{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:KU3HH7V7RMKTL7GR544SOKM3FQ","short_pith_number":"pith:KU3HH7V7","canonical_record":{"source":{"id":"2206.12845","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-26T11:12:49Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"7de24a15bbb2510a510c41ef3cd93134fa71af4c51d64fbfc69c86b405beb118","abstract_canon_sha256":"9a912cebbe8bb2da9fedce6679fd76c9ad7e4b9a4f90e63e6fdb6b62c45d9488"},"schema_version":"1.0"},"canonical_sha256":"553673febf8b1535fcd1ef3927299b2c14b659dfa23dac087320668a6db9b3a5","source":{"kind":"arxiv","id":"2206.12845","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.12845","created_at":"2026-07-05T04:34:59Z"},{"alias_kind":"arxiv_version","alias_value":"2206.12845v1","created_at":"2026-07-05T04:34:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.12845","created_at":"2026-07-05T04:34:59Z"},{"alias_kind":"pith_short_12","alias_value":"KU3HH7V7RMKT","created_at":"2026-07-05T04:34:59Z"},{"alias_kind":"pith_short_16","alias_value":"KU3HH7V7RMKTL7GR","created_at":"2026-07-05T04:34:59Z"},{"alias_kind":"pith_short_8","alias_value":"KU3HH7V7","created_at":"2026-07-05T04:34:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:KU3HH7V7RMKTL7GR544SOKM3FQ","target":"record","payload":{"canonical_record":{"source":{"id":"2206.12845","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-26T11:12:49Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"7de24a15bbb2510a510c41ef3cd93134fa71af4c51d64fbfc69c86b405beb118","abstract_canon_sha256":"9a912cebbe8bb2da9fedce6679fd76c9ad7e4b9a4f90e63e6fdb6b62c45d9488"},"schema_version":"1.0"},"canonical_sha256":"553673febf8b1535fcd1ef3927299b2c14b659dfa23dac087320668a6db9b3a5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:34:59.871122Z","signature_b64":"GV8zpPcXFDPi92v8i8GrQu7af8mrJa86tLvdhbQXTlVyOGR+gVNbVK4VHjjkAfcShBT6+/kYj7q0xxEkidwnBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"553673febf8b1535fcd1ef3927299b2c14b659dfa23dac087320668a6db9b3a5","last_reissued_at":"2026-07-05T04:34:59.870630Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:34:59.870630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.12845","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":"2026-07-05T04:34:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lmzb+AZq32wkllThYtB/0MdtDoGCnFXGOmbT0GKlPIN3PjkKccfMpaAfK1D216kvgkoYnsNqmZskvCpRctEEAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T05:38:24.004653Z"},"content_sha256":"5b4dd65709785fb4ec9616ea321096f00d3475f28fc5ab9ef30a8fce5e01f2e8","schema_version":"1.0","event_id":"sha256:5b4dd65709785fb4ec9616ea321096f00d3475f28fc5ab9ef30a8fce5e01f2e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:KU3HH7V7RMKTL7GR544SOKM3FQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RoME: Role-aware Mixture-of-Expert Transformer for Text-to-Video Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Burak Satar, Hanwang Zhang, Hongyuan Zhu, Joo Hwee Lim","submitted_at":"2022-06-26T11:12:49Z","abstract_excerpt":"Seas of videos are uploaded daily with the popularity of social channels; thus, retrieving the most related video contents with user textual queries plays a more crucial role. Most methods consider only one joint embedding space between global visual and textual features without considering the local structures of each modality. Some other approaches consider multiple embedding spaces consisting of global and local features separately, ignoring rich inter-modality correlations.\n  We propose a novel mixture-of-expert transformer RoME that disentangles the text and the video into three levels; t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.12845","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/2206.12845/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":"2026-07-05T04:34:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T68x1lY5YkIKYw+hwPHax4T3ObrEDK3HxZ1lEnLrDc5hIwnLjuBbhuL2hSkxMvNx25wEESovT6exza4mA+8rCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T05:38:24.005155Z"},"content_sha256":"77cd74ca76a6d3eddce815ec592b73c5f4af7dcf33e0ea581d2d71cf25558f2e","schema_version":"1.0","event_id":"sha256:77cd74ca76a6d3eddce815ec592b73c5f4af7dcf33e0ea581d2d71cf25558f2e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KU3HH7V7RMKTL7GR544SOKM3FQ/bundle.json","state_url":"https://pith.science