{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:IDKVDK63DOKR37PADZNMOLEQ2L","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":"b82a53da9182e6249adf84474d6411d0d8158a01fca878cf68873fb9ab831863","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-17T17:26:23Z","title_canon_sha256":"b94981acca69d546b1fe772bb5ce6373d78c2c6ede8d0a1f8df848df4092ec0f"},"schema_version":"1.0","source":{"id":"2205.08508","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.08508","created_at":"2026-07-05T04:24:03Z"},{"alias_kind":"arxiv_version","alias_value":"2205.08508v1","created_at":"2026-07-05T04:24:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.08508","created_at":"2026-07-05T04:24:03Z"},{"alias_kind":"pith_short_12","alias_value":"IDKVDK63DOKR","created_at":"2026-07-05T04:24:03Z"},{"alias_kind":"pith_short_16","alias_value":"IDKVDK63DOKR37PA","created_at":"2026-07-05T04:24:03Z"},{"alias_kind":"pith_short_8","alias_value":"IDKVDK63","created_at":"2026-07-05T04:24:03Z"}],"graph_snapshots":[{"event_id":"sha256:fd805044f2655f023d07f92ff9e7da880907d13a5eab299b9f5af0d405202309","target":"graph","created_at":"2026-07-05T04:24:03Z","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/2205.08508/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Our goal in this paper is the adaptation of image-text models for long video retrieval. Recent works have demonstrated state-of-the-art performance in video retrieval by adopting CLIP, effectively hitchhiking on the image-text representation for video tasks. However, there has been limited success in learning temporal aggregation that outperform mean-pooling the image-level representations extracted per frame by CLIP. We find that the simple yet effective baseline of weighted-mean of frame embeddings via query-scoring is a significant improvement above all prior temporal modelling attempts and","authors_text":"Andrew Zisserman, Arsha Nagrani, G\\\"ul Varol, Max Bain","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-17T17:26:23Z","title":"A CLIP-Hitchhiker's Guide to Long Video Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.08508","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":"sha256:848e012b141e9bee54ed4137e0c105db8a556eecc3811e446b53b353ea6a7f13","target":"record","created_at":"2026-07-05T04:24:03Z","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":"b82a53da9182e6249adf84474d6411d0d8158a01fca878cf68873fb9ab831863","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-17T17:26:23Z","title_canon_sha256":"b94981acca69d546b1fe772bb5ce6373d78c2c6ede8d0a1f8df848df4092ec0f"},"schema_version":"1.0","source":{"id":"2205.08508","kind":"arxiv","version":1}},"canonical_sha256":"40d551abdb1b951dfde01e5ac72c90d2c01ab2b229a10cbd6446af01942010ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40d551abdb1b951dfde01e5ac72c90d2c01ab2b229a10cbd6446af01942010ab","first_computed_at":"2026-07-05T04:24:03.800288Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:24:03.800288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HIKL7qHfy7jzTsLl+5a5A6MMCfAdyNxD9HlQy7j1JCbJ/7KZgLivL3noM/PnTZTQTeOgb2GRPIQZPKZU9Z5JDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:24:03.800808Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.08508","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:848e012b141e9bee54ed4137e0c105db8a556eecc3811e446b53b353ea6a7f13","sha256:fd805044f2655f023d07f92ff9e7da880907d13a5eab299b9f5af0d405202309"],"state_sha256":"03e21ce10b55eaead515f962c05a879da887cfb6a858d3eaae13298a0c94de44"}