{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VKHTD5ZCXWPY2JU22O4ZVCL7TL","short_pith_number":"pith:VKHTD5ZC","schema_version":"1.0","canonical_sha256":"aa8f31f722bd9f8d269ad3b99a897f9af3e05cbd0c5e8ffc263ef770688c07ef","source":{"kind":"arxiv","id":"2212.13738","version":2},"attestation_state":"computed","paper":{"title":"TempCLR: Temporal Alignment Representation with Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Guangxing Han, Jiawei Ma, Long Chen, Shih-Fu Chang, Shiyuan Huang, Xudong Lin, Yuncong Yang","submitted_at":"2022-12-28T08:10:31Z","abstract_excerpt":"Video representation learning has been successful in video-text pre-training for zero-shot transfer, where each sentence is trained to be close to the paired video clips in a common feature space. For long videos, given a paragraph of description where the sentences describe different segments of the video, by matching all sentence-clip pairs, the paragraph and the full video are aligned implicitly. However, such unit-level comparison may ignore global temporal context, which inevitably limits the generalization ability. In this paper, we propose a contrastive learning framework TempCLR to com"},"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":"2212.13738","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-28T08:10:31Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"278fc833fbaab1fbe8ba49f5bae58f3773f715c8313450ea09789ac48c395522","abstract_canon_sha256":"a912302c61be6746177f45805e5db65f407d05cd08cb7f1b8632b8651803c0f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:56:15.438210Z","signature_b64":"WbzfpIQhmJI5PrderSYskDGdLzDO5oZy93rPkqov8Px3usr6snFYqoDJQu5cpyhCuQ5awjSwyxlFR/v63DznDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa8f31f722bd9f8d269ad3b99a897f9af3e05cbd0c5e8ffc263ef770688c07ef","last_reissued_at":"2026-07-05T05:56:15.437711Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:56:15.437711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TempCLR: Temporal Alignment Representation with Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Guangxing Han, Jiawei Ma, Long Chen, Shih-Fu Chang, Shiyuan Huang, Xudong Lin, Yuncong Yang","submitted_at":"2022-12-28T08:10:31Z","abstract_excerpt":"Video representation learning has been successful in video-text pre-training for zero-shot transfer, where each sentence is trained to be close to the paired video clips in a common feature space. For long videos, given a paragraph of description where the sentences describe different segments of the video, by matching all sentence-clip pairs, the paragraph and the full video are aligned implicitly. However, such unit-level comparison may ignore global temporal context, which inevitably limits the generalization ability. In this paper, we propose a contrastive learning framework TempCLR to com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.13738","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/2212.13738/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":"2212.13738","created_at":"2026-07-05T05:56:15.437771+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.13738v2","created_at":"2026-07-05T05:56:15.437771+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.13738","created_at":"2026-07-05T05:56:15.437771+00:00"},{"alias_kind":"pith_short_12","alias_value":"VKHTD5ZCXWPY","created_at":"2026-07-05T05:56:15.437771+00:00"},{"alias_kind":"pith_short_16","alias_value":"VKHTD5ZCXWPY2JU2","created_at":"2026-07-05T05:56:15.437771+00:00"},{"alias_kind":"pith_short_8","alias_value":"VKHTD5ZC","created_at":"2026-07-05T05:56:15.437771+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/VKHTD5ZCXWPY2JU22O4ZVCL7TL","json":"https://pith.science/pith/VKHTD5ZCXWPY2JU22O4ZVCL7TL.json","graph_json":"https://pith.science/api/pith-number/VKHTD5ZCXWPY2JU22O4ZVCL7TL/graph.json","events_json":"https://pith.science/api/pith-number/VKHTD5ZCXWPY2JU22O4ZVCL7TL/events.json","paper":"https://pith.science/paper/VKHTD5ZC"},"agent_actions":{"view_html":"https://pith.science/pith/VKHTD5ZCXWPY2JU22O4ZVCL7TL","download_json":"https://pith.science/pith/VKHTD5ZCXWPY2JU22O4ZVCL7TL.json","view_paper":"https://pith.science/paper/VKHTD5ZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.13738&json=true","fetch_graph":"https://pith.science/api/pith-number/VKHTD5ZCXWPY2JU22O4ZVCL7TL/graph.json","fetch_events":"https://pith.science/api/pith-number/VKHTD5ZCXWPY2JU22O4ZVCL7TL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VKHTD5ZCXWPY2JU22O4ZVCL7TL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VKHTD5ZCXWPY2JU22O4ZVCL7TL/action/storage_attestation","attest_author":"https://pith.science/pith/VKHTD5ZCXWPY2JU22O4ZVCL7TL/action/author_attestation","sign_citation":"https://pith.science/pith/VKHTD5ZCXWPY2JU22O4ZVCL7TL/action/citation_signature","submit_replication":"https://pith.science/pith/VKHTD5ZCXWPY2JU22O4ZVCL7TL/action/replication_record"}},"created_at":"2026-07-05T05:56:15.437771+00:00","updated_at":"2026-07-05T05:56:15.437771+00:00"}