payload":{"canonical_record":{"source":{"id":"2109.14084","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-28T23:01:51Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"889299d8d78f474ee79c7e8991a1cafe322088745f26ec2670546023743ef379","abstract_canon_sha256":"fa32e0230e9d947bc9c0135fa9ce66b64e32ace2520ece4050a96259a0358c0e"},"schema_version":"1.0"},"canonical_sha256":"2cb994abe1d8883fd0f3e562826120d4f92e4a6d6cd1b471a6fd107cce897c17","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:19:24.724696Z","signature_b64":"7cB73GZTJwytvr7aVvENMz1aR8Dy/IOqcEHEl8+LUrqH3VxhgngzHSPgF62IWP/UeaLO+Ij7hHQzTfiHdglkAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cb994abe1d8883fd0f3e562826120d4f92e4a6d6cd1b471a6fd107cce897c17","last_reissued_at":"2026-07-05T03:19:24.724215Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:19:24.724215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.14084","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:19:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EjkD5gMFnoLWgP8rrOIMz4GGaWb461XkcaGhUDniI9QFCquY+FtxSUHr7NZQyBb9DnSrRpp7ENCEAGw5MWgDDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T23:41:35.441304Z"},"content_sha256":"115ca2599891c314f00fe537d34a00a1be85facc196d9efc1dbb6b6243ae629c","schema_version":"1.0","event_id":"sha256:115ca2599891c314f00fe537d34a00a1be85facc196d9efc1dbb6b6243ae629c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:FS4ZJK7B3CED7UHT4VRIEYJA2T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Armen Aghajanyan, Christoph Feichtenhofer, Dmytro Okhonko, Florian Metze, Gargi Ghosh, Hu Xu, Luke Zettlemoyer, Po-Yao Huang","submitted_at":"2021-09-28T23:01:51Z","abstract_excerpt":"We present VideoCLIP, a contrastive approach to pre-train a unified model for zero-shot video and text understanding, without using any labels on downstream tasks. VideoCLIP trains a transformer for video and text by contrasting temporally overlapping positive video-text pairs with hard negatives from nearest neighbor retrieval. Our experiments on a diverse series of downstream tasks, including sequence-level text-video retrieval, VideoQA, token-level action localization, and action segmentation reveal state-of-the-art performance, surpassing prior work, and in some cases even outperforming su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.14084","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/2109.14084/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":"2026-07-05T03:19:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FmXhsu7yxbOl3ovVJe1HnMmykCQHn01IA0CDbfpUU2Vi+8psBa35/FlIGcHxoUMtABmtqWxawwkp9oHAJLrLCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T23:41:35.441718Z"},"content_sha256":"1ab1f4ec5f08305ffa91ea0401ab32752d8737148d870c5bef5e4a04770cd75a","schema_version":"1.0","event_id":"sha256:1ab1f4ec5f08305ffa91ea0401ab32752d8737148d870c5bef5e4a04770cd75a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FS4ZJK7B3CED7UHT4VRIEYJA2T/bundle.json","state_url":"https://pith.science/pith/FS4ZJK7B3CED7UHT4VRIEYJA2T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FS4ZJK7B3CED7UHT4VRIEYJA2T/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":"2026-07-12T23:41:35Z","links":{"resolver":"https://pith.science/pith/FS4ZJK7B3CED7UHT4VRIEYJA2T","bundle":"https://pith.science/pith/FS4ZJK7B3CED7UHT4VRIEYJA2T/bundle.json","state":"https://pith.science/pith/FS4ZJK7B3CED7UHT4VRIEYJA2T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FS4ZJK7B3CED7UHT4VRIEYJA2T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FS4ZJK7B3CED7UHT4VRIEYJA2T","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":"fa32e0230e9d947bc9c0135fa9ce66b64e32ace2520ece4050a96259a0358c0e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-28T23:01:51Z","title_canon_sha256":"889299d8d78f474ee79c7e8991a1cafe322088745f26ec2670546023743ef379"},"schema_version":"1.0","source":{"id":"2109.14084","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.14084","created_at":"2026-07-05T03:19:24Z"},{"alias_kind":"arxiv_version","alias_value":"2109.14084v2","created_at":"2026-07-05T03:19:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.14084","created_at":"2026-07-05T03:19:24Z"},{"alias_kind":"pith_short_12","alias_value":"FS4ZJK7B3CED","created_at":"2026-07-05T03:19:24Z"},{"alias_kind":"pith_short_16","alias_value":"FS4ZJK7B3CED7UHT","created_at":"2026-07-05T03:19:24Z"},{"alias_kind":"pith_short_8","alias_value":"FS4ZJK7B","created_at":"2026-07-05T03:19:24Z"}],"graph_snapshots":[{"event_id":"sha256:1ab1f4ec5f08305ffa91ea0401ab32752d8737148d870c5bef5e4a04770cd75a","target":"graph","created_at":"2026-07-05T03:19:24Z","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/2109.14084/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present VideoCLIP, a contrastive approach to pre-train a unified model for zero-shot video and text understanding, without using any labels on downstream tasks. VideoCLIP trains a transformer for video and text by contrasting temporally overlapping positive video-text pairs with hard negatives from nearest neighbor retrieval. Our experiments on a diverse series of downstream tasks, including sequence-level text-video retrieval, VideoQA, token-level action localization, and action segmentation reveal state-of-the-art performance, surpassing prior work, and in some cases even outperforming su","authors_text":"Armen Aghajanyan, Christoph Feichtenhofer, Dmytro Okhonko, Florian Metze, Gargi Ghosh, Hu Xu, Luke Zettlemoyer, Po-Yao Huang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-28T23:01:51Z","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.14084","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":"sha256:115ca2599891c314f00fe537d34a00a1be85facc196d9efc1dbb6b6243ae629c","target":"record","created_at":"2026-07-05T03:19:24Z","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":"fa32e0230e9d947bc9c0135fa9ce66b64e32ace2520ece4050a96259a0358c0e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-28T23:01:51Z","title_canon_sha256":"889299d8d78f474ee79c7e8991a1cafe322088745f26ec2670546023743ef379"},"schema_version":"1.0","source":{"id":"2109.14084","kind":"arxiv","version":2}},"canonical_sha256":"2cb994abe1d8883fd0f3e562826120d4f92e4a6d6cd1b471a6fd107cce897c17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2cb994abe1d8883fd0f3e562826120d4f92e4a6d6cd1b471a6fd107cce897c17","first_computed_at":"2026-07-05T03:19:24.724215Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:19:24.724215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7cB73GZTJwytvr7aVvENMz1aR8Dy/IOqcEHEl8+LUrqH3VxhgngzHSPgF62IWP/UeaLO+Ij7hHQzTfiHdglkAw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:19:24.724696Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.14084","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:115ca2599891c314f00fe537d34a00a1be85facc196d9efc1dbb6b6243ae629c","sha256:1ab1f4ec5f08305ffa91ea0401ab32752d8737148d870c5bef5e4a04770cd75a"],"state_sha256":"ba486eb0ce846c9a1235ff5d7be810c4e0f15de4f789041b75a8f686db2ebf43"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XHLz9RBgOC4quC3A1lLD6uPo2tuh8QP7YsgOrZEWylsIUWN1kD1bXNNog8GyIxktOYQA1er+Uuc7G5d0UCueDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T23:41:35.443993Z","bundle_sha256":"4ba6db22b252f8fc9b0b1a311ca4ff5024869bd1eb0b01e37b4224eef336bb30"}}