{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:DDWGSW5E6XXESRI5XEVACWQ5XU","short_pith_number":"pith:DDWGSW5E","canonical_record":{"source":{"id":"2205.00823","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-02T12:02:09Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"053321f207463dc1dcc1a9125c712d71a0adaed46bb99019851612271eb58c4f","abstract_canon_sha256":"077844708c808bdfbc2e9fb1fa86ebc332986c34ed4280e56cf790e81b5bde7d"},"schema_version":"1.0"},"canonical_sha256":"18ec695ba4f5ee49451db92a015a1dbd24ab298533ba138dd52a2b95720f45c6","source":{"kind":"arxiv","id":"2205.00823","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.00823","created_at":"2026-07-05T04:19:24Z"},{"alias_kind":"arxiv_version","alias_value":"2205.00823v1","created_at":"2026-07-05T04:19:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.00823","created_at":"2026-07-05T04:19:24Z"},{"alias_kind":"pith_short_12","alias_value":"DDWGSW5E6XXE","created_at":"2026-07-05T04:19:24Z"},{"alias_kind":"pith_short_16","alias_value":"DDWGSW5E6XXESRI5","created_at":"2026-07-05T04:19:24Z"},{"alias_kind":"pith_short_8","alias_value":"DDWGSW5E","created_at":"2026-07-05T04:19:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:DDWGSW5E6XXESRI5XEVACWQ5XU","target":"record","payload":{"canonical_record":{"source":{"id":"2205.00823","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-02T12:02:09Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"053321f207463dc1dcc1a9125c712d71a0adaed46bb99019851612271eb58c4f","abstract_canon_sha256":"077844708c808bdfbc2e9fb1fa86ebc332986c34ed4280e56cf790e81b5bde7d"},"schema_version":"1.0"},"canonical_sha256":"18ec695ba4f5ee49451db92a015a1dbd24ab298533ba138dd52a2b95720f45c6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:19:24.935065Z","signature_b64":"cQmu4eQwKS2sdh7jVbbKguxHi1+ctAc3E3smo5JoJVg8NNf//gpRDIFeAXbH+1EZ4aj+CQXkXIYun3mC42+ECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18ec695ba4f5ee49451db92a015a1dbd24ab298533ba138dd52a2b95720f45c6","last_reissued_at":"2026-07-05T04:19:24.934633Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:19:24.934633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.00823","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":"2026-07-05T04:19:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gMyCZhKlS8/ypjficO+I9f5tjaES6Q99osJKGpsivUGdPN67lDnWlKTm4db7XSTu5Nw4k8UTMCjulOqYviFLDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:17:53.641231Z"},"content_sha256":"42b148df9b881962c7d14c59d73dc33221f9961570e757a57c41a4e53ef09840","schema_version":"1.0","event_id":"sha256:42b148df9b881962c7d14c59d73dc33221f9961570e757a57c41a4e53ef09840"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:DDWGSW5E6XXESRI5XEVACWQ5XU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CenterCLIP: Token Clustering for Efficient Text-Video Retrieval","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CV","authors_text":"Linchao Zhu, Shuai Zhao, Xiaohan Wang, Yi Yang","submitted_at":"2022-05-02T12:02:09Z","abstract_excerpt":"Recently, large-scale pre-training methods like CLIP have made great progress in multi-modal research such as text-video retrieval. In CLIP, transformers are vital for modeling complex multi-modal relations. However, in the vision transformer of CLIP, the essential visual tokenization process, which produces discrete visual token sequences, generates many homogeneous tokens due to the redundancy nature of consecutive and similar frames in videos. This significantly increases computation costs and hinders the deployment of video retrieval models in web applications. In this paper, to reduce the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.00823","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/2205.00823/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":"2026-07-05T04:19:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SJqKv23DYBJT5Gk+o5U91Shk/3n7dFahffDjUXTwqlhCxJSrI9hWNtJ45dircn9ddtTAdFDDqglLXfptDZzeAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:17:53.641731Z"},"content_sha256":"6cbf19f1d218d02f52a83bfe5b65385fccd9f18899ea7ff6326800b0a82068e3","schema_version":"1.0","event_id":"sha256:6cbf19f1d218d02f52a83bfe5b65385fccd9f18899ea7ff6326800b0a82068e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DDWGSW5E6XXESRI5XEVACWQ5XU/bundle.json","state