{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LIZ2WLZVURTJXTKXLIRSJALK4A","short_pith_number":"pith:LIZ2WLZV","schema_version":"1.0","canonical_sha256":"5a33ab2f35a4669bcd575a2324816ae02e6b9af0e4708e581bc3b2d58f4bde4c","source":{"kind":"arxiv","id":"2501.00868","version":1},"attestation_state":"computed","paper":{"title":"Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Shaolei Zhang, Shoutao Guo, Yang Feng, Zhengrui Ma","submitted_at":"2025-01-01T15:20:35Z","abstract_excerpt":"Simultaneous generation models write generation results while reading streaming inputs, necessitating a policy-maker to determine the appropriate output timing. Existing simultaneous generation methods generally adopt the traditional encoder-decoder architecture and learn the generation and policy-making capabilities through complex dynamic programming techniques. Although LLMs excel at text generation, they face challenges in taking on the role of policy-makers through traditional training methods, limiting their exploration in simultaneous generation. To overcome these limitations, we propos"},"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":"2501.00868","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-01T15:20:35Z","cross_cats_sorted":[],"title_canon_sha256":"141e8c08f0471280c436d1a9eafd340d92cef47e6750c99c379d1dee24820ba2","abstract_canon_sha256":"4414c07004a2c942d7b6db4a6ff864047739d12c3230152a2469b1a4f1737de0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:11.323763Z","signature_b64":"BWCyvjfwJQQMTKDynLNAinCXgjUZvQSXMCqfHchMkvXwn5ERuclzIuUA/FW+wlfI5IkTqZ6qXo2xbCHAKRDeBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a33ab2f35a4669bcd575a2324816ae02e6b9af0e4708e581bc3b2d58f4bde4c","last_reissued_at":"2026-07-05T09:56:11.323258Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:11.323258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Shaolei Zhang, Shoutao Guo, Yang Feng, Zhengrui Ma","submitted_at":"2025-01-01T15:20:35Z","abstract_excerpt":"Simultaneous generation models write generation results while reading streaming inputs, necessitating a policy-maker to determine the appropriate output timing. Existing simultaneous generation methods generally adopt the traditional encoder-decoder architecture and learn the generation and policy-making capabilities through complex dynamic programming techniques. Although LLMs excel at text generation, they face challenges in taking on the role of policy-makers through traditional training methods, limiting their exploration in simultaneous generation. To overcome these limitations, we propos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00868","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/2501.00868/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":"2501.00868","created_at":"2026-07-05T09:56:11.323324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00868v1","created_at":"2026-07-05T09:56:11.323324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00868","created_at":"2026-07-05T09:56:11.323324+00:00"},{"alias_kind":"pith_short_12","alias_value":"LIZ2WLZVURTJ","created_at":"2026-07-05T09:56:11.323324+00:00"},{"alias_kind":"pith_short_16","alias_value":"LIZ2WLZVURTJXTKX","created_at":"2026-07-05T09:56:11.323324+00:00"},{"alias_kind":"pith_short_8","alias_value":"LIZ2WLZV","created_at":"2026-07-05T09:56:11.323324+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.19810","citing_title":"SimulS2ST-Omni: Data-Efficient Streaming Speech-to-Speech Translation via Explicit Trajectory Supervision","ref_index":200,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LIZ2WLZVURTJXTKXLIRSJALK4A","json":"https://pith.science/pith/LIZ2WLZVURTJXTKXLIRSJALK4A.json","graph_json":"https://pith.science/api/pith-number/LIZ2WLZVURTJXTKXLIRSJALK4A/graph.json","events_json":"https://pith.science/api/pith-number/LIZ2WLZVURTJXTKXLIRSJALK4A/events.json","paper":"https://pith.science/paper/LIZ2WLZV"},"agent_actions":{"view_html":"https://pith.science/pith/LIZ2WLZVURTJXTKXLIRSJALK4A","download_json":"https://pith.science/pith/LIZ2WLZVURTJXTKXLIRSJALK4A.json","view_paper":"https://pith.science/paper/LIZ2WLZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00868&json=true","fetch_graph":"https://pith.science/api/pith-number/LIZ2WLZVURTJXTKXLIRSJALK4A/graph.json","fetch_events":"https://pith.science/api/pith-number/LIZ2WLZVURTJXTKXLIRSJALK4A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LIZ2WLZVURTJXTKXLIRSJALK4A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LIZ2WLZVURTJXTKXLIRSJALK4A/action/storage_attestation","attest_author":"https://pith.science/pith/LIZ2WLZVURTJXTKXLIRSJALK4A/action/author_attestation","sign_citation":"https://pith.science/pith/LIZ2WLZVURTJXTKXLIRSJALK4A/action/citation_signature","submit_replication":"https://pith.science/pith/LIZ2WLZVURTJXTKXLIRSJALK4A/action/replication_record"}},"created_at":"2026-07-05T09:56:11.323324+00:00","updated_at":"2026-07-05T09:56:11.323324+00:00"}