{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HEQVVI7FTX37DR6JDHBZKDTNRD","short_pith_number":"pith:HEQVVI7F","schema_version":"1.0","canonical_sha256":"39215aa3e59df7f1c7c919c3950e6d88fcc57afee86687b648fbecb4352e39e1","source":{"kind":"arxiv","id":"2305.10649","version":1},"attestation_state":"computed","paper":{"title":"ZeroPrompt: Streaming Acoustic Encoders are Zero-Shot Masked LMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Binbin Zhang, Bo Dang, Di Wu, Fuping Pan, Xingchen Song, Zhendong Peng, Zhiyong Wu","submitted_at":"2023-05-18T02:08:33Z","abstract_excerpt":"In this paper, we present ZeroPrompt (Figure 1-(a)) and the corresponding Prompt-and-Refine strategy (Figure 3), two simple but effective \\textbf{training-free} methods to decrease the Token Display Time (TDT) of streaming ASR models \\textbf{without any accuracy loss}. The core idea of ZeroPrompt is to append zeroed content to each chunk during inference, which acts like a prompt to encourage the model to predict future tokens even before they were spoken. We argue that streaming acoustic encoders naturally have the modeling ability of Masked Language Models and our experiments demonstrate tha"},"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":"2305.10649","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-18T02:08:33Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"1820db54693e7d7ecad090ed57752299ef120f8658ee0cae52adcc80d240664e","abstract_canon_sha256":"2304f4ebdc7ffa39bddfe8953b9f350be1377488639eaceb24940ed60f2c496c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:58:09.888231Z","signature_b64":"KlvARY78yHvterSNjOz2bk/6Caw+J2kdkOROyBFMQsW9iUZLHHiJZoqbe6U6YtzVyoETqEjc9TiomswEL1PYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39215aa3e59df7f1c7c919c3950e6d88fcc57afee86687b648fbecb4352e39e1","last_reissued_at":"2026-07-05T06:58:09.887787Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:58:09.887787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ZeroPrompt: Streaming Acoustic Encoders are Zero-Shot Masked LMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Binbin Zhang, Bo Dang, Di Wu, Fuping Pan, Xingchen Song, Zhendong Peng, Zhiyong Wu","submitted_at":"2023-05-18T02:08:33Z","abstract_excerpt":"In this paper, we present ZeroPrompt (Figure 1-(a)) and the corresponding Prompt-and-Refine strategy (Figure 3), two simple but effective \\textbf{training-free} methods to decrease the Token Display Time (TDT) of streaming ASR models \\textbf{without any accuracy loss}. The core idea of ZeroPrompt is to append zeroed content to each chunk during inference, which acts like a prompt to encourage the model to predict future tokens even before they were spoken. We argue that streaming acoustic encoders naturally have the modeling ability of Masked Language Models and our experiments demonstrate tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10649","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/2305.10649/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":"2305.10649","created_at":"2026-07-05T06:58:09.887849+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.10649v1","created_at":"2026-07-05T06:58:09.887849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10649","created_at":"2026-07-05T06:58:09.887849+00:00"},{"alias_kind":"pith_short_12","alias_value":"HEQVVI7FTX37","created_at":"2026-07-05T06:58:09.887849+00:00"},{"alias_kind":"pith_short_16","alias_value":"HEQVVI7FTX37DR6J","created_at":"2026-07-05T06:58:09.887849+00:00"},{"alias_kind":"pith_short_8","alias_value":"HEQVVI7F","created_at":"2026-07-05T06:58:09.887849+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/HEQVVI7FTX37DR6JDHBZKDTNRD","json":"https://pith.science/pith/HEQVVI7FTX37DR6JDHBZKDTNRD.json","graph_json":"https://pith.science/api/pith-number/HEQVVI7FTX37DR6JDHBZKDTNRD/graph.json","events_json":"https://pith.science/api/pith-number/HEQVVI7FTX37DR6JDHBZKDTNRD/events.json","paper":"https://pith.science/paper/HEQVVI7F"},"agent_actions":{"view_html":"https://pith.science/pith/HEQVVI7FTX37DR6JDHBZKDTNRD","download_json":"https://pith.science/pith/HEQVVI7FTX37DR6JDHBZKDTNRD.json","view_paper":"https://pith.science/paper/HEQVVI7F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.10649&json=true","fetch_graph":"https://pith.science/api/pith-number/HEQVVI7FTX37DR6JDHBZKDTNRD/graph.json","fetch_events":"https://pith.science/api/pith-number/HEQVVI7FTX37DR6JDHBZKDTNRD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HEQVVI7FTX37DR6JDHBZKDTNRD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HEQVVI7FTX37DR6JDHBZKDTNRD/action/storage_attestation","attest_author":"https://pith.science/pith/HEQVVI7FTX37DR6JDHBZKDTNRD/action/author_attestation","sign_citation":"https://pith.science/pith/HEQVVI7FTX37DR6JDHBZKDTNRD/action/citation_signature","submit_replication":"https://pith.science/pith/HEQVVI7FTX37DR6JDHBZKDTNRD/action/replication_record"}},"created_at":"2026-07-05T06:58:09.887849+00:00","updated_at":"2026-07-05T06:58:09.887849+00:00"}