{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:66KU3SRK5FHUFRUJ5NGJIWOTCE","short_pith_number":"pith:66KU3SRK","canonical_record":{"source":{"id":"2410.01162","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-10-02T01:32:47Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"8ff682239f8847418cb6b5e6adc65ed742e5eb40c9b331734ba92e4d3f2ff65c","abstract_canon_sha256":"cae37acd35bea6d8e0fc4284851710298ffceae28dfce9c5494e454e11abb006"},"schema_version":"1.0"},"canonical_sha256":"f7954dca2ae94f42c689eb4c9459d3110e69526484591f2d4b439f7a2f30d766","source":{"kind":"arxiv","id":"2410.01162","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01162","created_at":"2026-07-05T12:03:22Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01162v2","created_at":"2026-07-05T12:03:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01162","created_at":"2026-07-05T12:03:22Z"},{"alias_kind":"pith_short_12","alias_value":"66KU3SRK5FHU","created_at":"2026-07-05T12:03:22Z"},{"alias_kind":"pith_short_16","alias_value":"66KU3SRK5FHUFRUJ","created_at":"2026-07-05T12:03:22Z"},{"alias_kind":"pith_short_8","alias_value":"66KU3SRK","created_at":"2026-07-05T12:03:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:66KU3SRK5FHUFRUJ5NGJIWOTCE","target":"record","payload":{"canonical_record":{"source":{"id":"2410.01162","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-10-02T01:32:47Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"8ff682239f8847418cb6b5e6adc65ed742e5eb40c9b331734ba92e4d3f2ff65c","abstract_canon_sha256":"cae37acd35bea6d8e0fc4284851710298ffceae28dfce9c5494e454e11abb006"},"schema_version":"1.0"},"canonical_sha256":"f7954dca2ae94f42c689eb4c9459d3110e69526484591f2d4b439f7a2f30d766","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:22.792596Z","signature_b64":"DbGf1QGjEnHY0nMXQ5ENfbCFc8sJDEPTUUbq1ynPRdfVdzMol9xysfqboG59qM3G9pdP+jrRUA9MhkQigGQYDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7954dca2ae94f42c689eb4c9459d3110e69526484591f2d4b439f7a2f30d766","last_reissued_at":"2026-07-05T12:03:22.792188Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:22.792188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.01162","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":"2026-07-05T12:03:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JkoOOOMDsee5jtW+JFRshk4OWdfOTTsY6ws8JygED+NK9tLIn3TnCcGan4fCZ84ulDs+8NX4l21TKKV3dMRVAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T03:18:29.062598Z"},"content_sha256":"f6d88f79f6cc6934299247dafb6df1d7755be27aa65c7f4c9d096a8fdf465bd9","schema_version":"1.0","event_id":"sha256:f6d88f79f6cc6934299247dafb6df1d7755be27aa65c7f4c9d096a8fdf465bd9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:66KU3SRK5FHUFRUJ5NGJIWOTCE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Frozen Large Language Models Can Perceive Paralinguistic Aspects of Speech","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chunyang Wu, Egor Lakomkin, Jay Mahadeokar, Junteng Jia, Ke Li, Leda Sari, Ozlem Kalinli, Suyoun Kim, Wei Zhou, Wonjune Kang, Yashesh Gaur","submitted_at":"2024-10-02T01:32:47Z","abstract_excerpt":"This work studies the capabilities of a large language model (LLM) to understand paralinguistic aspects of speech without fine-tuning its weights. We utilize an end-to-end system with a speech encoder, which is trained to produce token embeddings such that the LLM's response to an expressive speech prompt is aligned with its response to a semantically matching text prompt that has also been conditioned on the user's speaking style. This framework enables the encoder to generate tokens that capture both linguistic and paralinguistic information and effectively convey them to the LLM, even when "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01162","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/2410.01162/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":"2026-07-05T12:03:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rkZR2bOGaZSbPJsLA4/x+8Sp7peiiK0ksIUqpm1COjEUEUSy7AcxslrNVixkPtD99YmFJhc1mT7YjDNvoPobDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T03:18:29.063220Z"},"content_sha256":"7f3a40b0bfe4c1b33e2d93fa4d5657ec8e3bdfe2306831dc5287bad72ce46f04","schema_version":"1.0","event_id":"sha256:7f3a40b0bfe4c1b33e2d93fa4d5657ec8e3bdfe2306831dc5287bad72ce46f04"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/66KU3SRK5FHUFRUJ5NGJIWOTCE/bundle.json","state_url":"