{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TWBJBROKQBVEASU2T26YSESQWS","short_pith_number":"pith:TWBJBROK","schema_version":"1.0","canonical_sha256":"9d8290c5ca806a404a9a9ebd891250b4868e593d052fb78a4c4198f78aef7f86","source":{"kind":"arxiv","id":"2508.18701","version":1},"attestation_state":"computed","paper":{"title":"Attention2Probability: Attention-Driven Terminology Probability Estimation for Robust Speech-to-Text System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin Wang, Jingbo Zhu, Jin Qiu, Jun Zhang, Lu Huang, Tong Xiao, Xiaoqian Liu, Yanfan Du, Yuan Ge","submitted_at":"2025-08-26T06:08:17Z","abstract_excerpt":"Recent advances in speech large language models (SLMs) have improved speech recognition and translation in general domains, but accurately generating domain-specific terms or neologisms remains challenging. To address this, we propose Attention2Probability: attention-driven terminology probability estimation for robust speech-to-text system, which is lightweight, flexible, and accurate. Attention2Probability converts cross-attention weights between speech and terminology into presence probabilities, and it further employs curriculum learning to enhance retrieval accuracy. Furthermore, to tackl"},"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":"2508.18701","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-26T06:08:17Z","cross_cats_sorted":[],"title_canon_sha256":"37e01ac21ce607e48f605416e5b2328e651ba4dc44f13e412c89a6ed1d6d8dc2","abstract_canon_sha256":"d899945dc279fc4e34ff53dcdfb2f8064344de37f31263f9160ab3d24c7d77f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:29.469252Z","signature_b64":"Vbrr7QAZIlPUKsPJowPUsQDK3dOGqdYUqlvhrWDXRQoszBJ181s51RaSKIeoWC99QXBPlb2U1X/JZTkr9TGjCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d8290c5ca806a404a9a9ebd891250b4868e593d052fb78a4c4198f78aef7f86","last_reissued_at":"2026-07-05T11:59:29.468716Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:29.468716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attention2Probability: Attention-Driven Terminology Probability Estimation for Robust Speech-to-Text System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin Wang, Jingbo Zhu, Jin Qiu, Jun Zhang, Lu Huang, Tong Xiao, Xiaoqian Liu, Yanfan Du, Yuan Ge","submitted_at":"2025-08-26T06:08:17Z","abstract_excerpt":"Recent advances in speech large language models (SLMs) have improved speech recognition and translation in general domains, but accurately generating domain-specific terms or neologisms remains challenging. To address this, we propose Attention2Probability: attention-driven terminology probability estimation for robust speech-to-text system, which is lightweight, flexible, and accurate. Attention2Probability converts cross-attention weights between speech and terminology into presence probabilities, and it further employs curriculum learning to enhance retrieval accuracy. Furthermore, to tackl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18701","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/2508.18701/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":"2508.18701","created_at":"2026-07-05T11:59:29.468787+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.18701v1","created_at":"2026-07-05T11:59:29.468787+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18701","created_at":"2026-07-05T11:59:29.468787+00:00"},{"alias_kind":"pith_short_12","alias_value":"TWBJBROKQBVE","created_at":"2026-07-05T11:59:29.468787+00:00"},{"alias_kind":"pith_short_16","alias_value":"TWBJBROKQBVEASU2","created_at":"2026-07-05T11:59:29.468787+00:00"},{"alias_kind":"pith_short_8","alias_value":"TWBJBROK","created_at":"2026-07-05T11:59:29.468787+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TWBJBROKQBVEASU2T26YSESQWS","json":"https://pith.science/pith/TWBJBROKQBVEASU2T26YSESQWS.json","graph_json":"https://pith.science/api/pith-number/TWBJBROKQBVEASU2T26YSESQWS/graph.json","events_json":"https://pith.science/api/pith-number/TWBJBROKQBVEASU2T26YSESQWS/events.json","paper":"https://pith.science/paper/TWBJBROK"},"agent_actions":{"view_html":"https://pith.science/pith/TWBJBROKQBVEASU2T26YSESQWS","download_json":"https://pith.science/pith/TWBJBROKQBVEASU2T26YSESQWS.json","view_paper":"https://pith.science/paper/TWBJBROK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.18701&json=true","fetch_graph":"https://pith.science/api/pith-number/TWBJBROKQBVEASU2T26YSESQWS/graph.json","fetch_events":"https://pith.science/api/pith-number/TWBJBROKQBVEASU2T26YSESQWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TWBJBROKQBVEASU2T26YSESQWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TWBJBROKQBVEASU2T26YSESQWS/action/storage_attestation","attest_author":"https://pith.science/pith/TWBJBROKQBVEASU2T26YSESQWS/action/author_attestation","sign_citation":"https://pith.science/pith/TWBJBROKQBVEASU2T26YSESQWS/action/citation_signature","submit_replication":"https://pith.science/pith/TWBJBROKQBVEASU2T26YSESQWS/action/replication_record"}},"created_at":"2026-07-05T11:59:29.468787+00:00","updated_at":"2026-07-05T11:59:29.468787+00:00"}