{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:E4Z22ORPANUUFUNAOFVV32SP3W","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":"1ef4143fcce795688fe3b482501fe129b3393abc289c8147e49fd420b3edc589","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-31T11:36:53Z","title_canon_sha256":"ce5f996d3e36b57e5ea31488a95666255f67a711d3f45b305dbbc0d8e02837a6"},"schema_version":"1.0","source":{"id":"2301.00182","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.00182","created_at":"2026-07-05T05:54:34Z"},{"alias_kind":"arxiv_version","alias_value":"2301.00182v2","created_at":"2026-07-05T05:54:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.00182","created_at":"2026-07-05T05:54:34Z"},{"alias_kind":"pith_short_12","alias_value":"E4Z22ORPANUU","created_at":"2026-07-05T05:54:34Z"},{"alias_kind":"pith_short_16","alias_value":"E4Z22ORPANUUFUNA","created_at":"2026-07-05T05:54:34Z"},{"alias_kind":"pith_short_8","alias_value":"E4Z22ORP","created_at":"2026-07-05T05:54:34Z"}],"graph_snapshots":[{"event_id":"sha256:b8fdeffd03a02dca21be226d5ba33fb645923652fe17a2da75bca2cdfc9a9e55","target":"graph","created_at":"2026-07-05T05:54:34Z","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/2301.00182/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) pre-trained on large-scale image-text pairs have demonstrated impressive transferability on various visual tasks. Transferring knowledge from such powerful VLMs is a promising direction for building effective video recognition models. However, current exploration in this field is still limited. We believe that the greatest value of pre-trained VLMs lies in building a bridge between visual and textual domains. In this paper, we propose a novel framework called BIKE, which utilizes the cross-modal bridge to explore bidirectional knowledge: i) We introduce the Video ","authors_text":"Haipeng Luo, Jingdong Wang, Wanli Ouyang, Wenhao Wu, Xiaohan Wang, Yi Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-31T11:36:53Z","title":"Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.00182","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":"sha256:7cfab3915994835e8f0d1323b6ab1e231b69d604814e4e99b7a6fd0e22a9b03a","target":"record","created_at":"2026-07-05T05:54:34Z","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":"1ef4143fcce795688fe3b482501fe129b3393abc289c8147e49fd420b3edc589","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-31T11:36:53Z","title_canon_sha256":"ce5f996d3e36b57e5ea31488a95666255f67a711d3f45b305dbbc0d8e02837a6"},"schema_version":"1.0","source":{"id":"2301.00182","kind":"arxiv","version":2}},"canonical_sha256":"2733ad3a2f036942d1a0716b5dea4fddae860690056f82652bf0cea02aade245","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2733ad3a2f036942d1a0716b5dea4fddae860690056f82652bf0cea02aade245","first_computed_at":"2026-07-05T05:54:34.905003Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:54:34.905003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h1/V3s0A0fi/CqtFt3FtLfSdiJPheKeoLRbRijB0QIIEr3UAqHWAtb46B/2ebrOzaMsyAcfDxks878QNkoaiCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:54:34.905404Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.00182","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7cfab3915994835e8f0d1323b6ab1e231b69d604814e4e99b7a6fd0e22a9b03a","sha256:b8fdeffd03a02dca21be226d5ba33fb645923652fe17a2da75bca2cdfc9a9e55"],"state_sha256":"cbf4e02fd0796dc6fb56f1c0e4e1ac81ffa50a2677cf854b3f0a3484f0e7846a"}