{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QURBN5LFPDXBWIEZNWTRNOXNAT","short_pith_number":"pith:QURBN5LF","schema_version":"1.0","canonical_sha256":"852216f56578ee1b20996da716baed04f4717a5acf11517d2845dd8e3622fe92","source":{"kind":"arxiv","id":"2505.14887","version":1},"attestation_state":"computed","paper":{"title":"In-Context Learning Boosts Speech Recognition via Human-like Adaptation to Speakers and Language Varieties","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Calbert Graham, Dan Jurafsky, Kim Tien Nguyen, Meghan Sumner, Nathan Roll, Yuka Tatsumi","submitted_at":"2025-05-20T20:20:37Z","abstract_excerpt":"Human listeners readily adjust to unfamiliar speakers and language varieties through exposure, but do these adaptation benefits extend to state-of-the-art spoken language models? We introduce a scalable framework that allows for in-context learning (ICL) in Phi-4 Multimodal using interleaved task prompts and audio-text pairs, and find that as few as 12 example utterances (~50 seconds) at inference time reduce word error rates by a relative 19.7% (1.2 pp.) on average across diverse English corpora. These improvements are most pronounced in low-resource varieties, when the context and target spe"},"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":"2505.14887","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-20T20:20:37Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"77a26ba27cfa77edb4c737457619550f0fe10fd2fb468be7016cfca105b22639","abstract_canon_sha256":"4295e67fe5874775ee0a05d611a34e51baeb776570dd2018e16f39951cc7dfc2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:56.335357Z","signature_b64":"QtibnPW3XCRJSUkOmXkPXTTnL1wg5TX0SnKwpvOzCuJEiVLh0tsjKYtf9fSfQNkHbMQ/0uNHfCD/T27iKufsCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"852216f56578ee1b20996da716baed04f4717a5acf11517d2845dd8e3622fe92","last_reissued_at":"2026-07-05T11:06:56.334818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:56.334818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In-Context Learning Boosts Speech Recognition via Human-like Adaptation to Speakers and Language Varieties","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Calbert Graham, Dan Jurafsky, Kim Tien Nguyen, Meghan Sumner, Nathan Roll, Yuka Tatsumi","submitted_at":"2025-05-20T20:20:37Z","abstract_excerpt":"Human listeners readily adjust to unfamiliar speakers and language varieties through exposure, but do these adaptation benefits extend to state-of-the-art spoken language models? We introduce a scalable framework that allows for in-context learning (ICL) in Phi-4 Multimodal using interleaved task prompts and audio-text pairs, and find that as few as 12 example utterances (~50 seconds) at inference time reduce word error rates by a relative 19.7% (1.2 pp.) on average across diverse English corpora. These improvements are most pronounced in low-resource varieties, when the context and target spe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14887","kind":"arxiv","version":1},"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/2505.14887/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":"2505.14887","created_at":"2026-07-05T11:06:56.334879+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.14887v1","created_at":"2026-07-05T11:06:56.334879+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14887","created_at":"2026-07-05T11:06:56.334879+00:00"},{"alias_kind":"pith_short_12","alias_value":"QURBN5LFPDXB","created_at":"2026-07-05T11:06:56.334879+00:00"},{"alias_kind":"pith_short_16","alias_value":"QURBN5LFPDXBWIEZ","created_at":"2026-07-05T11:06:56.334879+00:00"},{"alias_kind":"pith_short_8","alias_value":"QURBN5LF","created_at":"2026-07-05T11:06:56.334879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11219","citing_title":"Afrispeech Semantics: Evaluating Audio Semantic Reasoning in Spoken Language Models Across Domains and Accents","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01381","citing_title":"A framework for analyzing concept representations in neural models","ref_index":119,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QURBN5LFPDXBWIEZNWTRNOXNAT","json":"https://pith.science/pith/QURBN5LFPDXBWIEZNWTRNOXNAT.json","graph_json":"https://pith.science/api/pith-number/QURBN5LFPDXBWIEZNWTRNOXNAT/graph.json","events_json":"https://pith.science/api/pith-number/QURBN5LFPDXBWIEZNWTRNOXNAT/events.json","paper":"https://pith.science/paper/QURBN5LF"},"agent_actions":{"view_html":"https://pith.science/pith/QURBN5LFPDXBWIEZNWTRNOXNAT","download_json":"https://pith.science/pith/QURBN5LFPDXBWIEZNWTRNOXNAT.json","view_paper":"https://pith.science/paper/QURBN5LF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.14887&json=true","fetch_graph":"https://pith.science/api/pith-number/QURBN5LFPDXBWIEZNWTRNOXNAT/graph.json","fetch_events":"https://pith.science/api/pith-number/QURBN5LFPDXBWIEZNWTRNOXNAT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QURBN5LFPDXBWIEZNWTRNOXNAT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QURBN5LFPDXBWIEZNWTRNOXNAT/action/storage_attestation","attest_author":"https://pith.science/pith/QURBN5LFPDXBWIEZNWTRNOXNAT/action/author_attestation","sign_citation":"https://pith.science/pith/QURBN5LFPDXBWIEZNWTRNOXNAT/action/citation_signature","submit_replication":"https://pith.science/pith/QURBN5LFPDXBWIEZNWTRNOXNAT/action/replication_record"}},"created_at":"2026-07-05T11:06:56.334879+00:00","updated_at":"2026-07-05T11:06:56.334879+00:00"}