{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:N7JU6PYUNLY2KWFTGBKTLPVJ6R","short_pith_number":"pith:N7JU6PYU","canonical_record":{"source":{"id":"2508.09389","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-08-12T23:12:18Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"d5fe970aaa3ad20c652ee4749ec211e0a3520e6fd9527d5937ca06e6de7d3cb7","abstract_canon_sha256":"1acb7532eb7fd6dabb199e77fb200022832eb587dffb9fff95a57218e4d72475"},"schema_version":"1.0"},"canonical_sha256":"6fd34f3f146af1a558b3305535bea9f46600aeda9daa418b869a09a73df6ba64","source":{"kind":"arxiv","id":"2508.09389","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.09389","created_at":"2026-07-05T11:53:13Z"},{"alias_kind":"arxiv_version","alias_value":"2508.09389v1","created_at":"2026-07-05T11:53:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09389","created_at":"2026-07-05T11:53:13Z"},{"alias_kind":"pith_short_12","alias_value":"N7JU6PYUNLY2","created_at":"2026-07-05T11:53:13Z"},{"alias_kind":"pith_short_16","alias_value":"N7JU6PYUNLY2KWFT","created_at":"2026-07-05T11:53:13Z"},{"alias_kind":"pith_short_8","alias_value":"N7JU6PYU","created_at":"2026-07-05T11:53:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:N7JU6PYUNLY2KWFTGBKTLPVJ6R","target":"record","payload":{"canonical_record":{"source":{"id":"2508.09389","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-08-12T23:12:18Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"d5fe970aaa3ad20c652ee4749ec211e0a3520e6fd9527d5937ca06e6de7d3cb7","abstract_canon_sha256":"1acb7532eb7fd6dabb199e77fb200022832eb587dffb9fff95a57218e4d72475"},"schema_version":"1.0"},"canonical_sha256":"6fd34f3f146af1a558b3305535bea9f46600aeda9daa418b869a09a73df6ba64","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:13.924538Z","signature_b64":"SiTo5zirhYRXVvwo9eTxiqp59dfDGYyL8M7qw7gMig6lhDiLgqp7ZP/QMXqXPtNv4ACFqHsW6ziZWf7zujy6DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fd34f3f146af1a558b3305535bea9f46600aeda9daa418b869a09a73df6ba64","last_reissued_at":"2026-07-05T11:53:13.924021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:13.924021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.09389","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":"2026-07-05T11:53:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hd2kamDNdVC154f5abrOuYCIi5d87L03nZPyRLuElSpWLKW4E2a9ke0s9OGmAEcvf3gyaTdRda4MXDLnOCMSAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T16:34:25.617596Z"},"content_sha256":"7c728ad4aacd92cd0418b0ed8d0acb287c6081535a8d379fc433447098fcc19d","schema_version":"1.0","event_id":"sha256:7c728ad4aacd92cd0418b0ed8d0acb287c6081535a8d379fc433447098fcc19d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:N7JU6PYUNLY2KWFTGBKTLPVJ6R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ProMode: A Speech Prosody Model Conditioned on Acoustic and Textual Inputs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Abeer Alwan, Eray Eren, Hyeongwoo Kim, Pablo Garrido, Qingju Liu","submitted_at":"2025-08-12T23:12:18Z","abstract_excerpt":"Prosody conveys rich emotional and semantic information of the speech signal as well as individual idiosyncrasies. We propose a stand-alone model that maps text-to-prosodic features such as F0 and energy and can be used in downstream tasks such as TTS. The ProMode encoder takes as input acoustic features and time-aligned textual content, both are partially masked, and obtains a fixed-length latent prosodic embedding. The decoder predicts acoustics in the masked region using both the encoded prosody input and unmasked textual content. Trained on the GigaSpeech dataset, we compare our method wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09389","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/2508.09389/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":"2026-07-05T11:53:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZaRJRjFydmW+DuEkFPA45zj9BfwvSWn3uK8S+nsecMBwa49VLvJjsGxrr1FQjIZAjlnm6GUk5MUIOaRX6dyOAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T16:34:25.618105Z"},"content_sha256":"771b8b2e9ed8637ae72f17992b4c00bd154c98a8de8a08bdd68e133b9983dc82","schema_version":"1.0","event_id":"sha256:771b8b2e9ed8637ae72f17992b4c00bd154c98a8de8a08bdd68e133b9983dc82"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N7JU6PYUNLY2KWFTGBKTLPVJ6R/bundle.json","state_url":"https://pith.science/