{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XCNSMZOX4DWJP3JI34KT3PMNR7","short_pith_number":"pith:XCNSMZOX","canonical_record":{"source":{"id":"2411.11278","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-18T04:35:20Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"e9f5590f5282cd0f1e95364667c12c22da092e61e7689949776b888bf00e1552","abstract_canon_sha256":"00db3541f7d980a60dfb4d06295a2d72a1ccb0bc680b69967c3de9f5c1a05a8c"},"schema_version":"1.0"},"canonical_sha256":"b89b2665d7e0ec97ed28df153dbd8d8ff5a84d294755533c9bad727692f20055","source":{"kind":"arxiv","id":"2411.11278","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.11278","created_at":"2026-07-05T10:28:26Z"},{"alias_kind":"arxiv_version","alias_value":"2411.11278v3","created_at":"2026-07-05T10:28:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11278","created_at":"2026-07-05T10:28:26Z"},{"alias_kind":"pith_short_12","alias_value":"XCNSMZOX4DWJ","created_at":"2026-07-05T10:28:26Z"},{"alias_kind":"pith_short_16","alias_value":"XCNSMZOX4DWJP3JI","created_at":"2026-07-05T10:28:26Z"},{"alias_kind":"pith_short_8","alias_value":"XCNSMZOX","created_at":"2026-07-05T10:28:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XCNSMZOX4DWJP3JI34KT3PMNR7","target":"record","payload":{"canonical_record":{"source":{"id":"2411.11278","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-18T04:35:20Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"e9f5590f5282cd0f1e95364667c12c22da092e61e7689949776b888bf00e1552","abstract_canon_sha256":"00db3541f7d980a60dfb4d06295a2d72a1ccb0bc680b69967c3de9f5c1a05a8c"},"schema_version":"1.0"},"canonical_sha256":"b89b2665d7e0ec97ed28df153dbd8d8ff5a84d294755533c9bad727692f20055","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:26.460998Z","signature_b64":"aBKthAf+ng7H0McQrIIJYCgO0iDtQvMxrYmGALMYc/oSzioSPnriySPvO7ObaeHWcJEZ1W6OO4eEZ0+nhQ0kCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b89b2665d7e0ec97ed28df153dbd8d8ff5a84d294755533c9bad727692f20055","last_reissued_at":"2026-07-05T10:28:26.460490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:26.460490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.11278","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:28:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F+7N6DoiYwrAaqCU4BI9b7wRruf/thBRIYKDMMo9n50U5v7qpmsBEyN9bXam3LDrjONm8hqH8x948NcWRBpBCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T02:41:13.657822Z"},"content_sha256":"aa7562e93ce41a9528b1a0c5132ed88bf51fb04572904279165d878cfdce8b66","schema_version":"1.0","event_id":"sha256:aa7562e93ce41a9528b1a0c5132ed88bf51fb04572904279165d878cfdce8b66"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XCNSMZOX4DWJP3JI34KT3PMNR7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Open-Vocabulary Audio-Visual Event Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Dan Guo, Jingjing Hu, Jinxing Zhou, Meng Wang, Ruohao Guo, Xiaojun Chang, Yiran Zhong, Yuxin Mao","submitted_at":"2024-11-18T04:35:20Z","abstract_excerpt":"The Audio-Visual Event Localization (AVEL) task aims to temporally locate and classify video events that are both audible and visible. Most research in this field assumes a closed-set setting, which restricts these models' ability to handle test data containing event categories absent (unseen) during training. Recently, a few studies have explored AVEL in an open-set setting, enabling the recognition of unseen events as ``unknown'', but without providing category-specific semantics. In this paper, we advance the field by introducing the Open-Vocabulary Audio-Visual Event Localization (OV-AVEL)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11278","kind":"arxiv","version":3},"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/2411.11278/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":"2026-07-05T10:28:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NRyaVsCy5DNEu/hZN7M9i/xCgWyib+zY04vgSWrL595RqPStqwfX9sTyvXCZbqbpZMrpuR3xnipqLhl5qtvADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T02:41:13.658757Z"},"content_sha256":"b6607686f7dd73a2b806c4223e7dd1fa4d208f1d9c2009461beab6a57f78b624","schema_version":"1.0","event_id":"sha256:b6607686f7dd73a2b806c4223e7dd1fa4d208f1d9c2009461beab6a57f78b624"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XCNSMZOX4DWJP3JI34KT3PMNR7/bundle.json","state_url":"https://pith.science/pith/XCNSMZOX4DWJP3JI34KT3PMNR7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XCNSMZOX4DWJP3JI34KT3PMNR7/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":"2026-08-18T02:41:13Z","links":{"resolver":"https://pith.science/pith/XCNSMZOX4DWJP3JI34KT3PMNR7","bundle":"https://pith.science/pith/XCNSMZOX4DWJP3JI34KT3PMNR7/bundle.json","state":"https://pith.science/pith/XCNSMZOX4DWJP3JI34KT3PMNR7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XCNSMZOX4DWJP3JI34KT3PMNR7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XCNSMZOX4DWJP3JI34KT3PMNR7","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":"00db3541f7d980a60dfb4d06295a2d72a1ccb0bc680b69967c3de9f5c1a05a8c","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-18T04:35:20Z","title_canon_sha256":"e9f5590f5282cd0f1e95364667c12c22da092e61e7689949776b888bf00e1552"},"schema_version":"1.0","source":{"id":"2411.11278","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.11278","created_at":"2026-07-05T10:28:26Z"},{"alias_kind":"arxiv_version","alias_value":"2411.11278v3","created_at":"2026-07-05T10:28:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11278","created_at":"2026-07-05T10:28:26Z"},{"alias_kind":"pith_short_12","alias_value":"XCNSMZOX4DWJ","created_at":"2026-07-05T10:28:26Z"},{"alias_kind":"pith_short_16","alias_value":"XCNSMZOX4DWJP3JI","created_at":"2026-07-05T10:28:26Z"},{"alias_kind":"pith_short_8","alias_value":"XCNSMZOX","created_at":"2026-07-05T10:28:26Z"}],"graph_snapshots":[{"event_id":"sha256:b6607686f7dd73a2b806c4223e7dd1fa4d208f1d9c2009461beab6a57f78b624","target":"graph","created_at":"2026-07-05T10:28:26Z","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/2411.11278/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Audio-Visual Event Localization (AVEL) task aims to temporally locate and classify video events that are both audible and visible. Most research in this field assumes a closed-set setting, which restricts these models' ability to handle test data containing event categories absent (unseen) during training. Recently, a few studies have explored AVEL in an open-set setting, enabling the recognition of unseen events as ``unknown'', but without providing category-specific semantics. In this paper, we advance the field by introducing the Open-Vocabulary Audio-Visual Event Localization (OV-AVEL)","authors_text":"Dan Guo, Jingjing Hu, Jinxing Zhou, Meng Wang, Ruohao Guo, Xiaojun Chang, Yiran Zhong, Yuxin Mao","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-18T04:35:20Z","title":"Towards Open-Vocabulary Audio-Visual Event Localization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11278","kind":"arxiv","version":3},"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:aa7562e93ce41a9528b1a0c5132ed88bf51fb04572904279165d878cfdce8b66","target":"record","created_at":"2026-07-05T10:28:26Z","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":"00db3541f7d980a60dfb4d06295a2d72a1ccb0bc680b69967c3de9f5c1a05a8c","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-18T04:35:20Z","title_canon_sha256":"e9f5590f5282cd0f1e95364667c12c22da092e61e7689949776b888bf00e1552"},"schema_version":"1.0","source":{"id":"2411.11278","kind":"arxiv","version":3}},"canonical_sha256":"b89b2665d7e0ec97ed28df153dbd8d8ff5a84d294755533c9bad727692f20055","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b89b2665d7e0ec97ed28df153dbd8d8ff5a84d294755533c9bad727692f20055","first_computed_at":"2026-07-05T10:28:26.460490Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:28:26.460490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aBKthAf+ng7H0McQrIIJYCgO0iDtQvMxrYmGALMYc/oSzioSPnriySPvO7ObaeHWcJEZ1W6OO4eEZ0+nhQ0kCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:28:26.460998Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.11278","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa7562e93ce41a9528b1a0c5132ed88bf51fb04572904279165d878cfdce8b66","sha256:b6607686f7dd73a2b806c4223e7dd1fa4d208f1d9c2009461beab6a57f78b624"],"state_sha256":"556688d97c6ce743ee7fcafe403f07e44d62736c62447234596cc08eb3667662"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1aRc64xdFTOkIgghrJMZVjHmSOS4n8y7IFWZ285SO6mLsnJrDjItB7zQXBxefjtIMPgOkX9k67FBGKKSrtXrBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T02:41:13.666192Z","bundle_sha256":"7204e81cb4a8ef2438e372afad892b2a1282e22dbb415a96be22439e161a4505"}}