{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YPQBJSQA67JHVUMXFL3LSRWBOF","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":"4a8bbea98d244aaababc61b8668cc3138ef4aeada2c4dc8d985ac2eb89efe945","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-02-02T18:58:34Z","title_canon_sha256":"ae0bca3d1e6be7edd8c725aacd75cd805b2eabe957b85be3b1258f248a12853d"},"schema_version":"1.0","source":{"id":"2402.01831","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01831","created_at":"2026-07-05T08:24:00Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01831v3","created_at":"2026-07-05T08:24:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01831","created_at":"2026-07-05T08:24:00Z"},{"alias_kind":"pith_short_12","alias_value":"YPQBJSQA67JH","created_at":"2026-07-05T08:24:00Z"},{"alias_kind":"pith_short_16","alias_value":"YPQBJSQA67JHVUMX","created_at":"2026-07-05T08:24:00Z"},{"alias_kind":"pith_short_8","alias_value":"YPQBJSQA","created_at":"2026-07-05T08:24:00Z"}],"graph_snapshots":[{"event_id":"sha256:1d2278c8134385645b6829cd6a755481b4a32e1bc6914123199b6118b893252f","target":"graph","created_at":"2026-07-05T08:24:00Z","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/2402.01831/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Augmenting large language models (LLMs) to understand audio -- including non-speech sounds and non-verbal speech -- is critically important for diverse real-world applications of LLMs. In this paper, we propose Audio Flamingo, a novel audio language model with 1) strong audio understanding abilities, 2) the ability to quickly adapt to unseen tasks via in-context learning and retrieval, and 3) strong multi-turn dialogue abilities. We introduce a series of training techniques, architecture design, and data strategies to enhance our model with these abilities. Extensive evaluations across various","authors_text":"Arushi Goel, Bryan Catanzaro, Rafael Valle, Rohan Badlani, Wei Ping, Zhifeng Kong","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-02-02T18:58:34Z","title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01831","kind":"arxiv","version":3},"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":"sha256:2b70fc81fd8790c962ad6903dfa1bc1bf72e2c3d1bceaa860d2fdbe537553f6e","target":"record","created_at":"2026-07-05T08:24:00Z","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":"4a8bbea98d244aaababc61b8668cc3138ef4aeada2c4dc8d985ac2eb89efe945","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-02-02T18:58:34Z","title_canon_sha256":"ae0bca3d1e6be7edd8c725aacd75cd805b2eabe957b85be3b1258f248a12853d"},"schema_version":"1.0","source":{"id":"2402.01831","kind":"arxiv","version":3}},"canonical_sha256":"c3e014ca00f7d27ad1972af6b946c1714d7dd9974a8cd60660fe1b29cd2c8d0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3e014ca00f7d27ad1972af6b946c1714d7dd9974a8cd60660fe1b29cd2c8d0d","first_computed_at":"2026-07-05T08:24:00.652723Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:00.652723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UE8dTL/H/CPTPh4V88EDe+xkzen8dWiJCz7PU3IWnUp/r6uIc4N3EX/yw/T6yXMieQigmOlk7yg/RA0RPkDZBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:00.653230Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.01831","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b70fc81fd8790c962ad6903dfa1bc1bf72e2c3d1bceaa860d2fdbe537553f6e","sha256:1d2278c8134385645b6829cd6a755481b4a32e1bc6914123199b6118b893252f"],"state_sha256":"6ca19a2c9b9e1b47d6493dd7af18c8f7b72d139446654cf91e370cc9a8b1315c"}