{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NL4QGJ6WJIDR6RE4NZQJWEN5TS","short_pith_number":"pith:NL4QGJ6W","schema_version":"1.0","canonical_sha256":"6af90327d64a071f449c6e609b11bd9c895bcb69ff4bdd1235bc2e1ec30904e5","source":{"kind":"arxiv","id":"2311.06753","version":2},"attestation_state":"computed","paper":{"title":"AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Christian Fuegen, Chunyang Wu, Egor Lakomkin, Jay Mahadeokar, Junteng Jia, Ke Li, Mike Seltzer, Ozlem Kalinli, Yassir Fathullah, Yuan Shangguan","submitted_at":"2023-11-12T06:56:14Z","abstract_excerpt":"In this work, we extend the instruction-tuned Llama-2 model with end-to-end general-purpose speech processing and reasoning abilities while maintaining the wide range of original LLM capabilities, without using any carefully curated paired data. The resulting end-to-end model, named AudioChatLlama, can utilize audio prompts as a replacement for text and sustain a conversation. Such a model also has extended cross-modal capabilities such as being able to perform spoken question answering (QA), speech translation, and audio summarization amongst many other closed and open-domain tasks. This is u"},"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":"2311.06753","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-12T06:56:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"07813b17814af950c117e803bd0dba284b5e0973998b6fac18137f6a7f1f728d","abstract_canon_sha256":"e30c8753af4bd1619795dceb2a4c23b167c25948182ff88fa022feda4bc76dd6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:30.764164Z","signature_b64":"9AwEzeDxDXX/8ZIOFe+ixQTE/beD0QYlUUvA1I/OqIlW8YwEXPiXD0UAqAvYPKfIpuH+GtX6564hrTHpF7MhAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6af90327d64a071f449c6e609b11bd9c895bcb69ff4bdd1235bc2e1ec30904e5","last_reissued_at":"2026-07-05T08:07:30.763670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:30.763670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Christian Fuegen, Chunyang Wu, Egor Lakomkin, Jay Mahadeokar, Junteng Jia, Ke Li, Mike Seltzer, Ozlem Kalinli, Yassir Fathullah, Yuan Shangguan","submitted_at":"2023-11-12T06:56:14Z","abstract_excerpt":"In this work, we extend the instruction-tuned Llama-2 model with end-to-end general-purpose speech processing and reasoning abilities while maintaining the wide range of original LLM capabilities, without using any carefully curated paired data. The resulting end-to-end model, named AudioChatLlama, can utilize audio prompts as a replacement for text and sustain a conversation. Such a model also has extended cross-modal capabilities such as being able to perform spoken question answering (QA), speech translation, and audio summarization amongst many other closed and open-domain tasks. This is u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.06753","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/2311.06753/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":"2311.06753","created_at":"2026-07-05T08:07:30.763732+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.06753v2","created_at":"2026-07-05T08:07:30.763732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06753","created_at":"2026-07-05T08:07:30.763732+00:00"},{"alias_kind":"pith_short_12","alias_value":"NL4QGJ6WJIDR","created_at":"2026-07-05T08:07:30.763732+00:00"},{"alias_kind":"pith_short_16","alias_value":"NL4QGJ6WJIDR6RE4","created_at":"2026-07-05T08:07:30.763732+00:00"},{"alias_kind":"pith_short_8","alias_value":"NL4QGJ6W","created_at":"2026-07-05T08:07:30.763732+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.03526","citing_title":"Enhancing Speech Large Language Models through Reinforced Behavior Alignment","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NL4QGJ6WJIDR6RE4NZQJWEN5TS","json":"https://pith.science/pith/NL4QGJ6WJIDR6RE4NZQJWEN5TS.json","graph_json":"https://pith.science/api/pith-number/NL4QGJ6WJIDR6RE4NZQJWEN5TS/graph.json","events_json":"https://pith.science/api/pith-number/NL4QGJ6WJIDR6RE4NZQJWEN5TS/events.json","paper":"https://pith.science/paper/NL4QGJ6W"},"agent_actions":{"view_html":"https://pith.science/pith/NL4QGJ6WJIDR6RE4NZQJWEN5TS","download_json":"https://pith.science/pith/NL4QGJ6WJIDR6RE4NZQJWEN5TS.json","view_paper":"https://pith.science/paper/NL4QGJ6W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.06753&json=true","fetch_graph":"https://pith.science/api/pith-number/NL4QGJ6WJIDR6RE4NZQJWEN5TS/graph.json","fetch_events":"https://pith.science/api/pith-number/NL4QGJ6WJIDR6RE4NZQJWEN5TS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NL4QGJ6WJIDR6RE4NZQJWEN5TS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NL4QGJ6WJIDR6RE4NZQJWEN5TS/action/storage_attestation","attest_author":"https://pith.science/pith/NL4QGJ6WJIDR6RE4NZQJWEN5TS/action/author_attestation","sign_citation":"https://pith.science/pith/NL4QGJ6WJIDR6RE4NZQJWEN5TS/action/citation_signature","submit_replication":"https://pith.science/pith/NL4QGJ6WJIDR6RE4NZQJWEN5TS/action/replication_record"}},"created_at":"2026-07-05T08:07:30.763732+00:00","updated_at":"2026-07-05T08:07:30.763732+00:00"}