{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:I5TRUSWQW5HU5AFKF5CASDJJVA","short_pith_number":"pith:I5TRUSWQ","canonical_record":{"source":{"id":"2606.07033","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-05T08:23:58Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a7c128c2a68eb7f37114820fcb31c999cd3b7075fcdbc3c499db7fe66e26fcec","abstract_canon_sha256":"221f1951ff9e627c6451e498d748089456439fd13a610a6f2af33adcb9e902a6"},"schema_version":"1.0"},"canonical_sha256":"47671a4ad0b74f4e80aa2f44090d29a82eca92453fc785b592b03dde06033826","source":{"kind":"arxiv","id":"2606.07033","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07033","created_at":"2026-06-08T01:04:42Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07033v1","created_at":"2026-06-08T01:04:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07033","created_at":"2026-06-08T01:04:42Z"},{"alias_kind":"pith_short_12","alias_value":"I5TRUSWQW5HU","created_at":"2026-06-08T01:04:42Z"},{"alias_kind":"pith_short_16","alias_value":"I5TRUSWQW5HU5AFK","created_at":"2026-06-08T01:04:42Z"},{"alias_kind":"pith_short_8","alias_value":"I5TRUSWQ","created_at":"2026-06-08T01:04:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:I5TRUSWQW5HU5AFKF5CASDJJVA","target":"record","payload":{"canonical_record":{"source":{"id":"2606.07033","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-05T08:23:58Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a7c128c2a68eb7f37114820fcb31c999cd3b7075fcdbc3c499db7fe66e26fcec","abstract_canon_sha256":"221f1951ff9e627c6451e498d748089456439fd13a610a6f2af33adcb9e902a6"},"schema_version":"1.0"},"canonical_sha256":"47671a4ad0b74f4e80aa2f44090d29a82eca92453fc785b592b03dde06033826","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:42.407727Z","signature_b64":"dvVyxE5yCLgz5E6hAWLEeNBO47sqVJkBuk+UmISqqGE0uh48W+rp7PhqNxUI4538Mb1W0vfOKfgJ6RcPMO+2DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47671a4ad0b74f4e80aa2f44090d29a82eca92453fc785b592b03dde06033826","last_reissued_at":"2026-06-08T01:04:42.406829Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:42.406829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.07033","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":"2026-06-08T01:04:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zE9zbIX8UdGikce5jorYNRXgTDfwgF0Eo3EJs3KCn61qVkgktb5E2Tdopx/9ReZOQYC3Ea97gpyZxeKK2E/hCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T13:40:35.049818Z"},"content_sha256":"ea16c9efd96f9a4d7c4d8bf2444d188e4a5854cef32031dbae8d30e03115e15c","schema_version":"1.0","event_id":"sha256:ea16c9efd96f9a4d7c4d8bf2444d188e4a5854cef32031dbae8d30e03115e15c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:I5TRUSWQW5HU5AFKF5CASDJJVA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical Semantic-Constrained Heterogeneous Graph for Audio-Visual Event Localization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Hengyu Man, Hongtao Chen, Ruyi Zhang, Wangmeng Zuo, Wenrui Li, Xiaopeng Fan, Zhe Yang","submitted_at":"2026-06-05T08:23:58Z","abstract_excerpt":"Open-vocabulary audio-visual event localization (OV-AVEL) jointly models audio-visual cues to recognize and temporally localize events, including categories unseen during training. Existing methods primarily learn joint audio-visual representations in Euclidean space, but still face two significant challenges. First, the lack of supervision signals for unseen categories makes it difficult to maintain audio-visual consistency across multiple temporal scales. Second, the lack of hierarchical constraints between segment- and video-level semantics prevents the model from establishing semantic cons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07033","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/2606.07033/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":"2026-06-08T01:04:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z2P1CvFqJyVrF+3XhhAaBc8jP4cYZKda+vb4vCzdceuZrTHiZN7x2ezcaG33VeaUZs/FR+dHTEnubtdCl03hDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T13:40:35.050193Z"},"content_sha256":"1eb8a975e2b07645f1e054879bcd3976eb684735d44a795b10c360f090964a18","schema_version":"1.0","event_id":"sha256:1eb8a975e2b07645f1e054879bcd3976eb684735d44a795b10c360f090964a18"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I5TRUSWQW5HU5AFKF5CASDJJVA/bundle.json","state_url":"https://pith.science