{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:6Y3EFFYXICM5JEZAANVDHD6D55","short_pith_number":"pith:6Y3EFFYX","schema_version":"1.0","canonical_sha256":"f6364297174099d49320036a338fc3ef620545dc512c2437b4bb2bd46991c66f","source":{"kind":"arxiv","id":"2209.15280","version":3},"attestation_state":"computed","paper":{"title":"Learning Transferable Spatiotemporal Representations from Natural Script Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Chen, Ping Luo, Shu-Tao Xia, Xihui Liu, Yixiao Ge, Yuying Ge, Ziyun Zeng","submitted_at":"2022-09-30T07:39:48Z","abstract_excerpt":"Pre-training on large-scale video data has become a common recipe for learning transferable spatiotemporal representations in recent years. Despite some progress, existing methods are mostly limited to highly curated datasets (e.g., K400) and exhibit unsatisfactory out-of-the-box representations. We argue that it is due to the fact that they only capture pixel-level knowledge rather than spatiotemporal semantics, which hinders further progress in video understanding. Inspired by the great success of image-text pre-training (e.g., CLIP), we take the first step to exploit language semantics to b"},"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":"2209.15280","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-30T07:39:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bacf542f5dd048cbb4d8a7a77ec6f58c8fbe26b3e38775e48edb29550fbc7f01","abstract_canon_sha256":"40a74bbf7a046fd3c2694e42346aab561e612587e9fa761ea7c857f12825b67f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:50:08.953935Z","signature_b64":"4IsM4fBvYQvSTEqHU5+4uuKnwSlj6t5lytsKoqe7iJiObljLJ7UJg9KMShCPPFEkEO4IyefZ9lHIXJt1XxlVCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6364297174099d49320036a338fc3ef620545dc512c2437b4bb2bd46991c66f","last_reissued_at":"2026-07-05T05:50:08.953504Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:50:08.953504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Transferable Spatiotemporal Representations from Natural Script Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Chen, Ping Luo, Shu-Tao Xia, Xihui Liu, Yixiao Ge, Yuying Ge, Ziyun Zeng","submitted_at":"2022-09-30T07:39:48Z","abstract_excerpt":"Pre-training on large-scale video data has become a common recipe for learning transferable spatiotemporal representations in recent years. Despite some progress, existing methods are mostly limited to highly curated datasets (e.g., K400) and exhibit unsatisfactory out-of-the-box representations. We argue that it is due to the fact that they only capture pixel-level knowledge rather than spatiotemporal semantics, which hinders further progress in video understanding. Inspired by the great success of image-text pre-training (e.g., CLIP), we take the first step to exploit language semantics to b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.15280","kind":"arxiv","version":3},"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/2209.15280/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":"2209.15280","created_at":"2026-07-05T05:50:08.953563+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.15280v3","created_at":"2026-07-05T05:50:08.953563+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.15280","created_at":"2026-07-05T05:50:08.953563+00:00"},{"alias_kind":"pith_short_12","alias_value":"6Y3EFFYXICM5","created_at":"2026-07-05T05:50:08.953563+00:00"},{"alias_kind":"pith_short_16","alias_value":"6Y3EFFYXICM5JEZA","created_at":"2026-07-05T05:50:08.953563+00:00"},{"alias_kind":"pith_short_8","alias_value":"6Y3EFFYX","created_at":"2026-07-05T05:50:08.953563+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/6Y3EFFYXICM5JEZAANVDHD6D55","json":"https://pith.science/pith/6Y3EFFYXICM5JEZAANVDHD6D55.json","graph_json":"https://pith.science/api/pith-number/6Y3EFFYXICM5JEZAANVDHD6D55/graph.json","events_json":"https://pith.science/api/pith-number/6Y3EFFYXICM5JEZAANVDHD6D55/events.json","paper":"https://pith.science/paper/6Y3EFFYX"},"agent_actions":{"view_html":"https://pith.science/pith/6Y3EFFYXICM5JEZAANVDHD6D55","download_json":"https://pith.science/pith/6Y3EFFYXICM5JEZAANVDHD6D55.json","view_paper":"https://pith.science/paper/6Y3EFFYX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.15280&json=true","fetch_graph":"https://pith.science/api/pith-number/6Y3EFFYXICM5JEZAANVDHD6D55/graph.json","fetch_events":"https://pith.science/api/pith-number/6Y3EFFYXICM5JEZAANVDHD6D55/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6Y3EFFYXICM5JEZAANVDHD6D55/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6Y3EFFYXICM5JEZAANVDHD6D55/action/storage_attestation","attest_author":"https://pith.science/pith/6Y3EFFYXICM5JEZAANVDHD6D55/action/author_attestation","sign_citation":"https://pith.science/pith/6Y3EFFYXICM5JEZAANVDHD6D55/action/citation_signature","submit_replication":"https://pith.science/pith/6Y3EFFYXICM5JEZAANVDHD6D55/action/replication_record"}},"created_at":"2026-07-05T05:50:08.953563+00:00","updated_at":"2026-07-05T05:50:08.953563+00:00"}