/pith/KU3HH7V7RMKTL7GR544SOKM3FQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KU3HH7V7RMKTL7GR544SOKM3FQ/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":"2026-08-19T05:38:24Z","links":{"resolver":"https://pith.science/pith/KU3HH7V7RMKTL7GR544SOKM3FQ","bundle":"https://pith.science/pith/KU3HH7V7RMKTL7GR544SOKM3FQ/bundle.json","state":"https://pith.science/pith/KU3HH7V7RMKTL7GR544SOKM3FQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KU3HH7V7RMKTL7GR544SOKM3FQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:KU3HH7V7RMKTL7GR544SOKM3FQ","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":"9a912cebbe8bb2da9fedce6679fd76c9ad7e4b9a4f90e63e6fdb6b62c45d9488","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-26T11:12:49Z","title_canon_sha256":"7de24a15bbb2510a510c41ef3cd93134fa71af4c51d64fbfc69c86b405beb118"},"schema_version":"1.0","source":{"id":"2206.12845","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.12845","created_at":"2026-07-05T04:34:59Z"},{"alias_kind":"arxiv_version","alias_value":"2206.12845v1","created_at":"2026-07-05T04:34:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.12845","created_at":"2026-07-05T04:34:59Z"},{"alias_kind":"pith_short_12","alias_value":"KU3HH7V7RMKT","created_at":"2026-07-05T04:34:59Z"},{"alias_kind":"pith_short_16","alias_value":"KU3HH7V7RMKTL7GR","created_at":"2026-07-05T04:34:59Z"},{"alias_kind":"pith_short_8","alias_value":"KU3HH7V7","created_at":"2026-07-05T04:34:59Z"}],"graph_snapshots":[{"event_id":"sha256:77cd74ca76a6d3eddce815ec592b73c5f4af7dcf33e0ea581d2d71cf25558f2e","target":"graph","created_at":"2026-07-05T04:34:59Z","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/2206.12845/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Seas of videos are uploaded daily with the popularity of social channels; thus, retrieving the most related video contents with user textual queries plays a more crucial role. Most methods consider only one joint embedding space between global visual and textual features without considering the local structures of each modality. Some other approaches consider multiple embedding spaces consisting of global and local features separately, ignoring rich inter-modality correlations.\n  We propose a novel mixture-of-expert transformer RoME that disentangles the text and the video into three levels; t","authors_text":"Burak Satar, Hanwang Zhang, Hongyuan Zhu, Joo Hwee Lim","cross_cats":["cs.IR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-26T11:12:49Z","title":"RoME: Role-aware Mixture-of-Expert Transformer for Text-to-Video Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.12845","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":"sha256:5b4dd65709785fb4ec9616ea321096f00d3475f28fc5ab9ef30a8fce5e01f2e8","target":"record","created_at":"2026-07-05T04:34:59Z","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":"9a912cebbe8bb2da9fedce6679fd76c9ad7e4b9a4f90e63e6fdb6b62c45d9488","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-06-26T11:12:49Z","title_canon_sha256":"7de24a15bbb2510a510c41ef3cd93134fa71af4c51d64fbfc69c86b405beb118"},"schema_version":"1.0","source":{"id":"2206.12845","kind":"arxiv","version":1}},"canonical_sha256":"553673febf8b1535fcd1ef3927299b2c14b659dfa23dac087320668a6db9b3a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"553673febf8b1535fcd1ef3927299b2c14b659dfa23dac087320668a6db9b3a5","first_computed_at":"2026-07-05T04:34:59.870630Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:34:59.870630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GV8zpPcXFDPi92v8i8GrQu7af8mrJa86tLvdhbQXTlVyOGR+gVNbVK4VHjjkAfcShBT6+/kYj7q0xxEkidwnBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:34:59.871122Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.12845","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b4dd65709785fb4ec9616ea321096f00d3475f28fc5ab9ef30a8fce5e01f2e8","sha256:77cd74ca76a6d3eddce815ec592b73c5f4af7dcf33e0ea581d2d71cf25558f2e"],"state_sha256":"25f614d1a90e4c100b66013bed1e4d99f758690069be02abdef7552f7ac61f2b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c845ymxKtRMS4PfwkExCMlRNO+7gJgG2KrlOA+cGUFzzeBlD9dpHyako4CwEYbAx1kFvHGzPwjbNM4bMFdYCAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T05:38:24.009733Z","bundle_sha256":"d1fb7552939f6cc2484226afeee02a5507f5d6fc0cd474fb1ad7656955a26ce8"}}