{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SZ2TZNWDLCUEYNQLHNTH7QTOWW","short_pith_number":"pith:SZ2TZNWD","canonical_record":{"source":{"id":"2408.07600","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-14T15:00:27Z","cross_cats_sorted":[],"title_canon_sha256":"5ead3d4445948ee2ea3d03b99f1ab235adec36826ec01bfc2eca12567c2694d6","abstract_canon_sha256":"eb4d7c684658f5b3fdca80ddedc308884a34d8e587f39153a0b8ed3a3d781aa7"},"schema_version":"1.0"},"canonical_sha256":"96753cb6c358a84c360b3b667fc26eb59ca3be4e102b52b78cce59fd3255ad58","source":{"kind":"arxiv","id":"2408.07600","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.07600","created_at":"2026-07-05T08:55:27Z"},{"alias_kind":"arxiv_version","alias_value":"2408.07600v1","created_at":"2026-07-05T08:55:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07600","created_at":"2026-07-05T08:55:27Z"},{"alias_kind":"pith_short_12","alias_value":"SZ2TZNWDLCUE","created_at":"2026-07-05T08:55:27Z"},{"alias_kind":"pith_short_16","alias_value":"SZ2TZNWDLCUEYNQL","created_at":"2026-07-05T08:55:27Z"},{"alias_kind":"pith_short_8","alias_value":"SZ2TZNWD","created_at":"2026-07-05T08:55:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SZ2TZNWDLCUEYNQLHNTH7QTOWW","target":"record","payload":{"canonical_record":{"source":{"id":"2408.07600","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-14T15:00:27Z","cross_cats_sorted":[],"title_canon_sha256":"5ead3d4445948ee2ea3d03b99f1ab235adec36826ec01bfc2eca12567c2694d6","abstract_canon_sha256":"eb4d7c684658f5b3fdca80ddedc308884a34d8e587f39153a0b8ed3a3d781aa7"},"schema_version":"1.0"},"canonical_sha256":"96753cb6c358a84c360b3b667fc26eb59ca3be4e102b52b78cce59fd3255ad58","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:55:27.622774Z","signature_b64":"y+/GRKJpAq77Ww7Bfx4Hx64sYKjwwF83nEhbISd5KGMdITDYo+5vNwSEDk7aTrRS2EMf5f/8/Sx1mjrums2xBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96753cb6c358a84c360b3b667fc26eb59ca3be4e102b52b78cce59fd3255ad58","last_reissued_at":"2026-07-05T08:55:27.622400Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:55:27.622400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.07600","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":"2026-07-05T08:55:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BM/52zEIsczBRYX0RTD0ABFlN6zmTNXH4cSMJoc2FcXX/V+UuyHvgsB+Matx0TcvsYqV3Ydq7Q0vyamcHIKfAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:25:22.590408Z"},"content_sha256":"c4db1b2a35c52e61a5a8808076f7ad40bd648bb964769c60309accf0bec69beb","schema_version":"1.0","event_id":"sha256:c4db1b2a35c52e61a5a8808076f7ad40bd648bb964769c60309accf0bec69beb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SZ2TZNWDLCUEYNQLHNTH7QTOWW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Disentangle and denoise: Tackling context misalignment for video moment retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Ban, Han Fang, Hao Sun, Kaijing Ma, Lanxiang Zhou, Xianghao Zang, Xingsong Hou, Yongxiang Li, Zerun Feng, Zhongjiang He","submitted_at":"2024-08-14T15:00:27Z","abstract_excerpt":"Video Moment Retrieval, which aims to locate in-context video moments according to a natural language query, is an essential task for cross-modal grounding. Existing methods focus on enhancing the cross-modal interactions between all moments and the textual description for video understanding. However, constantly interacting with all locations is unreasonable because of uneven semantic distribution across the timeline and noisy visual backgrounds. This paper proposes a cross-modal Context Denoising Network (CDNet) for accurate moment retrieval by disentangling complex correlations and denoisin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07600","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/2408.07600/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":"2026-07-05T08:55:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KwDliB5CyTtt/BNUKMKsKwH3XmaJZbqyAYDMFVQLp5SUQJPcdh0+lHY9qCa1Ju6TSVtu1vwc37dKU5X8n9BFDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:25:22.591259Z"},"content_sha256":"f6ce4ae02280ecfdbe10a00b03155bb3998e805623077c04dbd4a06298bbe07d","schema_version":"1.0","event_id":"sha256:f6ce4ae02280ecfdbe10a00b03155bb3998e805623077c04dbd4a06298bbe07d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SZ2TZNWDLCUEYNQLHNTH7QTOWW/bundle.json","state_url":"https://pith.science