{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:F26ZVH2NHT5GDHBWPFVVCE5UGF","short_pith_number":"pith:F26ZVH2N","schema_version":"1.0","canonical_sha256":"2ebd9a9f4d3cfa619c36796b5113b4316ddb49f26cf2a38182f159887b03b9b4","source":{"kind":"arxiv","id":"2608.02673","version":1},"attestation_state":"computed","paper":{"title":"dots.tts.edit: Precisely Controlled Speech Editing with a Continuous Autoregressive Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bohan Li, Colin Zhang, Da Zheng, Hankun Wang, Jing Peng, Kai Yu, Shi Lian, Xiaoyu Gu","submitted_at":"2026-08-02T15:03:37Z","abstract_excerpt":"Speech editing for content creation requires precise control over both what an edit should do and where it should apply. Free-form natural language provides a flexible interface for expressing edit requests, but its ambiguity may leave the intended operation, parameters, or target region underspecified. We study a precise and explicit interface for speech editing: a transcript-grounded structural edit instruction with XML-style tags explicitly specifies typed operations and localizes them to transcript spans or boundaries. This semantic timeline avoids explicit timestamp alignment and provides"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.02673","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-08-02T15:03:37Z","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"title_canon_sha256":"bdf3676272fce442b4b08d0e1f6f60e70ae11785d4d3fe5ace23472637bbde53","abstract_canon_sha256":"5cdfd1eececcedb0c2499622abb19a9cc2e5ea2e2cae3fee4438a5a09b524a40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T00:38:49.718689Z","signature_b64":"wpfYkVI2wkB9365HIE8H/Jvoy/uaQ2RDzzYcxyviDwggY7TeE8M9JkmKJv7n6OODarVO9vJngtLtXYLEYapFDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ebd9a9f4d3cfa619c36796b5113b4316ddb49f26cf2a38182f159887b03b9b4","last_reissued_at":"2026-08-05T00:38:49.716270Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T00:38:49.716270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"dots.tts.edit: Precisely Controlled Speech Editing with a Continuous Autoregressive Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bohan Li, Colin Zhang, Da Zheng, Hankun Wang, Jing Peng, Kai Yu, Shi Lian, Xiaoyu Gu","submitted_at":"2026-08-02T15:03:37Z","abstract_excerpt":"Speech editing for content creation requires precise control over both what an edit should do and where it should apply. Free-form natural language provides a flexible interface for expressing edit requests, but its ambiguity may leave the intended operation, parameters, or target region underspecified. We study a precise and explicit interface for speech editing: a transcript-grounded structural edit instruction with XML-style tags explicitly specifies typed operations and localizes them to transcript spans or boundaries. This semantic timeline avoids explicit timestamp alignment and provides"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02673","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/2608.02673/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.02673","created_at":"2026-08-05T00:38:49.717115+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.02673v1","created_at":"2026-08-05T00:38:49.717115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02673","created_at":"2026-08-05T00:38:49.717115+00:00"},{"alias_kind":"pith_short_12","alias_value":"F26ZVH2NHT5G","created_at":"2026-08-05T00:38:49.717115+00:00"},{"alias_kind":"pith_short_16","alias_value":"F26ZVH2NHT5GDHBW","created_at":"2026-08-05T00:38:49.717115+00:00"},{"alias_kind":"pith_short_8","alias_value":"F26ZVH2N","created_at":"2026-08-05T00:38:49.717115+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F26ZVH2NHT5GDHBWPFVVCE5UGF","json":"https://pith.science/pith/F26ZVH2NHT5GDHBWPFVVCE5UGF.json","graph_json":"https://pith.science/api/pith-number/F26ZVH2NHT5GDHBWPFVVCE5UGF/graph.json","events_json":"https://pith.science/api/pith-number/F26ZVH2NHT5GDHBWPFVVCE5UGF/events.json","paper":"https://pith.science/paper/F26ZVH2N"},"agent_actions":{"view_html":"https://pith.science/pith/F26ZVH2NHT5GDHBWPFVVCE5UGF","download_json":"https://pith.science/pith/F26ZVH2NHT5GDHBWPFVVCE5UGF.json","view_paper":"https://pith.science/paper/F26ZVH2N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.02673&json=true","fetch_graph":"https://pith.science/api/pith-number/F26ZVH2NHT5GDHBWPFVVCE5UGF/graph.json","fetch_events":"https://pith.science/api/pith-number/F26ZVH2NHT5GDHBWPFVVCE5UGF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F26ZVH2NHT5GDHBWPFVVCE5UGF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F26ZVH2NHT5GDHBWPFVVCE5UGF/action/storage_attestation","attest_author":"https://pith.science/pith/F26ZVH2NHT5GDHBWPFVVCE5UGF/action/author_attestation","sign_citation":"https://pith.science/pith/F26ZVH2NHT5GDHBWPFVVCE5UGF/action/citation_signature","submit_replication":"https://pith.science/pith/F26ZVH2NHT5GDHBWPFVVCE5UGF/action/replication_record"}},"created_at":"2026-08-05T00:38:49.717115+00:00","updated_at":"2026-08-05T00:38:49.717115+00:00"}