{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TIZJQZRGOMUICZT6HXBZH65ZMG","short_pith_number":"pith:TIZJQZRG","canonical_record":{"source":{"id":"2505.13338","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T16:47:46Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"7cdb4e4e7a7874ff6b9818bc7a7ea0de25dec64a83e9ff89dfb181a23dc094a8","abstract_canon_sha256":"28fee73e143afdb98a89b4007e33f6e7eea0351d18fbd485ef9612beb6897be6"},"schema_version":"1.0"},"canonical_sha256":"9a32986626732881667e3dc393fbb961aab8343fa6a6620947802c1db8696787","source":{"kind":"arxiv","id":"2505.13338","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13338","created_at":"2026-07-05T11:14:29Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13338v2","created_at":"2026-07-05T11:14:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13338","created_at":"2026-07-05T11:14:29Z"},{"alias_kind":"pith_short_12","alias_value":"TIZJQZRGOMUI","created_at":"2026-07-05T11:14:29Z"},{"alias_kind":"pith_short_16","alias_value":"TIZJQZRGOMUICZT6","created_at":"2026-07-05T11:14:29Z"},{"alias_kind":"pith_short_8","alias_value":"TIZJQZRG","created_at":"2026-07-05T11:14:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TIZJQZRGOMUICZT6HXBZH65ZMG","target":"record","payload":{"canonical_record":{"source":{"id":"2505.13338","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T16:47:46Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"7cdb4e4e7a7874ff6b9818bc7a7ea0de25dec64a83e9ff89dfb181a23dc094a8","abstract_canon_sha256":"28fee73e143afdb98a89b4007e33f6e7eea0351d18fbd485ef9612beb6897be6"},"schema_version":"1.0"},"canonical_sha256":"9a32986626732881667e3dc393fbb961aab8343fa6a6620947802c1db8696787","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:29.095116Z","signature_b64":"rF7c1QNypKjgBSQ40e3NfXolf/+GGqSq/v0RLUYryvMkazohjZSKubHu36HlkOoXYcKICLf+LNx2qnIZB6vbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a32986626732881667e3dc393fbb961aab8343fa6a6620947802c1db8696787","last_reissued_at":"2026-07-05T11:14:29.094678Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:29.094678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.13338","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":"2026-07-05T11:14:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o+xgV7PdjdGAzp5WnUZ5KxW4Mjz0iB2QqpxZszE0kdL4m7tiWJHqIsrgkTLPo5BW+10sqcpkhbbUOLdcdnaTBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T04:14:19.503102Z"},"content_sha256":"09955b6ec3116386aa99c062b1fa880e50758672282c1e1780f302228e9e8bb9","schema_version":"1.0","event_id":"sha256:09955b6ec3116386aa99c062b1fa880e50758672282c1e1780f302228e9e8bb9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TIZJQZRGOMUICZT6HXBZH65ZMG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ai Ti Aw, Hardik B. Sailor, Qiongqiong Wang, Tianchi Liu","submitted_at":"2025-05-19T16:47:46Z","abstract_excerpt":"Current speech-LLMs exhibit limited capability in contextual reasoning alongside paralinguistic understanding, primarily due to the lack of Question-Answer (QA) datasets that cover both aspects. We propose a novel framework for dataset generation from in-the-wild speech data, that integrates contextual reasoning with paralinguistic information. It consists of a pseudo paralinguistic label-based data condensation of in-the-wild speech and LLM-based Contextual Paralinguistic QA (CPQA) generation. The effectiveness is validated by a strong correlation in evaluations of the Qwen2-Audio-7B-Instruct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13338","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/2505.13338/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":"2026-07-05T11:14:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lLLGi6Dmj1Au0wYYIsV+HZE4b0KZqHl8nbqt29bkAqBcgaUP+0ujxrRXWfpP/MlzhKvjkOoNA6UAnxentIctCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T04:14:19.503625Z"},"content_sha256":"dacecc3193b9cc9be133ec9f8ba9ed7c4837228f45c5a5b92a3744a5cd9b3d7c","schema_version":"1.0","event_id":"sha256:dacecc3193b9cc9be133ec9f8ba9ed7c4837228f45c5a5b92a3744a5cd9b3d7c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TIZJQZRGOMUICZT6HXBZH65ZMG/bundle.json","state_url":"https://pith.science/pith/TIZJQZRGOMUICZT6HXBZH65ZMG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TIZJQZRGOMUICZT6HXBZH65ZMG/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":"2026-08-18T04:14:19Z","links":{"resolver":"https://pith.science/pith/TIZJQZRGOMUICZT6HXBZH65ZMG","bundle":"https://pith.science/pith/TIZJQZRGOMUICZT6HXBZH65ZMG/bundle.json","state":"https://pith.science/pith/TIZJQZRGOMUICZT6HXBZH65ZMG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TIZJQZRGOMUICZT6HXBZH65ZMG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TIZJQZRGOMUICZT6HXBZH65ZMG","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":"28fee73e143afdb98a89b4007e33f6e7eea0351d18fbd485ef9612beb6897be6","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T16:47:46Z","title_canon_sha256":"7cdb4e4e7a7874ff6b9818bc7a7ea0de25dec64a83e9ff89dfb181a23dc094a8"},"schema_version":"1.0","source":{"id":"2505.13338","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13338","created_at":"2026-07-05T11:14:29Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13338v2","created_at":"2026-07-05T11:14:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13338","created_at":"2026-07-05T11:14:29Z"},{"alias_kind":"pith_short_12","alias_value":"TIZJQZRGOMUI","created_at":"2026-07-05T11:14:29Z"},{"alias_kind":"pith_short_16","alias_value":"TIZJQZRGOMUICZT6","created_at":"2026-07-05T11:14:29Z"},{"alias_kind":"pith_short_8","alias_value":"TIZJQZRG","created_at":"2026-07-05T11:14:29Z"}],"graph_snapshots":[{"event_id":"sha256:dacecc3193b9cc9be133ec9f8ba9ed7c4837228f45c5a5b92a3744a5cd9b3d7c","target":"graph","created_at":"2026-07-05T11:14:29Z","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/2505.13338/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current speech-LLMs exhibit limited capability in contextual reasoning alongside paralinguistic understanding, primarily due to the lack of Question-Answer (QA) datasets that cover both aspects. We propose a novel framework for dataset generation from in-the-wild speech data, that integrates contextual reasoning with paralinguistic information. It consists of a pseudo paralinguistic label-based data condensation of in-the-wild speech and LLM-based Contextual Paralinguistic QA (CPQA) generation. The effectiveness is validated by a strong correlation in evaluations of the Qwen2-Audio-7B-Instruct","authors_text":"Ai Ti Aw, Hardik B. Sailor, Qiongqiong Wang, Tianchi Liu","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T16:47:46Z","title":"Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13338","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":"sha256:09955b6ec3116386aa99c062b1fa880e50758672282c1e1780f302228e9e8bb9","target":"record","created_at":"2026-07-05T11:14:29Z","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":"28fee73e143afdb98a89b4007e33f6e7eea0351d18fbd485ef9612beb6897be6","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T16:47:46Z","title_canon_sha256":"7cdb4e4e7a7874ff6b9818bc7a7ea0de25dec64a83e9ff89dfb181a23dc094a8"},"schema_version":"1.0","source":{"id":"2505.13338","kind":"arxiv","version":2}},"canonical_sha256":"9a32986626732881667e3dc393fbb961aab8343fa6a6620947802c1db8696787","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a32986626732881667e3dc393fbb961aab8343fa6a6620947802c1db8696787","first_computed_at":"2026-07-05T11:14:29.094678Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:29.094678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rF7c1QNypKjgBSQ40e3NfXolf/+GGqSq/v0RLUYryvMkazohjZSKubHu36HlkOoXYcKICLf+LNx2qnIZB6vbDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:29.095116Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13338","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09955b6ec3116386aa99c062b1fa880e50758672282c1e1780f302228e9e8bb9","sha256:dacecc3193b9cc9be133ec9f8ba9ed7c4837228f45c5a5b92a3744a5cd9b3d7c"],"state_sha256":"d8e6aac746b71db46e8604a8430dbd6d02644c7a2d68a4177720a05f01ba0a3d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MXbnuksesyC/I+49EeTFpxUL4Q9zJGv6bb3zOohXVrtD4s+vsgm1nUTr4sxdWVrhKYuZV0B4fCz9QaNg7AX1Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T04:14:19.508693Z","bundle_sha256":"6a8b80036dbc9531bd76afd91150e8b177405a8513ef05ac379e19e932df7fe1"}}