{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OARVQ6EPQYJXAYSLFTHEE2TMUN","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":"b48232b9a71d4f31bb9c0b1ccb026a5e03ba508f3cc2645d179f7fca9301abd3","cross_cats_sorted":["cs.CL","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-25T07:46:40Z","title_canon_sha256":"da73db5783971de12ac550008c7ba93cc7347ce3315c62c5b69737bc5bf04abe"},"schema_version":"1.0","source":{"id":"2507.19037","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.19037","created_at":"2026-07-05T11:43:18Z"},{"alias_kind":"arxiv_version","alias_value":"2507.19037v1","created_at":"2026-07-05T11:43:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.19037","created_at":"2026-07-05T11:43:18Z"},{"alias_kind":"pith_short_12","alias_value":"OARVQ6EPQYJX","created_at":"2026-07-05T11:43:18Z"},{"alias_kind":"pith_short_16","alias_value":"OARVQ6EPQYJXAYSL","created_at":"2026-07-05T11:43:18Z"},{"alias_kind":"pith_short_8","alias_value":"OARVQ6EP","created_at":"2026-07-05T11:43:18Z"}],"graph_snapshots":[{"event_id":"sha256:a06058b7c14d3285d92b13002ada29460a5105a9dc996b978e8f31544b7bf272","target":"graph","created_at":"2026-07-05T11:43:18Z","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/2507.19037/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in multi-modal large language models (MLLMs) have opened new possibilities for unified modeling of speech, text, images, and other modalities. Building on our prior work, this paper examines the conditions and model architectures under which multiple input modalities can improve automatic speech recognition (ASR) accuracy in noisy environments. Through experiments on synthetic and real-world data, we find that (1) harnessing more modalities usually improves ASR accuracy, as each modality provides complementary information, but the improvement depends on the amount of auditory n","authors_text":"Jacob Whitehill, Viet Anh Trinh, Vivek Voleti, Yiwen Guan","cross_cats":["cs.CL","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-25T07:46:40Z","title":"MLLM-based Speech Recognition: When and How is Multimodality Beneficial?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.19037","kind":"arxiv","version":1},"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":"sha256:2b6b037721849171086fe6a07b016a282917f901ada7f28634a9cd28e1cfa9a8","target":"record","created_at":"2026-07-05T11:43:18Z","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":"b48232b9a71d4f31bb9c0b1ccb026a5e03ba508f3cc2645d179f7fca9301abd3","cross_cats_sorted":["cs.CL","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-07-25T07:46:40Z","title_canon_sha256":"da73db5783971de12ac550008c7ba93cc7347ce3315c62c5b69737bc5bf04abe"},"schema_version":"1.0","source":{"id":"2507.19037","kind":"arxiv","version":1}},"canonical_sha256":"702358788f861370624b2cce426a6ca3694b8d34659bc954eaf6a42a57187237","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"702358788f861370624b2cce426a6ca3694b8d34659bc954eaf6a42a57187237","first_computed_at":"2026-07-05T11:43:18.410452Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:18.410452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TAFqTUxlIxP8o76BmnAiCOl2y5sonxvqQLJnrgwJsQf+Xh1IdaG8GBUjTp+dq+FsND3Ik9BR/agHC2VYLHNGAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:18.410947Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.19037","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b6b037721849171086fe6a07b016a282917f901ada7f28634a9cd28e1cfa9a8","sha256:a06058b7c14d3285d92b13002ada29460a5105a9dc996b978e8f31544b7bf272"],"state_sha256":"f3f891f29a2d294385cae1865c7dca74ab5cc3ec2d50b209045ce229bf8b9241"}