{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FZ6HWZEERRML6SO5JT7SVBU46Q","short_pith_number":"pith:FZ6HWZEE","schema_version":"1.0","canonical_sha256":"2e7c7b64848c58bf49dd4cff2a869cf414d7cfd448b1d3395a45ff1010126b35","source":{"kind":"arxiv","id":"2506.00003","version":1},"attestation_state":"computed","paper":{"title":"Probing Audio-Generation Capabilities of Text-Based Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Arjun Prasaath Anbazhagan, Aslihan Akalin, Kevin Zhu, Parteek Kumar, Sean O'Brien, Ujjwal Kaur","submitted_at":"2025-05-04T23:46:01Z","abstract_excerpt":"How does textual representation of audio relate to the Large Language Model's (LLMs) learning about the audio world? This research investigates the extent to which LLMs can be prompted to generate audio, despite their primary training in textual data. We employ a three-tier approach, progressively increasing the complexity of audio generation: 1) Musical Notes, 2) Environmental Sounds, and 3) Human Speech. To bridge the gap between text and audio, we leverage code as an intermediary, prompting LLMs to generate code that, when executed, produces the desired audio output. To evaluate the quality"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.00003","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-05-04T23:46:01Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"882873cfcfac0e4d441cee0aeb99bb0b3390609cacb2787f4260912259c27ff6","abstract_canon_sha256":"7c55ecad6408f3949e301c1f7bfe03ee320b47972a8c95c93917e01206483ad3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:58.334797Z","signature_b64":"NrG2A9HlhAcY0+5Sk+OZXTYcp0Xi8GjzPFM0qxJbyl3rNh9D9mTioHYHwCgElFyX5t4JmRM5ixaGVf5/o+rDCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e7c7b64848c58bf49dd4cff2a869cf414d7cfd448b1d3395a45ff1010126b35","last_reissued_at":"2026-07-05T11:12:58.334244Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:58.334244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probing Audio-Generation Capabilities of Text-Based Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Arjun Prasaath Anbazhagan, Aslihan Akalin, Kevin Zhu, Parteek Kumar, Sean O'Brien, Ujjwal Kaur","submitted_at":"2025-05-04T23:46:01Z","abstract_excerpt":"How does textual representation of audio relate to the Large Language Model's (LLMs) learning about the audio world? This research investigates the extent to which LLMs can be prompted to generate audio, despite their primary training in textual data. We employ a three-tier approach, progressively increasing the complexity of audio generation: 1) Musical Notes, 2) Environmental Sounds, and 3) Human Speech. To bridge the gap between text and audio, we leverage code as an intermediary, prompting LLMs to generate code that, when executed, produces the desired audio output. To evaluate the quality"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00003","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/2506.00003/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.00003","created_at":"2026-07-05T11:12:58.334310+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00003v1","created_at":"2026-07-05T11:12:58.334310+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00003","created_at":"2026-07-05T11:12:58.334310+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZ6HWZEERRML","created_at":"2026-07-05T11:12:58.334310+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZ6HWZEERRML6SO5","created_at":"2026-07-05T11:12:58.334310+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZ6HWZEE","created_at":"2026-07-05T11:12:58.334310+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FZ6HWZEERRML6SO5JT7SVBU46Q","json":"https://pith.science/pith/FZ6HWZEERRML6SO5JT7SVBU46Q.json","graph_json":"https://pith.science/api/pith-number/FZ6HWZEERRML6SO5JT7SVBU46Q/graph.json","events_json":"https://pith.science/api/pith-number/FZ6HWZEERRML6SO5JT7SVBU46Q/events.json","paper":"https://pith.science/paper/FZ6HWZEE"},"agent_actions":{"view_html":"https://pith.science/pith/FZ6HWZEERRML6SO5JT7SVBU46Q","download_json":"https://pith.science/pith/FZ6HWZEERRML6SO5JT7SVBU46Q.json","view_paper":"https://pith.science/paper/FZ6HWZEE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00003&json=true","fetch_graph":"https://pith.science/api/pith-number/FZ6HWZEERRML6SO5JT7SVBU46Q/graph.json","fetch_events":"https://pith.science/api/pith-number/FZ6HWZEERRML6SO5JT7SVBU46Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZ6HWZEERRML6SO5JT7SVBU46Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZ6HWZEERRML6SO5JT7SVBU46Q/action/storage_attestation","attest_author":"https://pith.science/pith/FZ6HWZEERRML6SO5JT7SVBU46Q/action/author_attestation","sign_citation":"https://pith.science/pith/FZ6HWZEERRML6SO5JT7SVBU46Q/action/citation_signature","submit_replication":"https://pith.science/pith/FZ6HWZEERRML6SO5JT7SVBU46Q/action/replication_record"}},"created_at":"2026-07-05T11:12:58.334310+00:00","updated_at":"2026-07-05T11:12:58.334310+00:00"}