{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NLU4LZZ6RMAUPA5BBNJTEHEZFR","short_pith_number":"pith:NLU4LZZ6","canonical_record":{"source":{"id":"2607.04383","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-05T16:22:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"95477fc5382b69716b0ab8888d004bf1d3a636dd560e6173fd076df00f8055e9","abstract_canon_sha256":"e86c6ea4dbe1ccb27e83c861bc49cdb9231da96cb158e0791058f20f0a616186"},"schema_version":"1.0"},"canonical_sha256":"6ae9c5e73e8b014783a10b53321c992c6da004667f9dceb65abe8073972081fc","source":{"kind":"arxiv","id":"2607.04383","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04383","created_at":"2026-07-07T02:19:15Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04383v1","created_at":"2026-07-07T02:19:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04383","created_at":"2026-07-07T02:19:15Z"},{"alias_kind":"pith_short_12","alias_value":"NLU4LZZ6RMAU","created_at":"2026-07-07T02:19:15Z"},{"alias_kind":"pith_short_16","alias_value":"NLU4LZZ6RMAUPA5B","created_at":"2026-07-07T02:19:15Z"},{"alias_kind":"pith_short_8","alias_value":"NLU4LZZ6","created_at":"2026-07-07T02:19:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NLU4LZZ6RMAUPA5BBNJTEHEZFR","target":"record","payload":{"canonical_record":{"source":{"id":"2607.04383","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-05T16:22:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"95477fc5382b69716b0ab8888d004bf1d3a636dd560e6173fd076df00f8055e9","abstract_canon_sha256":"e86c6ea4dbe1ccb27e83c861bc49cdb9231da96cb158e0791058f20f0a616186"},"schema_version":"1.0"},"canonical_sha256":"6ae9c5e73e8b014783a10b53321c992c6da004667f9dceb65abe8073972081fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:19:15.733621Z","signature_b64":"1w21PL/SWNPbCu/m05wS3q6KyaLQIZ5wRZIUSjFvyCxOA31RhugJoDk3NgtHcvReAc1Hxom94LEyr3VOfztUCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ae9c5e73e8b014783a10b53321c992c6da004667f9dceb65abe8073972081fc","last_reissued_at":"2026-07-07T02:19:15.732784Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:19:15.732784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.04383","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":"2026-07-07T02:19:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2TQ+FBTtvMwSeOvi5CEqEGW6JFVEuMp+IX6CI1z59PK2ZJ1+6VhgstyVBH3ACcoEkyS5dk4qhUzjcPYnQ5kKDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T20:37:27.120817Z"},"content_sha256":"f3524c84e27f616ec2c3c7875a3e802898d622bca89bf6d9c92fc1fc4c5af395","schema_version":"1.0","event_id":"sha256:f3524c84e27f616ec2c3c7875a3e802898d622bca89bf6d9c92fc1fc4c5af395"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NLU4LZZ6RMAUPA5BBNJTEHEZFR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Auto-AEG: Scalable Data Construction for Open-Vocabulary Audio Event Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Boyun Zhang, Dongjie Fu, Tao Jin, Tong Zhang, Wenhao Yan, Xize Cheng, Yongbo He, Zihan Zhang","submitted_at":"2026-07-05T16:22:14Z","abstract_excerpt":"Large Audio-Language Models (LALMs) reason fluently about sound yet struggle to localize precisely when events occur, while classical Sound Event Detection attains frame-level precision only over a closed label set. At the intersection of these paradigms lies the task of Open-Vocabulary Audio Event Grounding: predicting all time intervals of a target sound event described by an arbitrary natural language query. While this task is crucial for real-world audio understanding and LALM adaptation, it is bottlenecked by data scarcity. Few large-scale resources provide open-vocabulary onset/offset