{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ZJATMCK5KBSFJVIC4QC52LEUHD","short_pith_number":"pith:ZJATMCK5","canonical_record":{"source":{"id":"2206.13865","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2022-06-28T10:02:41Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"a9475f4634ae81a13d88a0d1f1046e1aef931d45eacd77658de0a1e702d65ee4","abstract_canon_sha256":"530f908558c4a7e7edff4d8da1e7585cfd7965ad8f38fda11eaccd20d55364d9"},"schema_version":"1.0"},"canonical_sha256":"ca4136095d506454d502e405dd2c9438dd43739e68688e2d816f9fba2a413085","source":{"kind":"arxiv","id":"2206.13865","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.13865","created_at":"2026-07-05T04:35:26Z"},{"alias_kind":"arxiv_version","alias_value":"2206.13865v1","created_at":"2026-07-05T04:35:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.13865","created_at":"2026-07-05T04:35:26Z"},{"alias_kind":"pith_short_12","alias_value":"ZJATMCK5KBSF","created_at":"2026-07-05T04:35:26Z"},{"alias_kind":"pith_short_16","alias_value":"ZJATMCK5KBSFJVIC","created_at":"2026-07-05T04:35:26Z"},{"alias_kind":"pith_short_8","alias_value":"ZJATMCK5","created_at":"2026-07-05T04:35:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ZJATMCK5KBSFJVIC4QC52LEUHD","target":"record","payload":{"canonical_record":{"source":{"id":"2206.13865","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2022-06-28T10:02:41Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"a9475f4634ae81a13d88a0d1f1046e1aef931d45eacd77658de0a1e702d65ee4","abstract_canon_sha256":"530f908558c4a7e7edff4d8da1e7585cfd7965ad8f38fda11eaccd20d55364d9"},"schema_version":"1.0"},"canonical_sha256":"ca4136095d506454d502e405dd2c9438dd43739e68688e2d816f9fba2a413085","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:35:26.359599Z","signature_b64":"TX3ZIb9oZmX1e3z0AcYhaoziMaISFuD9AKQVvE9XS57TCxgNhJIuGQ3aMZ3W6SN9wM4CyWp1MMd7lDqdMhnzBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca4136095d506454d502e405dd2c9438dd43739e68688e2d816f9fba2a413085","last_reissued_at":"2026-07-05T04:35:26.359127Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:35:26.359127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.13865","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":"2026-07-05T04:35:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+20px9cPrSF6YD6XxpBx/i3Wy+HWKI9bb/aypAezKbIG15G8HjjkzVaDcIqHBw+PDP3d9KBjczu6rarsSAXYCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:08:31.373116Z"},"content_sha256":"de4eb8331bbc49b4d84371b96cf20574e5efc271f1bf2d8450f97f1c52904faf","schema_version":"1.0","event_id":"sha256:de4eb8331bbc49b4d84371b96cf20574e5efc271f1bf2d8450f97f1c52904faf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ZJATMCK5KBSFJVIC4QC52LEUHD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RetrieverTTS: Modeling Decomposed Factors for Text-Based Speech Insertion","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chong Luo, Chuanxin Tang, Dacheng Yin, Sheng Zhao, Xiaoqiang Wang, Yanqing Liu, Yucheng Zhao, Zhiwei Xiong, Zhiyuan Zhao","submitted_at":"2022-06-28T10:02:41Z","abstract_excerpt":"This paper proposes a new \"decompose-and-edit\" paradigm for the text-based speech insertion task that facilitates arbitrary-length speech insertion and even full sentence generation. In the proposed paradigm, global and local factors in speech are explicitly decomposed and separately manipulated to achieve high speaker similarity and continuous prosody. Specifically, we proposed to represent the global factors by multiple tokens, which are extracted by cross-attention operation and then injected back by link-attention operation. Due to the rich representation of global factors, we manage to ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.13865","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/2206.13865/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":"2026-07-05T04:35:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t3xRKb5rgllEYQqumHJ5vnFEYhzpL5DXdmWGyhU6FIA6zcTSwj551xJxOSgm/1jvNcpoRDl+8K7EYQAOwZNmCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:08:31.373442Z"},"content_sha256":"0f119572e78df81232fbf5309caeffbba238af73a68c1921af2aea7c76548d59","schema_version":"1.0","event_id":"sha256:0f119572e78df81232fbf5309caeffbba238af73a68c1921af2aea7c76548d59"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZJATMCK5KBSFJVIC4QC52LEUHD/bundle.json","state_url":"https