pith/N7JU6PYUNLY2KWFTGBKTLPVJ6R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N7JU6PYUNLY2KWFTGBKTLPVJ6R/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":"2026-08-15T16:34:25Z","links":{"resolver":"https://pith.science/pith/N7JU6PYUNLY2KWFTGBKTLPVJ6R","bundle":"https://pith.science/pith/N7JU6PYUNLY2KWFTGBKTLPVJ6R/bundle.json","state":"https://pith.science/pith/N7JU6PYUNLY2KWFTGBKTLPVJ6R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N7JU6PYUNLY2KWFTGBKTLPVJ6R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:N7JU6PYUNLY2KWFTGBKTLPVJ6R","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":"1acb7532eb7fd6dabb199e77fb200022832eb587dffb9fff95a57218e4d72475","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-08-12T23:12:18Z","title_canon_sha256":"d5fe970aaa3ad20c652ee4749ec211e0a3520e6fd9527d5937ca06e6de7d3cb7"},"schema_version":"1.0","source":{"id":"2508.09389","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.09389","created_at":"2026-07-05T11:53:13Z"},{"alias_kind":"arxiv_version","alias_value":"2508.09389v1","created_at":"2026-07-05T11:53:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09389","created_at":"2026-07-05T11:53:13Z"},{"alias_kind":"pith_short_12","alias_value":"N7JU6PYUNLY2","created_at":"2026-07-05T11:53:13Z"},{"alias_kind":"pith_short_16","alias_value":"N7JU6PYUNLY2KWFT","created_at":"2026-07-05T11:53:13Z"},{"alias_kind":"pith_short_8","alias_value":"N7JU6PYU","created_at":"2026-07-05T11:53:13Z"}],"graph_snapshots":[{"event_id":"sha256:771b8b2e9ed8637ae72f17992b4c00bd154c98a8de8a08bdd68e133b9983dc82","target":"graph","created_at":"2026-07-05T11:53:13Z","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/2508.09389/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prosody conveys rich emotional and semantic information of the speech signal as well as individual idiosyncrasies. We propose a stand-alone model that maps text-to-prosodic features such as F0 and energy and can be used in downstream tasks such as TTS. The ProMode encoder takes as input acoustic features and time-aligned textual content, both are partially masked, and obtains a fixed-length latent prosodic embedding. The decoder predicts acoustics in the masked region using both the encoded prosody input and unmasked textual content. Trained on the GigaSpeech dataset, we compare our method wit","authors_text":"Abeer Alwan, Eray Eren, Hyeongwoo Kim, Pablo Garrido, Qingju Liu","cross_cats":["cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-08-12T23:12:18Z","title":"ProMode: A Speech Prosody Model Conditioned on Acoustic and Textual Inputs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09389","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":"sha256:7c728ad4aacd92cd0418b0ed8d0acb287c6081535a8d379fc433447098fcc19d","target":"record","created_at":"2026-07-05T11:53:13Z","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":"1acb7532eb7fd6dabb199e77fb200022832eb587dffb9fff95a57218e4d72475","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-08-12T23:12:18Z","title_canon_sha256":"d5fe970aaa3ad20c652ee4749ec211e0a3520e6fd9527d5937ca06e6de7d3cb7"},"schema_version":"1.0","source":{"id":"2508.09389","kind":"arxiv","version":1}},"canonical_sha256":"6fd34f3f146af1a558b3305535bea9f46600aeda9daa418b869a09a73df6ba64","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6fd34f3f146af1a558b3305535bea9f46600aeda9daa418b869a09a73df6ba64","first_computed_at":"2026-07-05T11:53:13.924021Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:53:13.924021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SiTo5zirhYRXVvwo9eTxiqp59dfDGYyL8M7qw7gMig6lhDiLgqp7ZP/QMXqXPtNv4ACFqHsW6ziZWf7zujy6DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:53:13.924538Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.09389","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c728ad4aacd92cd0418b0ed8d0acb287c6081535a8d379fc433447098fcc19d","sha256:771b8b2e9ed8637ae72f17992b4c00bd154c98a8de8a08bdd68e133b9983dc82"],"state_sha256":"141c6cc9e293ef0eb7230a2cec64b5211c1c9d1169f6aba047d7ed7f801ee9e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XVdmDi5yyO1p6pwvbOIVQa7xl96e2wOAA0PxtFxDqUG/cMwuD4D89hz7fEi0zfiAwLqonpKw8XE1iU1ge9WLDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T16:34:25.621479Z","bundle_sha256":"ec9ac80ba746457df595e59b0e91f2b34cd8500fde7520d3ccd50098cafb85d1"}}