su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04383","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/2607.04383/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":"2026-07-07T02:19:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DN90I0x4zsCG8XKl37uC9MSWU9pcG3xHdtroWRIoXLJ+7NdG3q5EZ1rHLSIdXGDX/Sn49WqH2FhfAwUZGTXjCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T20:37:27.121246Z"},"content_sha256":"83131c1c74cb8cb63ece7450fdce6c26a5d32c42a58949ad5a291abd158454e9","schema_version":"1.0","event_id":"sha256:83131c1c74cb8cb63ece7450fdce6c26a5d32c42a58949ad5a291abd158454e9"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:NLU4LZZ6RMAUPA5BBNJTEHEZFR","target":"integrity","payload":{"note":"Identifier '10.1109/taslp.2020.3030497.url:https://doi.org/10.1109/taslp.2020.3030497' is syntactically valid but the DOI registry (doi.org) returned 404, and Crossref / OpenAlex / internal corpus also have no record. The cited work could not be located through any authoritative source.","snippet":"Qiuqiang Kong, Yin Cao, Turab Iqbal, Yuxuan Wang, Wenwu Wang, and Mark D. Plumbley. “PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition”. In: IEEE/ACM Trans. Audio, Speech and Lang. Proc.28 (Nov. 2020), pp. 28","arxiv_id":"2607.04383","detector":"doi_compliance","evidence":{"doi":"10.1109/taslp.2020.3030497.url:https://doi.org/10.1109/taslp.2020.3030497","arxiv_id":null,"ref_index":16,"raw_excerpt":"Qiuqiang Kong, Yin Cao, Turab Iqbal, Yuxuan Wang, Wenwu Wang, and Mark D. Plumbley. “PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition”. In: IEEE/ACM Trans. Audio, Speech and Lang. Proc.28 (Nov. 2020), pp. 2880–2894.issn: 2329-9290. doi:10.1109/TASLP.2020.3030497.url:https://doi.org/10.1109/TASLP.2020.3030497","verdict_class":"cross_source","checked_sources":["crossref_by_doi","openalex_by_doi","doi_org_head"]},"severity":"critical","ref_index":16,"audited_at":"2026-07-11T19:44:41.642241Z","event_type":"pith.integrity.v1","detected_doi":"10.1109/taslp.2020.3030497.url:https://doi.org/10.1109/taslp.2020.3030497","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"unresolvable_identifier","evidence_hash":"c1a1146789a5a11201964322e7996498b48967fcc2fe1bf387b57da1d35505b1","paper_version":1,"verdict_class":"cross_source","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":12256,"payload_sha256":"e2491f55dfdc1d4312684d2f7b527ca672ef1cd61925d2aa70fcb2d1a82d859b","signature_b64":"41fzFbWjH70LYnCLNLlCZBjGRSoF3bfXR2DsjjgJCV8UhOP7/vrZFVh1WmQ+/pX05Cpqwp3n3pj/dISvx27EBg==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-11T19:46:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gwU+i4eBEqp4/8Ekhiqo2ezN9sVSNhpNPvCXXKU3DI/y4haOEH1Zvfsz4OvSwe6SaGMkFBdS7Yx+QjQ2hvW0Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T20:37:27.122804Z"},"content_sha256":"1a7b28ca9f17c850fcc9ac9d18f7baeaa9fdda49f69dcf582c1c4cb1318afa9e","schema_version":"1.0","event_id":"sha256:1a7b28ca9f17c850fcc9ac9d18f7baeaa9fdda49f69dcf582c1c4cb1318afa9e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NLU4LZZ6RMAUPA5BBNJTEHEZFR/bundle.json","state_url":"https://pith.science/pith/NLU4LZZ6RMAUPA5BBNJTEHEZFR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NLU4LZZ6RMAUPA5BBNJTEHEZFR/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":"2026-08-19T20:37:27Z","links":{"resolver":"https://pith.science/pith/NLU4LZZ6RMAUPA5BBNJTEHEZFR","bundle":"https://pith.science/pith/NLU4LZZ6RMAUPA5BBNJTEHEZFR/bundle.json","state":"https://pith.science/pith/NLU4LZZ6RMAUPA5BBNJTEHEZFR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NLU4LZZ6RMAUPA5BBNJTEHEZFR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NLU4LZZ6RMAUPA5BBNJTEHEZFR","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e86c6ea4dbe1ccb27e83c861bc49cdb9231da96cb158e0791058f20f0a616186","