{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:2HNO52MGEX2WAAHDEENUTYUTUS","short_pith_number":"pith:2HNO52MG","canonical_record":{"source":{"id":"2106.11097","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-21T13:30:33Z","cross_cats_sorted":[],"title_canon_sha256":"e693e5322b8125619e4b02d87a64a347b300dccc01fe471d84eed7086556a05c","abstract_canon_sha256":"20b8cd2b30f2cd4c88aca1884c384f720d7e808ac6c746acca023881a4db6a15"},"schema_version":"1.0"},"canonical_sha256":"d1daeee98625f56000e3211b49e293a4b2cd443d862206c1849e115120bef603","source":{"kind":"arxiv","id":"2106.11097","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.11097","created_at":"2026-07-05T02:50:56Z"},{"alias_kind":"arxiv_version","alias_value":"2106.11097v1","created_at":"2026-07-05T02:50:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.11097","created_at":"2026-07-05T02:50:56Z"},{"alias_kind":"pith_short_12","alias_value":"2HNO52MGEX2W","created_at":"2026-07-05T02:50:56Z"},{"alias_kind":"pith_short_16","alias_value":"2HNO52MGEX2WAAHD","created_at":"2026-07-05T02:50:56Z"},{"alias_kind":"pith_short_8","alias_value":"2HNO52MG","created_at":"2026-07-05T02:50:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:2HNO52MGEX2WAAHDEENUTYUTUS","target":"record","payload":{"canonical_record":{"source":{"id":"2106.11097","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-21T13:30:33Z","cross_cats_sorted":[],"title_canon_sha256":"e693e5322b8125619e4b02d87a64a347b300dccc01fe471d84eed7086556a05c","abstract_canon_sha256":"20b8cd2b30f2cd4c88aca1884c384f720d7e808ac6c746acca023881a4db6a15"},"schema_version":"1.0"},"canonical_sha256":"d1daeee98625f56000e3211b49e293a4b2cd443d862206c1849e115120bef603","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:56.742412Z","signature_b64":"ryDWioKrxhBhi5NR/zbQkqQe9lSo0R5Sz/fr+CDJvj2Ej8pzCAJLid5aeskZFtT9Y8/oH83yTzDEPPsccKLXBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1daeee98625f56000e3211b49e293a4b2cd443d862206c1849e115120bef603","last_reissued_at":"2026-07-05T02:50:56.741982Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:56.741982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.11097","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":"2026-07-05T02:50:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"00HkLvrJ3h93eCAV9Vq3uEOKONtQNzUHV3057qg7nCPeVy5XLrMTU7o3YJeh6qgIQPMujVEM/xj1+xEyMDntDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:12:29.586943Z"},"content_sha256":"2dc66fbb4be9fadd5b37c3a0b31ab896b28a214d34beedfe35b9aabe7054da1e","schema_version":"1.0","event_id":"sha256:2dc66fbb4be9fadd5b37c3a0b31ab896b28a214d34beedfe35b9aabe7054da1e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:2HNO52MGEX2WAAHDEENUTYUTUS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Fang, Luhui Xu, Pengfei Xiong, Yu Chen","submitted_at":"2021-06-21T13:30:33Z","abstract_excerpt":"We present CLIP2Video network to transfer the image-language pre-training model to video-text retrieval in an end-to-end manner. Leading approaches in the domain of video-and-language learning try to distill the spatio-temporal video features and multi-modal interaction between videos and languages from a large-scale video-text dataset. Different from them, we leverage pretrained image-language model, simplify it as a two-stage framework with co-learning of image-text and enhancing temporal relations between video frames and video-text respectively, make it able to train on comparatively small"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.11097","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/2106.11097/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":"2026-07-05T02:50:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sK5x7EkrkvRzKbBkX//14ukd2wCbFYOaRprSgxsLKiRMb3U+LqHvI3YCFq/wA7KfiVuQ6VTGIvNQAR+lzJ18Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:12:29.587442Z"},"content_sha256":"28cdd5f9293d83236a06ca48dcaf5c0d43c9151eb6666ab2d4b3eb9ac6686b15","schema_version":"1.0","event_id":"sha256:28cdd5f9293d83236a06ca48dcaf5c0d43c9151eb6666ab2d4b3eb9ac6686b15"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2HNO52MGEX2WAAHDEENUTYUTUS/bundle.json","state_url":"https://pith.science/pith/2HNO52MGEX2WAAHDEENUTYUTUS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2HNO52MGEX2WAAHDEENUTYUTUS/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":"2026-08-09T14:12:29Z","links":{"resolver":"https://pith.science/pith/2HNO52MGEX2WAAHDEENUTYUTUS","bundle":"https://pith.science/pith/2HNO52MGEX2WAAHDEENUTYUTUS/bundle.json","state":"https://pith.science/pith/2HNO52MGEX2WAAHDEENUTYUTUS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2HNO52MGEX2WAAHDEENUTYUTUS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:2HNO52MGEX2WAAHDEENUTYUTUS","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":"20b8cd2b30f2cd4c88aca1884c384f720d7e808ac6c746acca023881a4db6a15","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-21T13:30:33Z","title_canon_sha256":"e693e5322b8125619e4b02d87a64a347b300dccc01fe471d84eed7086556a05c"},"schema_version":"1.0","source":{"id":"2106.11097","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.11097","created_at":"2026-07-05T02:50:56Z"},{"alias_kind":"arxiv_version","alias_value":"2106.11097v1","created_at":"2026-07-05T02:50:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.11097","created_at":"2026-07-05T02:50:56Z"},{"alias_kind":"pith_short_12","alias_value":"2HNO52MGEX2W","created_at":"2026-07-05T02:50:56Z"},{"alias_kind":"pith_short_16","alias_value":"2HNO52MGEX2WAAHD","created_at":"2026-07-05T02:50:56Z"},{"alias_kind":"pith_short_8","alias_value":"2HNO52MG","created_at":"2026-07-05T02:50:56Z"}],"graph_snapshots":[{"event_id":"sha256:28cdd5f9293d83236a06ca48dcaf5c0d43c9151eb6666ab2d4b3eb9ac6686b15","target":"graph","created_at":"2026-07-05T02:50:56Z","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/2106.11097/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present CLIP2Video network to transfer the image-language pre-training model to video-text retrieval in an end-to-end manner. Leading approaches in the domain of video-and-language learning try to distill the spatio-temporal video features and multi-modal interaction between videos and languages from a large-scale video-text dataset. Different from them, we leverage pretrained image-language model, simplify it as a two-stage framework with co-learning of image-text and enhancing temporal relations between video frames and video-text respectively, make it able to train on comparatively small","authors_text":"Han Fang, Luhui Xu, Pengfei Xiong, Yu Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-21T13:30:33Z","title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.11097","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":"sha256:2dc66fbb4be9fadd5b37c3a0b31ab896b28a214d34beedfe35b9aabe7054da1e","target":"record","created_at":"2026-07-05T02:50:56Z","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":"20b8cd2b30f2cd4c88aca1884c384f720d7e808ac6c746acca023881a4db6a15","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-21T13:30:33Z","title_canon_sha256":"e693e5322b8125619e4b02d87a64a347b300dccc01fe471d84eed7086556a05c"},"schema_version":"1.0","source":{"id":"2106.11097","kind":"arxiv","version":1}},"canonical_sha256":"d1daeee98625f56000e3211b49e293a4b2cd443d862206c1849e115120bef603","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1daeee98625f56000e3211b49e293a4b2cd443d862206c1849e115120bef603","first_computed_at":"2026-07-05T02:50:56.741982Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:50:56.741982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ryDWioKrxhBhi5NR/zbQkqQe9lSo0R5Sz/fr+CDJvj2Ej8pzCAJLid5aeskZFtT9Y8/oH83yTzDEPPsccKLXBw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:50:56.742412Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.11097","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2dc66fbb4be9fadd5b37c3a0b31ab896b28a214d34beedfe35b9aabe7054da1e","sha256:28cdd5f9293d83236a06ca48dcaf5c0d43c9151eb6666ab2d4b3eb9ac6686b15"],"state_sha256":"670fbb156044cfbdeee15d7151a19baf2a549eefbda15ee564f4a65d0d5a674a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+OSdEkLFO+ic4ynWxUgUtMRq+TDiwcofpPZ+DYsCc2bO0GVh87PadQPxzHuLGgu+TzolRA74FRH/0nh8+yjPCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T14:12:29.591816Z","bundle_sha256":"5a0c3ea1b2f985a1aa2ed0a98264b7b2432f3991ecc9cc3dcae52bfd52dc53dd"}}