https://pith.science/pith/66KU3SRK5FHUFRUJ5NGJIWOTCE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/66KU3SRK5FHUFRUJ5NGJIWOTCE/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":"2026-08-22T03:18:29Z","links":{"resolver":"https://pith.science/pith/66KU3SRK5FHUFRUJ5NGJIWOTCE","bundle":"https://pith.science/pith/66KU3SRK5FHUFRUJ5NGJIWOTCE/bundle.json","state":"https://pith.science/pith/66KU3SRK5FHUFRUJ5NGJIWOTCE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/66KU3SRK5FHUFRUJ5NGJIWOTCE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:66KU3SRK5FHUFRUJ5NGJIWOTCE","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":"cae37acd35bea6d8e0fc4284851710298ffceae28dfce9c5494e454e11abb006","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-10-02T01:32:47Z","title_canon_sha256":"8ff682239f8847418cb6b5e6adc65ed742e5eb40c9b331734ba92e4d3f2ff65c"},"schema_version":"1.0","source":{"id":"2410.01162","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01162","created_at":"2026-07-05T12:03:22Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01162v2","created_at":"2026-07-05T12:03:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01162","created_at":"2026-07-05T12:03:22Z"},{"alias_kind":"pith_short_12","alias_value":"66KU3SRK5FHU","created_at":"2026-07-05T12:03:22Z"},{"alias_kind":"pith_short_16","alias_value":"66KU3SRK5FHUFRUJ","created_at":"2026-07-05T12:03:22Z"},{"alias_kind":"pith_short_8","alias_value":"66KU3SRK","created_at":"2026-07-05T12:03:22Z"}],"graph_snapshots":[{"event_id":"sha256:7f3a40b0bfe4c1b33e2d93fa4d5657ec8e3bdfe2306831dc5287bad72ce46f04","target":"graph","created_at":"2026-07-05T12:03:22Z","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/2410.01162/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work studies the capabilities of a large language model (LLM) to understand paralinguistic aspects of speech without fine-tuning its weights. We utilize an end-to-end system with a speech encoder, which is trained to produce token embeddings such that the LLM's response to an expressive speech prompt is aligned with its response to a semantically matching text prompt that has also been conditioned on the user's speaking style. This framework enables the encoder to generate tokens that capture both linguistic and paralinguistic information and effectively convey them to the LLM, even when ","authors_text":"Chunyang Wu, Egor Lakomkin, Jay Mahadeokar, Junteng Jia, Ke Li, Leda Sari, Ozlem Kalinli, Suyoun Kim, Wei Zhou, Wonjune Kang, Yashesh Gaur","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-10-02T01:32:47Z","title":"Frozen Large Language Models Can Perceive Paralinguistic Aspects of Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01162","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:f6d88f79f6cc6934299247dafb6df1d7755be27aa65c7f4c9d096a8fdf465bd9","target":"record","created_at":"2026-07-05T12:03:22Z","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":"cae37acd35bea6d8e0fc4284851710298ffceae28dfce9c5494e454e11abb006","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-10-02T01:32:47Z","title_canon_sha256":"8ff682239f8847418cb6b5e6adc65ed742e5eb40c9b331734ba92e4d3f2ff65c"},"schema_version":"1.0","source":{"id":"2410.01162","kind":"arxiv","version":2}},"canonical_sha256":"f7954dca2ae94f42c689eb4c9459d3110e69526484591f2d4b439f7a2f30d766","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7954dca2ae94f42c689eb4c9459d3110e69526484591f2d4b439f7a2f30d766","first_computed_at":"2026-07-05T12:03:22.792188Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:03:22.792188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DbGf1QGjEnHY0nMXQ5ENfbCFc8sJDEPTUUbq1ynPRdfVdzMol9xysfqboG59qM3G9pdP+jrRUA9MhkQigGQYDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:03:22.792596Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.01162","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6d88f79f6cc6934299247dafb6df1d7755be27aa65c7f4c9d096a8fdf465bd9","sha256:7f3a40b0bfe4c1b33e2d93fa4d5657ec8e3bdfe2306831dc5287bad72ce46f04"],"state_sha256":"06e9b35c2cc9c9dc50f4945fdbc3582d67fe16b4dbf8ccf65eec7fa21c33e4f8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/8a2qbq8qD1E7CGm+mtYsF7ufr34UiNTLrpW9awIr9rSQ2jMh3CmacoV1vqzdQW4gUduNSuKvRlcpQx6fbx1Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T03:18:29.068227Z","bundle_sha256":"ab9c83d27746d003d3c918eeb45aef5135130c05795f0b925094ff8fd2f3c082"}}