{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XCV47KUP226FUYRT4CMJJQYEDF","short_pith_number":"pith:XCV47KUP","canonical_record":{"source":{"id":"2607.03670","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-07-04T02:50:05Z","cross_cats_sorted":["eess.SP"],"title_canon_sha256":"f871ec38104685bac4fad9b090490cf59512b4c5b60318002d62ae0a9603d979","abstract_canon_sha256":"661b125d0fe9e73e005e3a18bf34e5c02cb8a7247f60f6f929f857a9c4da10b2"},"schema_version":"1.0"},"canonical_sha256":"b8abcfaa8fd6bc5a6233e09894c304196128ce3885d7dc7941ab91bf5ed3517d","source":{"kind":"arxiv","id":"2607.03670","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.03670","created_at":"2026-07-07T02:18:00Z"},{"alias_kind":"arxiv_version","alias_value":"2607.03670v1","created_at":"2026-07-07T02:18:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03670","created_at":"2026-07-07T02:18:00Z"},{"alias_kind":"pith_short_12","alias_value":"XCV47KUP226F","created_at":"2026-07-07T02:18:00Z"},{"alias_kind":"pith_short_16","alias_value":"XCV47KUP226FUYRT","created_at":"2026-07-07T02:18:00Z"},{"alias_kind":"pith_short_8","alias_value":"XCV47KUP","created_at":"2026-07-07T02:18:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XCV47KUP226FUYRT4CMJJQYEDF","target":"record","payload":{"canonical_record":{"source":{"id":"2607.03670","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-07-04T02:50:05Z","cross_cats_sorted":["eess.SP"],"title_canon_sha256":"f871ec38104685bac4fad9b090490cf59512b4c5b60318002d62ae0a9603d979","abstract_canon_sha256":"661b125d0fe9e73e005e3a18bf34e5c02cb8a7247f60f6f929f857a9c4da10b2"},"schema_version":"1.0"},"canonical_sha256":"b8abcfaa8fd6bc5a6233e09894c304196128ce3885d7dc7941ab91bf5ed3517d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:18:00.825857Z","signature_b64":"TWVdcUtTbKMWesKHpLO2jIYVIhBUtW8CUb2Q0LMvaRRJOirZN/9eNU7w4cy0Of+4JsvsGM2ayw5hEkEKpqI7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8abcfaa8fd6bc5a6233e09894c304196128ce3885d7dc7941ab91bf5ed3517d","last_reissued_at":"2026-07-07T02:18:00.824859Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:18:00.824859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.03670","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":"2026-07-07T02:18:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tCzTcS66yxzNvREAM5j3SiehZMHnIb/HKxUHbo2Rq4ia8nTqFOTroOCRqqd1C6tp+6GNeYdbA5OERODjsE5AAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T08:51:14.756762Z"},"content_sha256":"f656cd87eef50aea940fc941614d81388448b951654d792e68ff0d7d205d3bdc","schema_version":"1.0","event_id":"sha256:f656cd87eef50aea940fc941614d81388448b951654d792e68ff0d7d205d3bdc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XCV47KUP226FUYRT4CMJJQYEDF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CHILDES-Aligned: A Curated Children's Speech Dataset via Multi-Model Timestamp Ensembling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"eess.AS","authors_text":"Brian Kingsbury, Dancheng Liu, Haolong Zheng, Jinjun Xiong, Mark A. Hasegawa-Johnson, Samuel Thomas, Vishal Sunder, Xinyu Liang, Yuanzhuo Hu, Zhizheng Wu","submitted_at":"2026-07-04T02:50:05Z","abstract_excerpt":"CHILDES is a large-scale child speech corpus containing long-form recordings of naturalistic child-adult interactions, making it a valuable resource for studying child speech and language development. However, utterance-level timestamps provided in this corpus are often noisy, incomplete, or misaligned with the audio. As a result, utterances cannot always be reliably localized within long recordings, which limits the direct use of these data for training and evaluating speech models. In this work, we propose BEACON (Boundary Estimation via Alignment CONsensus), an ensemble timestamp-curation f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03670","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/2607.03670/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":"2026-07-07T02:18:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bQap2PxrGvdxCv/mBJjS+i6oXiXSO+yhyFIpfn8og/NlIF22uxO33STEUrQrzUQHSEuC/jd2jQyV5yn2F/o3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T08:51:14.757119Z"},"content_sha256":"f7ecab3d611538d9e0805fbb18b0217e27d19c23b7a59779f69daf2bccbd9941","schema_version":"1.0","event_id":"sha256:f7ecab3d611538d9e0805fbb18b0217e27d19c23b7a59779f69daf2bccbd9941"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XCV47KUP226FUYRT4CMJJQYEDF/bundle.json","state_url":"https://pith.science/pith/XCV47KUP226FUYRT4CMJJQYEDF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XCV47KUP226FUYRT4CMJJQYEDF/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":"2026-07-22T08:51:14Z","links":{"resolver":"https://pith.science/pith/XCV47KUP226FUYRT4CMJJQYEDF","bundle":"https://pith.science/pith/XCV47KUP226FUYRT4CMJJQYEDF/bundle.json","state":"https://pith.science/pith/XCV47KUP226FUYRT4CMJJQYEDF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XCV47KUP226FUYRT4CMJJQYEDF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XCV47KUP226FUYRT4CMJJQYEDF","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":"661b125d0fe9e73e005e3a18bf34e5c02cb8a7247f60f6f929f857a9c4da10b2","cross_cats_sorted":["eess.SP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-07-04T02:50:05Z","title_canon_sha256":"f871ec38104685bac4fad9b090490cf59512b4c5b60318002d62ae0a9603d979"},"schema_version":"1.0","source":{"id":"2607.03670","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.03670","created_at":"2026-07-07T02:18:00Z"},{"alias_kind":"arxiv_version","alias_value":"2607.03670v1","created_at":"2026-07-07T02:18:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03670","created_at":"2026-07-07T02:18:00Z"},{"alias_kind":"pith_short_12","alias_value":"XCV47KUP226F","created_at":"2026-07-07T02:18:00Z"},{"alias_kind":"pith_short_16","alias_value":"XCV47KUP226FUYRT","created_at":"2026-07-07T02:18:00Z"},{"alias_kind":"pith_short_8","alias_value":"XCV47KUP","created_at":"2026-07-07T02:18:00Z"}],"graph_snapshots":[{"event_id":"sha256:f7ecab3d611538d9e0805fbb18b0217e27d19c23b7a59779f69daf2bccbd9941","target":"graph","created_at":"2026-07-07T02:18:00Z","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/2607.03670/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"CHILDES is a large-scale child speech corpus containing long-form recordings of naturalistic child-adult interactions, making it a valuable resource for studying child speech and language development. However, utterance-level timestamps provided in this corpus are often noisy, incomplete, or misaligned with the audio. As a result, utterances cannot always be reliably localized within long recordings, which limits the direct use of these data for training and evaluating speech models. In this work, we propose BEACON (Boundary Estimation via Alignment CONsensus), an ensemble timestamp-curation f","authors_text":"Brian Kingsbury, Dancheng Liu, Haolong Zheng, Jinjun Xiong, Mark A. Hasegawa-Johnson, Samuel Thomas, Vishal Sunder, Xinyu Liang, Yuanzhuo Hu, Zhizheng Wu","cross_cats":["eess.SP"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-07-04T02:50:05Z","title":"CHILDES-Aligned: A Curated Children's Speech Dataset via Multi-Model Timestamp Ensembling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03670","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:f656cd87eef50aea940fc941614d81388448b951654d792e68ff0d7d205d3bdc","target":"record","created_at":"2026-07-07T02:18:00Z","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":"661b125d0fe9e73e005e3a18bf34e5c02cb8a7247f60f6f929f857a9c4da10b2","cross_cats_sorted":["eess.SP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-07-04T02:50:05Z","title_canon_sha256":"f871ec38104685bac4fad9b090490cf59512b4c5b60318002d62ae0a9603d979"},"schema_version":"1.0","source":{"id":"2607.03670","kind":"arxiv","version":1}},"canonical_sha256":"b8abcfaa8fd6bc5a6233e09894c304196128ce3885d7dc7941ab91bf5ed3517d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b8abcfaa8fd6bc5a6233e09894c304196128ce3885d7dc7941ab91bf5ed3517d","first_computed_at":"2026-07-07T02:18:00.824859Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:18:00.824859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TWVdcUtTbKMWesKHpLO2jIYVIhBUtW8CUb2Q0LMvaRRJOirZN/9eNU7w4cy0Of+4JsvsGM2ayw5hEkEKpqI7Ag==","signature_status":"signed_v1","signed_at":"2026-07-07T02:18:00.825857Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.03670","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f656cd87eef50aea940fc941614d81388448b951654d792e68ff0d7d205d3bdc","sha256:f7ecab3d611538d9e0805fbb18b0217e27d19c23b7a59779f69daf2bccbd9941"],"state_sha256":"b971ce5ad3183a30a16fcee585af76a5c436d5e6700aa58e55c284d355644354"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NQjuSClwhqIE0JyNxOobzGlrpv6F5PK9yC40ElmD6QueM2rvAxL80SwZEktqRlWP7Hm77npY9o2EuAK58xJIBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-22T08:51:14.759249Z","bundle_sha256":"59ef0ede24f3651c91fc21b574b6961923930e814052989fd6ba411acc2fa297"}}