_url":"https://pith.science/pith/DDWGSW5E6XXESRI5XEVACWQ5XU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DDWGSW5E6XXESRI5XEVACWQ5XU/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":"2026-08-04T11:17:53Z","links":{"resolver":"https://pith.science/pith/DDWGSW5E6XXESRI5XEVACWQ5XU","bundle":"https://pith.science/pith/DDWGSW5E6XXESRI5XEVACWQ5XU/bundle.json","state":"https://pith.science/pith/DDWGSW5E6XXESRI5XEVACWQ5XU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DDWGSW5E6XXESRI5XEVACWQ5XU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DDWGSW5E6XXESRI5XEVACWQ5XU","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":"077844708c808bdfbc2e9fb1fa86ebc332986c34ed4280e56cf790e81b5bde7d","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-02T12:02:09Z","title_canon_sha256":"053321f207463dc1dcc1a9125c712d71a0adaed46bb99019851612271eb58c4f"},"schema_version":"1.0","source":{"id":"2205.00823","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.00823","created_at":"2026-07-05T04:19:24Z"},{"alias_kind":"arxiv_version","alias_value":"2205.00823v1","created_at":"2026-07-05T04:19:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.00823","created_at":"2026-07-05T04:19:24Z"},{"alias_kind":"pith_short_12","alias_value":"DDWGSW5E6XXE","created_at":"2026-07-05T04:19:24Z"},{"alias_kind":"pith_short_16","alias_value":"DDWGSW5E6XXESRI5","created_at":"2026-07-05T04:19:24Z"},{"alias_kind":"pith_short_8","alias_value":"DDWGSW5E","created_at":"2026-07-05T04:19:24Z"}],"graph_snapshots":[{"event_id":"sha256:6cbf19f1d218d02f52a83bfe5b65385fccd9f18899ea7ff6326800b0a82068e3","target":"graph","created_at":"2026-07-05T04:19:24Z","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/2205.00823/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, large-scale pre-training methods like CLIP have made great progress in multi-modal research such as text-video retrieval. In CLIP, transformers are vital for modeling complex multi-modal relations. However, in the vision transformer of CLIP, the essential visual tokenization process, which produces discrete visual token sequences, generates many homogeneous tokens due to the redundancy nature of consecutive and similar frames in videos. This significantly increases computation costs and hinders the deployment of video retrieval models in web applications. In this paper, to reduce the","authors_text":"Linchao Zhu, Shuai Zhao, Xiaohan Wang, Yi Yang","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-02T12:02:09Z","title":"CenterCLIP: Token Clustering for Efficient Text-Video Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.00823","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":"sha256:42b148df9b881962c7d14c59d73dc33221f9961570e757a57c41a4e53ef09840","target":"record","created_at":"2026-07-05T04:19:24Z","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":"077844708c808bdfbc2e9fb1fa86ebc332986c34ed4280e56cf790e81b5bde7d","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-02T12:02:09Z","title_canon_sha256":"053321f207463dc1dcc1a9125c712d71a0adaed46bb99019851612271eb58c4f"},"schema_version":"1.0","source":{"id":"2205.00823","kind":"arxiv","version":1}},"canonical_sha256":"18ec695ba4f5ee49451db92a015a1dbd24ab298533ba138dd52a2b95720f45c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18ec695ba4f5ee49451db92a015a1dbd24ab298533ba138dd52a2b95720f45c6","first_computed_at":"2026-07-05T04:19:24.934633Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:19:24.934633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cQmu4eQwKS2sdh7jVbbKguxHi1+ctAc3E3smo5JoJVg8NNf//gpRDIFeAXbH+1EZ4aj+CQXkXIYun3mC42+ECg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:19:24.935065Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.00823","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42b148df9b881962c7d14c59d73dc33221f9961570e757a57c41a4e53ef09840","sha256:6cbf19f1d218d02f52a83bfe5b65385fccd9f18899ea7ff6326800b0a82068e3"],"state_sha256":"5e624fae058430ce5fe2cac4e423cee24ff73f8724ffb58d83e974915d4f2a89"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ex6Y6QzjZA/xUz1OzWcYT78Lv0Y3jG6lQ6HqbWF+b+BC61wvnn/4TrnlHnMkArhgwF5dUyairbToqKsVfi3TBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T11:17:53.645209Z","bundle_sha256":"78e4c96f8ecac37257228d8f546ba003e96617bfbeb1305b0c9336a77415add6"}}