://pith.science/pith/ZJATMCK5KBSFJVIC4QC52LEUHD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZJATMCK5KBSFJVIC4QC52LEUHD/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":"2026-08-05T06:08:31Z","links":{"resolver":"https://pith.science/pith/ZJATMCK5KBSFJVIC4QC52LEUHD","bundle":"https://pith.science/pith/ZJATMCK5KBSFJVIC4QC52LEUHD/bundle.json","state":"https://pith.science/pith/ZJATMCK5KBSFJVIC4QC52LEUHD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZJATMCK5KBSFJVIC4QC52LEUHD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ZJATMCK5KBSFJVIC4QC52LEUHD","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":"530f908558c4a7e7edff4d8da1e7585cfd7965ad8f38fda11eaccd20d55364d9","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2022-06-28T10:02:41Z","title_canon_sha256":"a9475f4634ae81a13d88a0d1f1046e1aef931d45eacd77658de0a1e702d65ee4"},"schema_version":"1.0","source":{"id":"2206.13865","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.13865","created_at":"2026-07-05T04:35:26Z"},{"alias_kind":"arxiv_version","alias_value":"2206.13865v1","created_at":"2026-07-05T04:35:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.13865","created_at":"2026-07-05T04:35:26Z"},{"alias_kind":"pith_short_12","alias_value":"ZJATMCK5KBSF","created_at":"2026-07-05T04:35:26Z"},{"alias_kind":"pith_short_16","alias_value":"ZJATMCK5KBSFJVIC","created_at":"2026-07-05T04:35:26Z"},{"alias_kind":"pith_short_8","alias_value":"ZJATMCK5","created_at":"2026-07-05T04:35:26Z"}],"graph_snapshots":[{"event_id":"sha256:0f119572e78df81232fbf5309caeffbba238af73a68c1921af2aea7c76548d59","target":"graph","created_at":"2026-07-05T04:35:26Z","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/2206.13865/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes a new \"decompose-and-edit\" paradigm for the text-based speech insertion task that facilitates arbitrary-length speech insertion and even full sentence generation. In the proposed paradigm, global and local factors in speech are explicitly decomposed and separately manipulated to achieve high speaker similarity and continuous prosody. Specifically, we proposed to represent the global factors by multiple tokens, which are extracted by cross-attention operation and then injected back by link-attention operation. Due to the rich representation of global factors, we manage to ac","authors_text":"Chong Luo, Chuanxin Tang, Dacheng Yin, Sheng Zhao, Xiaoqiang Wang, Yanqing Liu, Yucheng Zhao, Zhiwei Xiong, Zhiyuan Zhao","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2022-06-28T10:02:41Z","title":"RetrieverTTS: Modeling Decomposed Factors for Text-Based Speech Insertion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.13865","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:de4eb8331bbc49b4d84371b96cf20574e5efc271f1bf2d8450f97f1c52904faf","target":"record","created_at":"2026-07-05T04:35:26Z","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":"530f908558c4a7e7edff4d8da1e7585cfd7965ad8f38fda11eaccd20d55364d9","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2022-06-28T10:02:41Z","title_canon_sha256":"a9475f4634ae81a13d88a0d1f1046e1aef931d45eacd77658de0a1e702d65ee4"},"schema_version":"1.0","source":{"id":"2206.13865","kind":"arxiv","version":1}},"canonical_sha256":"ca4136095d506454d502e405dd2c9438dd43739e68688e2d816f9fba2a413085","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca4136095d506454d502e405dd2c9438dd43739e68688e2d816f9fba2a413085","first_computed_at":"2026-07-05T04:35:26.359127Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:35:26.359127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TX3ZIb9oZmX1e3z0AcYhaoziMaISFuD9AKQVvE9XS57TCxgNhJIuGQ3aMZ3W6SN9wM4CyWp1MMd7lDqdMhnzBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:35:26.359599Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.13865","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de4eb8331bbc49b4d84371b96cf20574e5efc271f1bf2d8450f97f1c52904faf","sha256:0f119572e78df81232fbf5309caeffbba238af73a68c1921af2aea7c76548d59"],"state_sha256":"a06aacb7dd273a0e53989c90f75ec4a68ec6fcb3d76bc70dada4b99539c14689"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2dBWNSLxumgRkj/v3Mt1PGiwxPMUcepwS4aPbmDazWMKiGcl41qJ5lv1/Le0Il7aLkuFlChlO8jl4c/DYKgJDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T06:08:31.376492Z","bundle_sha256":"906ab32d71c31e62fcc19c629903109a411f18e17dc2b0d5d3b51f77ca867776"}}