/pith/I5TRUSWQW5HU5AFKF5CASDJJVA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I5TRUSWQW5HU5AFKF5CASDJJVA/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":"2026-06-30T13:40:35Z","links":{"resolver":"https://pith.science/pith/I5TRUSWQW5HU5AFKF5CASDJJVA","bundle":"https://pith.science/pith/I5TRUSWQW5HU5AFKF5CASDJJVA/bundle.json","state":"https://pith.science/pith/I5TRUSWQW5HU5AFKF5CASDJJVA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I5TRUSWQW5HU5AFKF5CASDJJVA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:I5TRUSWQW5HU5AFKF5CASDJJVA","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":"221f1951ff9e627c6451e498d748089456439fd13a610a6f2af33adcb9e902a6","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-05T08:23:58Z","title_canon_sha256":"a7c128c2a68eb7f37114820fcb31c999cd3b7075fcdbc3c499db7fe66e26fcec"},"schema_version":"1.0","source":{"id":"2606.07033","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07033","created_at":"2026-06-08T01:04:42Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07033v1","created_at":"2026-06-08T01:04:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07033","created_at":"2026-06-08T01:04:42Z"},{"alias_kind":"pith_short_12","alias_value":"I5TRUSWQW5HU","created_at":"2026-06-08T01:04:42Z"},{"alias_kind":"pith_short_16","alias_value":"I5TRUSWQW5HU5AFK","created_at":"2026-06-08T01:04:42Z"},{"alias_kind":"pith_short_8","alias_value":"I5TRUSWQ","created_at":"2026-06-08T01:04:42Z"}],"graph_snapshots":[{"event_id":"sha256:1eb8a975e2b07645f1e054879bcd3976eb684735d44a795b10c360f090964a18","target":"graph","created_at":"2026-06-08T01:04:42Z","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/2606.07033/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Open-vocabulary audio-visual event localization (OV-AVEL) jointly models audio-visual cues to recognize and temporally localize events, including categories unseen during training. Existing methods primarily learn joint audio-visual representations in Euclidean space, but still face two significant challenges. First, the lack of supervision signals for unseen categories makes it difficult to maintain audio-visual consistency across multiple temporal scales. Second, the lack of hierarchical constraints between segment- and video-level semantics prevents the model from establishing semantic cons","authors_text":"Hengyu Man, Hongtao Chen, Ruyi Zhang, Wangmeng Zuo, Wenrui Li, Xiaopeng Fan, Zhe Yang","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-05T08:23:58Z","title":"Hierarchical Semantic-Constrained Heterogeneous Graph for Audio-Visual Event Localization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07033","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:ea16c9efd96f9a4d7c4d8bf2444d188e4a5854cef32031dbae8d30e03115e15c","target":"record","created_at":"2026-06-08T01:04:42Z","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":"221f1951ff9e627c6451e498d748089456439fd13a610a6f2af33adcb9e902a6","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-05T08:23:58Z","title_canon_sha256":"a7c128c2a68eb7f37114820fcb31c999cd3b7075fcdbc3c499db7fe66e26fcec"},"schema_version":"1.0","source":{"id":"2606.07033","kind":"arxiv","version":1}},"canonical_sha256":"47671a4ad0b74f4e80aa2f44090d29a82eca92453fc785b592b03dde06033826","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"47671a4ad0b74f4e80aa2f44090d29a82eca92453fc785b592b03dde06033826","first_computed_at":"2026-06-08T01:04:42.406829Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:04:42.406829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dvVyxE5yCLgz5E6hAWLEeNBO47sqVJkBuk+UmISqqGE0uh48W+rp7PhqNxUI4538Mb1W0vfOKfgJ6RcPMO+2DQ==","signature_status":"signed_v1","signed_at":"2026-06-08T01:04:42.407727Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07033","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea16c9efd96f9a4d7c4d8bf2444d188e4a5854cef32031dbae8d30e03115e15c","sha256:1eb8a975e2b07645f1e054879bcd3976eb684735d44a795b10c360f090964a18"],"state_sha256":"c35a67aeed0cd54c1a28a79bf32d1f8b5443ea49fa9b42c1ad2027da18c2bce3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZpRsLiyBAZw0P+tv0Hbs8mEsrHc3BHqUPMSf2XcDkjAIbcWvLpXHcKDoeajE1CgPX+/D1UoyDrChAV30sWosBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T13:40:35.052152Z","bundle_sha256":"1e1289a67d447c6b2caff4b55163785c8ec69414d226121ae62b379859a78c58"}}