{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QFEHHBGWN5Z3JMO4FARG5IRNEU","short_pith_number":"pith:QFEHHBGW","canonical_record":{"source":{"id":"2507.20091","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-27T00:59:01Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"c6ea6bf497b3086936dbcd27e76babef35c2901268a6e952b2a8f05896bc425f","abstract_canon_sha256":"ca4c739f3311b6a99c9338c24791b74547dc09e8f24930928838a196b432409f"},"schema_version":"1.0"},"canonical_sha256":"81487384d66f73b4b1dc28226ea22d251049ebec8b936b9bb797aee2e31334cb","source":{"kind":"arxiv","id":"2507.20091","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.20091","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"arxiv_version","alias_value":"2507.20091v2","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20091","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"pith_short_12","alias_value":"QFEHHBGWN5Z3","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"pith_short_16","alias_value":"QFEHHBGWN5Z3JMO4","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"pith_short_8","alias_value":"QFEHHBGW","created_at":"2026-07-05T11:50:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QFEHHBGWN5Z3JMO4FARG5IRNEU","target":"record","payload":{"canonical_record":{"source":{"id":"2507.20091","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-27T00:59:01Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"c6ea6bf497b3086936dbcd27e76babef35c2901268a6e952b2a8f05896bc425f","abstract_canon_sha256":"ca4c739f3311b6a99c9338c24791b74547dc09e8f24930928838a196b432409f"},"schema_version":"1.0"},"canonical_sha256":"81487384d66f73b4b1dc28226ea22d251049ebec8b936b9bb797aee2e31334cb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:50:38.845501Z","signature_b64":"zphEK1yZaCkAigVCDtcIuhA6HUlqjMqnE4basBydgZLqngsayrUzauVyzlvs2nFYZK4qHxi8ac6746vJkaLeBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81487384d66f73b4b1dc28226ea22d251049ebec8b936b9bb797aee2e31334cb","last_reissued_at":"2026-07-05T11:50:38.845004Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:50:38.845004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.20091","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:50:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oKlEQDEgZndojmrhnETX8FzhhwD4mausy/vqi8ytFvBYZOZj0iCtdVi+K5vCOmoZDesGBpIlO8LOJyFrrHxXBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T18:26:40.187663Z"},"content_sha256":"dc96b019b3972b5f3e8a9540c6d61a181d5b556c76b732a2cb1c1e2c281098dd","schema_version":"1.0","event_id":"sha256:dc96b019b3972b5f3e8a9540c6d61a181d5b556c76b732a2cb1c1e2c281098dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QFEHHBGWN5Z3JMO4FARG5IRNEU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ProsodyLM: Uncovering the Emerging Prosody Processing Capabilities in Speech Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Chuang Gan, Junrui Ni, Kaizhi Qian, Mark Hasegawa-Johnson, Slava Shechtman, Xulin Fan, Yang Zhang","submitted_at":"2025-07-27T00:59:01Z","abstract_excerpt":"Speech language models refer to language models with speech processing and understanding capabilities. One key desirable capability for speech language models is the ability to capture the intricate interdependency between content and prosody. The existing mainstream paradigm of training speech language models, which converts speech into discrete tokens before feeding them into LLMs, is sub-optimal in learning prosody information -- we find that the resulting LLMs do not exhibit obvious emerging prosody processing capabilities via pre-training alone. To overcome this, we propose ProsodyLM, whi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20091","kind":"arxiv","version":2},"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/2507.20091/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":"2026-07-05T11:50:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k4Ch7KFHFOG3h6p751FnftazOiL8mLDGf98SYhZVaNYRzx+vuyajWOUNhQS5wu1DRM3L6xXmdII48T93qF5qDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T18:26:40.188183Z"},"content_sha256":"6be947a8535a7905226e2675fd1dd088c2d9ed721fd3c84ca8a462599f6ea5f7","schema_version":"1.0","event_id":"sha256:6be947a8535a7905226e2675fd1dd088c2d9ed721fd3c84ca8a462599f6ea5f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QFEHHBGWN5Z3JMO4FARG5IRNEU/bundle.json","state_url":"https://pith