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-05T16:22:14Z","title_canon_sha256":"95477fc5382b69716b0ab8888d004bf1d3a636dd560e6173fd076df00f8055e9"},"schema_version":"1.0","source":{"id":"2607.04383","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04383","created_at":"2026-07-07T02:19:15Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04383v1","created_at":"2026-07-07T02:19:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04383","created_at":"2026-07-07T02:19:15Z"},{"alias_kind":"pith_short_12","alias_value":"NLU4LZZ6RMAU","created_at":"2026-07-07T02:19:15Z"},{"alias_kind":"pith_short_16","alias_value":"NLU4LZZ6RMAUPA5B","created_at":"2026-07-07T02:19:15Z"},{"alias_kind":"pith_short_8","alias_value":"NLU4LZZ6","created_at":"2026-07-07T02:19:15Z"}],"graph_snapshots":[{"event_id":"sha256:83131c1c74cb8cb63ece7450fdce6c26a5d32c42a58949ad5a291abd158454e9","target":"graph","created_at":"2026-07-07T02:19:15Z","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/2607.04383/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Audio-Language Models (LALMs) reason fluently about sound yet struggle to localize precisely when events occur, while classical Sound Event Detection attains frame-level precision only over a closed label set. At the intersection of these paradigms lies the task of Open-Vocabulary Audio Event Grounding: predicting all time intervals of a target sound event described by an arbitrary natural language query. While this task is crucial for real-world audio understanding and LALM adaptation, it is bottlenecked by data scarcity. Few large-scale resources provide open-vocabulary onset/offset su","authors_text":"Boyun Zhang, Dongjie Fu, Tao Jin, Tong Zhang, Wenhao Yan, Xize Cheng, Yongbo He, Zihan Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-05T16:22:14Z","title":"Auto-AEG: Scalable Data Construction for Open-Vocabulary Audio Event Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04383","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:f3524c84e27f616ec2c3c7875a3e802898d622bca89bf6d9c92fc1fc4c5af395","target":"record","created_at":"2026-07-07T02:19:15Z","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":"e86c6ea4dbe1ccb27e83c861bc49cdb9231da96cb158e0791058f20f0a616186","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-07-05T16:22:14Z","title_canon_sha256":"95477fc5382b69716b0ab8888d004bf1d3a636dd560e6173fd076df00f8055e9"},"schema_version":"1.0","source":{"id":"2607.04383","kind":"arxiv","version":1}},"canonical_sha256":"6ae9c5e73e8b014783a10b53321c992c6da004667f9dceb65abe8073972081fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ae9c5e73e8b014783a10b53321c992c6da004667f9dceb65abe8073972081fc","first_computed_at":"2026-07-07T02:19:15.732784Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:19:15.732784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1w21PL/SWNPbCu/m05wS3q6KyaLQIZ5wRZIUSjFvyCxOA31RhugJoDk3NgtHcvReAc1Hxom94LEyr3VOfztUCw==","signature_status":"signed_v1","signed_at":"2026-07-07T02:19:15.733621Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.04383","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3524c84e27f616ec2c3c7875a3e802898d622bca89bf6d9c92fc1fc4c5af395","sha256:83131c1c74cb8cb63ece7450fdce6c26a5d32c42a58949ad5a291abd158454e9","sha256:1a7b28ca9f17c850fcc9ac9d18f7baeaa9fdda49f69dcf582c1c4cb1318afa9e"],"state_sha256":"0e739a3ab036a923166ebdc6c9a0d661d7b9082bde4f5ba2eb0ad5b17bcafe9c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SvT57ntjrSjnSK6QPlEkkyDsQmzr58h+TB7FZtTi0hynJiuJfaCji5prFRBiY+knOs3KpOSgGKtmcfwWLCMECQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T20:37:27.124481Z","bundle_sha256":"44489e5412ebe5f25c979bed02a8dc7cbc9bb949a5e14dccf3c7e74a14e898c4"}}