{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NL4QGJ6WJIDR6RE4NZQJWEN5TS","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":"e30c8753af4bd1619795dceb2a4c23b167c25948182ff88fa022feda4bc76dd6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-12T06:56:14Z","title_canon_sha256":"07813b17814af950c117e803bd0dba284b5e0973998b6fac18137f6a7f1f728d"},"schema_version":"1.0","source":{"id":"2311.06753","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.06753","created_at":"2026-07-05T08:07:30Z"},{"alias_kind":"arxiv_version","alias_value":"2311.06753v2","created_at":"2026-07-05T08:07:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06753","created_at":"2026-07-05T08:07:30Z"},{"alias_kind":"pith_short_12","alias_value":"NL4QGJ6WJIDR","created_at":"2026-07-05T08:07:30Z"},{"alias_kind":"pith_short_16","alias_value":"NL4QGJ6WJIDR6RE4","created_at":"2026-07-05T08:07:30Z"},{"alias_kind":"pith_short_8","alias_value":"NL4QGJ6W","created_at":"2026-07-05T08:07:30Z"}],"graph_snapshots":[{"event_id":"sha256:23d66bd86a7b504733290dad412b392a8ab7363a3ce544d7bdcef92450758b87","target":"graph","created_at":"2026-07-05T08:07:30Z","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/2311.06753/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Christian Fuegen, Chunyang Wu, Egor Lakomkin, Jay Mahadeokar, Junteng Jia, Ke Li, Mike Seltzer, Ozlem Kalinli, Yassir Fathullah, Yuan Shangguan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-12T06:56:14Z","title":"AudioChatLlama: Towards General-Purpose Speech Abilities for LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.06753","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":"sha256:451a008aa0ec07e4441ac5b1807c841d1eeea12a981bf385e0dcddbcfb725230","target":"record","created_at":"2026-07-05T08:07:30Z","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":"e30c8753af4bd1619795dceb2a4c23b167c25948182ff88fa022feda4bc76dd6","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-12T06:56:14Z","title_canon_sha256":"07813b17814af950c117e803bd0dba284b5e0973998b6fac18137f6a7f1f728d"},"schema_version":"1.0","source":{"id":"2311.06753","kind":"arxiv","version":2}},"canonical_sha256":"6af90327d64a071f449c6e609b11bd9c895bcb69ff4bdd1235bc2e1ec30904e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6af90327d64a071f449c6e609b11bd9c895bcb69ff4bdd1235bc2e1ec30904e5","first_computed_at":"2026-07-05T08:07:30.763670Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:07:30.763670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9AwEzeDxDXX/8ZIOFe+ixQTE/beD0QYlUUvA1I/OqIlW8YwEXPiXD0UAqAvYPKfIpuH+GtX6564hrTHpF7MhAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:07:30.764164Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.06753","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:451a008aa0ec07e4441ac5b1807c841d1eeea12a981bf385e0dcddbcfb725230","sha256:23d66bd86a7b504733290dad412b392a8ab7363a3ce544d7bdcef92450758b87"],"state_sha256":"fbb9b574cef9f5792e982fe2b8788ba5339499fea30da0ddb625bbe4ee8ec98f"}