.science/pith/QFEHHBGWN5Z3JMO4FARG5IRNEU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QFEHHBGWN5Z3JMO4FARG5IRNEU/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":"2026-08-17T18:26:40Z","links":{"resolver":"https://pith.science/pith/QFEHHBGWN5Z3JMO4FARG5IRNEU","bundle":"https://pith.science/pith/QFEHHBGWN5Z3JMO4FARG5IRNEU/bundle.json","state":"https://pith.science/pith/QFEHHBGWN5Z3JMO4FARG5IRNEU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QFEHHBGWN5Z3JMO4FARG5IRNEU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QFEHHBGWN5Z3JMO4FARG5IRNEU","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":"ca4c739f3311b6a99c9338c24791b74547dc09e8f24930928838a196b432409f","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-27T00:59:01Z","title_canon_sha256":"c6ea6bf497b3086936dbcd27e76babef35c2901268a6e952b2a8f05896bc425f"},"schema_version":"1.0","source":{"id":"2507.20091","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.20091","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"arxiv_version","alias_value":"2507.20091v2","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20091","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"pith_short_12","alias_value":"QFEHHBGWN5Z3","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"pith_short_16","alias_value":"QFEHHBGWN5Z3JMO4","created_at":"2026-07-05T11:50:38Z"},{"alias_kind":"pith_short_8","alias_value":"QFEHHBGW","created_at":"2026-07-05T11:50:38Z"}],"graph_snapshots":[{"event_id":"sha256:6be947a8535a7905226e2675fd1dd088c2d9ed721fd3c84ca8a462599f6ea5f7","target":"graph","created_at":"2026-07-05T11:50:38Z","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/2507.20091/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech language models refer to language models with speech processing and understanding capabilities. One key desirable capability for speech language models is the ability to capture the intricate interdependency between content and prosody. The existing mainstream paradigm of training speech language models, which converts speech into discrete tokens before feeding them into LLMs, is sub-optimal in learning prosody information -- we find that the resulting LLMs do not exhibit obvious emerging prosody processing capabilities via pre-training alone. To overcome this, we propose ProsodyLM, whi","authors_text":"Chuang Gan, Junrui Ni, Kaizhi Qian, Mark Hasegawa-Johnson, Slava Shechtman, Xulin Fan, Yang Zhang","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-27T00:59:01Z","title":"ProsodyLM: Uncovering the Emerging Prosody Processing Capabilities in Speech Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20091","kind":"arxiv","version":2},"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:dc96b019b3972b5f3e8a9540c6d61a181d5b556c76b732a2cb1c1e2c281098dd","target":"record","created_at":"2026-07-05T11:50:38Z","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":"ca4c739f3311b6a99c9338c24791b74547dc09e8f24930928838a196b432409f","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-27T00:59:01Z","title_canon_sha256":"c6ea6bf497b3086936dbcd27e76babef35c2901268a6e952b2a8f05896bc425f"},"schema_version":"1.0","source":{"id":"2507.20091","kind":"arxiv","version":2}},"canonical_sha256":"81487384d66f73b4b1dc28226ea22d251049ebec8b936b9bb797aee2e31334cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81487384d66f73b4b1dc28226ea22d251049ebec8b936b9bb797aee2e31334cb","first_computed_at":"2026-07-05T11:50:38.845004Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:50:38.845004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zphEK1yZaCkAigVCDtcIuhA6HUlqjMqnE4basBydgZLqngsayrUzauVyzlvs2nFYZK4qHxi8ac6746vJkaLeBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:50:38.845501Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.20091","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc96b019b3972b5f3e8a9540c6d61a181d5b556c76b732a2cb1c1e2c281098dd","sha256:6be947a8535a7905226e2675fd1dd088c2d9ed721fd3c84ca8a462599f6ea5f7"],"state_sha256":"ec8a46c8295087499502f493dbbdd5b59e0f75cf59c14114b4aaf8ec8c6bd430"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EREB0AlKTWXsG8iNq3fMYaG4DCCfX+olOKPHzkGLKM0MIzpPt4oScKe8WB7gISiFsOEEj0U7309YK8QpOenUDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T18:26:40.192619Z","bundle_sha256":"cd807ce42320b124adbf5f82d6518b3b4275b0884347ba70148161a72f4c1fbd"}}