{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FYKEWG6JQ3YRILG6G2Q4LHHD2G","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":"597962f8e73c40119d187228b2fe8a4a0aea7ee1bbec0d46f6282311f3157c18","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-09T16:00:00Z","title_canon_sha256":"9fdaec674e7de5ab44ab303270943260aaddf6d5d2db64b2538d818a85ddcfae"},"schema_version":"1.0","source":{"id":"2406.05839","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.05839","created_at":"2026-07-05T09:33:32Z"},{"alias_kind":"arxiv_version","alias_value":"2406.05839v2","created_at":"2026-07-05T09:33:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05839","created_at":"2026-07-05T09:33:32Z"},{"alias_kind":"pith_short_12","alias_value":"FYKEWG6JQ3YR","created_at":"2026-07-05T09:33:32Z"},{"alias_kind":"pith_short_16","alias_value":"FYKEWG6JQ3YRILG6","created_at":"2026-07-05T09:33:32Z"},{"alias_kind":"pith_short_8","alias_value":"FYKEWG6J","created_at":"2026-07-05T09:33:32Z"}],"graph_snapshots":[{"event_id":"sha256:5940335c2f97a8a1cd18d22880a0af267e7c6259db54a5576c230cbced8b57b0","target":"graph","created_at":"2026-07-05T09:33:32Z","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/2406.05839/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As more and more information-rich data like video become available, utilizing multi-modal auxiliary information to enhance audio tasks has sparked widespread research interest. The recent surge in research on LLM-based audio models provides fresh perspectives for tackling audio tasks. Given that LLM can flexibly ingest multiple inputs, we propose MaLa-ASR, an LLM-based ASR model that can integrate textual keywords extracted from presentation slides to improve recognition of conference content. MaLa-ASR yields average WERs of 9.4% and 11.7% on the L95 and S95 subsets of the SlideSpeech corpus, ","authors_text":"Fan Yu, Guanrou Yang, Shiliang Zhang, Xie Chen, Zhifu Gao, Ziyang Ma","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-09T16:00:00Z","title":"MaLa-ASR: Multimedia-Assisted LLM-Based ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05839","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":"sha256:4beea824a0cb287ee6df9221460c01b7ad93a4e99db082c209f9f7f69323cad1","target":"record","created_at":"2026-07-05T09:33:32Z","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":"597962f8e73c40119d187228b2fe8a4a0aea7ee1bbec0d46f6282311f3157c18","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-06-09T16:00:00Z","title_canon_sha256":"9fdaec674e7de5ab44ab303270943260aaddf6d5d2db64b2538d818a85ddcfae"},"schema_version":"1.0","source":{"id":"2406.05839","kind":"arxiv","version":2}},"canonical_sha256":"2e144b1bc986f1142cde36a1c59ce3d1ac170517e95efa6e9178b67f9374c353","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e144b1bc986f1142cde36a1c59ce3d1ac170517e95efa6e9178b67f9374c353","first_computed_at":"2026-07-05T09:33:32.883475Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:33:32.883475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T23RMEZEFVNI1XdB/C0SVdla2gRIKAAT8DwM2/Q/nUwpzqYv7HsdvJc90r+q3rtkr3qbFdgVFpvi38OVSW0UCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:33:32.884038Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.05839","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4beea824a0cb287ee6df9221460c01b7ad93a4e99db082c209f9f7f69323cad1","sha256:5940335c2f97a8a1cd18d22880a0af267e7c6259db54a5576c230cbced8b57b0"],"state_sha256":"738a1384fc1d6604a8410618dcc1d2263947fbba959930a136e921dd89cd48b8"}