{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:IDKVDK63DOKR37PADZNMOLEQ2L","short_pith_number":"pith:IDKVDK63","canonical_record":{"source":{"id":"2205.08508","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-17T17:26:23Z","cross_cats_sorted":[],"title_canon_sha256":"b94981acca69d546b1fe772bb5ce6373d78c2c6ede8d0a1f8df848df4092ec0f","abstract_canon_sha256":"b82a53da9182e6249adf84474d6411d0d8158a01fca878cf68873fb9ab831863"},"schema_version":"1.0"},"canonical_sha256":"40d551abdb1b951dfde01e5ac72c90d2c01ab2b229a10cbd6446af01942010ab","source":{"kind":"arxiv","id":"2205.08508","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:IDKVDK63DOKR37PADZNMOLEQ2L","target":"record","payload":{"canonical_record":{"source":{"id":"2205.08508","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-17T17:26:23Z","cross_cats_sorted":[],"title_canon_sha256":"b94981acca69d546b1fe772bb5ce6373d78c2c6ede8d0a1f8df848df4092ec0f","abstract_canon_sha256":"b82a53da9182e6249adf84474d6411d0d8158a01fca878cf68873fb9ab831863"},"schema_version":"1.0"},"canonical_sha256":"40d551abdb1b951dfde01e5ac72c90d2c01ab2b229a10cbd6446af01942010ab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:24:03.800808Z","signature_b64":"HIKL7qHfy7jzTsLl+5a5A6MMCfAdyNxD9HlQy7j1JCbJ/7KZgLivL3noM/PnTZTQTeOgb2GRPIQZPKZU9Z5JDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40d551abdb1b951dfde01e5ac72c90d2c01ab2b229a10cbd6446af01942010ab","last_reissued_at":"2026-07-05T04:24:03.800288Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:24:03.800288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.08508","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:24:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Trraw57V1V/NRH/N8KbJ8xeHIlv9sk0dDq7wmWxPv8jllu4FeflwDPXdIab/O+NXVW3DoHiOk08ErvZlUwxbDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:37:47.912584Z"},"content_sha256":"848e012b141e9bee54ed4137e0c105db8a556eecc3811e446b53b353ea6a7f13","schema_version":"1.0","event_id":"sha256:848e012b141e9bee54ed4137e0c105db8a556eecc3811e446b53b353ea6a7f13"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:IDKVDK63DOKR37PADZNMOLEQ2L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A CLIP-Hitchhiker's Guide to Long Video Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Zisserman, Arsha Nagrani, G\\\"ul Varol, Max Bain","submitted_at":"2022-05-17T17:26:23Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.08508","kind":"arxiv","version":1},"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/2205.08508/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:24:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E2aAAd2LgjH+clEPtp25fqaYPqbQ+KfmHQ59NKkzWtK9ETLlftp5LZxHw3M2hzh2V/wpBNMFXl9bpQtX0ViQAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:37:47.913095Z"},"content_sha256":"fd805044f2655f023d07f92ff9e7da880907d13a5eab299b9f5af0d405202309","schema_version":"1.0","event_id":"sha256:fd805044f2655f023d07f92ff9e7da880907d13a5eab299b9f5af0d405202309"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IDKVDK63DOKR37PADZNMOLEQ2L/bundle.json","state_url":"https://pith.science/pith/IDKVDK63DOKR37PADZNMOLEQ2L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IDKVDK63DOKR37PADZNMOLEQ2L/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T23:37:47Z","links":{"resolver":"https://pith.science/pith/IDKVDK63DOKR37PADZNMOLEQ2L","bundle":"https://pith.science/pith/IDKVDK63DOKR37PADZNMOLEQ2L/bundle.json","state":"https://pith.science/pith/IDKVDK63DOKR37PADZNMOLEQ2L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IDKVDK63DOKR37PADZNMOLEQ2L/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t1q5K/M1245AND2i+RDfVSwfBjiIB29X9QD4Ri3aDwBgPmrSCpY41x4gnZMBGsN+E1hlAdqv7BcqMW/euuCRBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T23:37:47.917600Z","bundle_sha256":"8c63fab74a06f2424a9fb0d574cfeea92d913f34c3ff8eacbf24b4122aa91d36"}}