{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:R3RRXSB3W6QRGOAKJMSV6UTIPZ","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":"b58d1d5be7ef5a04e179e1aaae34bda480c551bf3b21ce170a3813bfacf68605","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-08T18:58:16Z","title_canon_sha256":"5f0bd99a51f5aca953cea495a520eb1b68d2f3c68fa61ec5b3051205b645df94"},"schema_version":"1.0","source":{"id":"2112.04478","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.04478","created_at":"2026-07-05T04:40:24Z"},{"alias_kind":"arxiv_version","alias_value":"2112.04478v2","created_at":"2026-07-05T04:40:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.04478","created_at":"2026-07-05T04:40:24Z"},{"alias_kind":"pith_short_12","alias_value":"R3RRXSB3W6QR","created_at":"2026-07-05T04:40:24Z"},{"alias_kind":"pith_short_16","alias_value":"R3RRXSB3W6QRGOAK","created_at":"2026-07-05T04:40:24Z"},{"alias_kind":"pith_short_8","alias_value":"R3RRXSB3","created_at":"2026-07-05T04:40:24Z"}],"graph_snapshots":[{"event_id":"sha256:0d71a6da1958ce1b061522aa0b8a05cd7c0134f12e88c0f9bd56c837c402ba79","target":"graph","created_at":"2026-07-05T04:40:24Z","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/2112.04478/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image-based visual-language (I-VL) pre-training has shown great success for learning joint visual-textual representations from large-scale web data, revealing remarkable ability for zero-shot generalisation. This paper presents a simple but strong baseline to efficiently adapt the pre-trained I-VL model, and exploit its powerful ability for resource-hungry video understanding tasks, with minimal training. Specifically, we propose to optimise a few random vectors, termed as continuous prompt vectors, that convert video-related tasks into the same format as the pre-training objectives. In additi","authors_text":"Chen Ju, Kunhao Zheng, Tengda Han, Weidi Xie, Ya Zhang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-08T18:58:16Z","title":"Prompting Visual-Language Models for Efficient Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.04478","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":"sha256:8d00114a90306cf093123c519caaef0681c0541352ef43e7cac68f8794182ca1","target":"record","created_at":"2026-07-05T04:40:24Z","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":"b58d1d5be7ef5a04e179e1aaae34bda480c551bf3b21ce170a3813bfacf68605","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-08T18:58:16Z","title_canon_sha256":"5f0bd99a51f5aca953cea495a520eb1b68d2f3c68fa61ec5b3051205b645df94"},"schema_version":"1.0","source":{"id":"2112.04478","kind":"arxiv","version":2}},"canonical_sha256":"8ee31bc83bb7a113380a4b255f52687e571f78696f521c2e8ec4ba9ce961bc6a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ee31bc83bb7a113380a4b255f52687e571f78696f521c2e8ec4ba9ce961bc6a","first_computed_at":"2026-07-05T04:40:24.786036Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:40:24.786036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N1pyFR/G9rfloXt5oSRMgErMu8VcJzdwTeMchpd0zb2VBPNwvHBsX8S90UciXwIfbfs052hq2WJIDp4RNIFgBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:40:24.786558Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.04478","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d00114a90306cf093123c519caaef0681c0541352ef43e7cac68f8794182ca1","sha256:0d71a6da1958ce1b061522aa0b8a05cd7c0134f12e88c0f9bd56c837c402ba79"],"state_sha256":"e571fba361d5a5cc878ce188c757e616bf72ec1ecee87849298cac3a91442f67"}