/pith/SZ2TZNWDLCUEYNQLHNTH7QTOWW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SZ2TZNWDLCUEYNQLHNTH7QTOWW/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":"2026-08-07T16:25:22Z","links":{"resolver":"https://pith.science/pith/SZ2TZNWDLCUEYNQLHNTH7QTOWW","bundle":"https://pith.science/pith/SZ2TZNWDLCUEYNQLHNTH7QTOWW/bundle.json","state":"https://pith.science/pith/SZ2TZNWDLCUEYNQLHNTH7QTOWW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SZ2TZNWDLCUEYNQLHNTH7QTOWW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SZ2TZNWDLCUEYNQLHNTH7QTOWW","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":"eb4d7c684658f5b3fdca80ddedc308884a34d8e587f39153a0b8ed3a3d781aa7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-14T15:00:27Z","title_canon_sha256":"5ead3d4445948ee2ea3d03b99f1ab235adec36826ec01bfc2eca12567c2694d6"},"schema_version":"1.0","source":{"id":"2408.07600","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.07600","created_at":"2026-07-05T08:55:27Z"},{"alias_kind":"arxiv_version","alias_value":"2408.07600v1","created_at":"2026-07-05T08:55:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.07600","created_at":"2026-07-05T08:55:27Z"},{"alias_kind":"pith_short_12","alias_value":"SZ2TZNWDLCUE","created_at":"2026-07-05T08:55:27Z"},{"alias_kind":"pith_short_16","alias_value":"SZ2TZNWDLCUEYNQL","created_at":"2026-07-05T08:55:27Z"},{"alias_kind":"pith_short_8","alias_value":"SZ2TZNWD","created_at":"2026-07-05T08:55:27Z"}],"graph_snapshots":[{"event_id":"sha256:f6ce4ae02280ecfdbe10a00b03155bb3998e805623077c04dbd4a06298bbe07d","target":"graph","created_at":"2026-07-05T08:55:27Z","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/2408.07600/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video Moment Retrieval, which aims to locate in-context video moments according to a natural language query, is an essential task for cross-modal grounding. Existing methods focus on enhancing the cross-modal interactions between all moments and the textual description for video understanding. However, constantly interacting with all locations is unreasonable because of uneven semantic distribution across the timeline and noisy visual backgrounds. This paper proposes a cross-modal Context Denoising Network (CDNet) for accurate moment retrieval by disentangling complex correlations and denoisin","authors_text":"Chao Ban, Han Fang, Hao Sun, Kaijing Ma, Lanxiang Zhou, Xianghao Zang, Xingsong Hou, Yongxiang Li, Zerun Feng, Zhongjiang He","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-14T15:00:27Z","title":"Disentangle and denoise: Tackling context misalignment for video moment retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.07600","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:c4db1b2a35c52e61a5a8808076f7ad40bd648bb964769c60309accf0bec69beb","target":"record","created_at":"2026-07-05T08:55:27Z","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":"eb4d7c684658f5b3fdca80ddedc308884a34d8e587f39153a0b8ed3a3d781aa7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-14T15:00:27Z","title_canon_sha256":"5ead3d4445948ee2ea3d03b99f1ab235adec36826ec01bfc2eca12567c2694d6"},"schema_version":"1.0","source":{"id":"2408.07600","kind":"arxiv","version":1}},"canonical_sha256":"96753cb6c358a84c360b3b667fc26eb59ca3be4e102b52b78cce59fd3255ad58","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96753cb6c358a84c360b3b667fc26eb59ca3be4e102b52b78cce59fd3255ad58","first_computed_at":"2026-07-05T08:55:27.622400Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:55:27.622400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y+/GRKJpAq77Ww7Bfx4Hx64sYKjwwF83nEhbISd5KGMdITDYo+5vNwSEDk7aTrRS2EMf5f/8/Sx1mjrums2xBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:55:27.622774Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.07600","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4db1b2a35c52e61a5a8808076f7ad40bd648bb964769c60309accf0bec69beb","sha256:f6ce4ae02280ecfdbe10a00b03155bb3998e805623077c04dbd4a06298bbe07d"],"state_sha256":"45c2ae0006f4ecdd260bef826f2796ccdbddf819c1f2a31b8f78063fcb575e6d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EIPmWoXlpuaZfdB3DYY+Nai3XN2OYMI2WB3OxFnH703BdusxD6wn4HCpNtz4xVpPCQIAlW8zvzQ3N9I+aBaRBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T16:25:22.597093Z","bundle_sha256":"09bd77cc56444033b3a548b38993b58404f6370d3fda5091aea6ed14fc1ee751"}}