{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TTYGA6DNID6BDISGNW3IPPCNJN","short_pith_number":"pith:TTYGA6DN","schema_version":"1.0","canonical_sha256":"9cf060786d40fc11a2466db687bc4d4b6cb4b8e82ac7909a8aa0b76d353a077d","source":{"kind":"arxiv","id":"2509.06160","version":1},"attestation_state":"computed","paper":{"title":"Reverse-Engineered Reasoning for Open-Ended Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Fangzhen Lin, Ge Zhang, Haoran Que, Haozhe Wang, Jiazhan Feng, Minghao Liu, Qixin Xu, Tong Yang, Wangchunshu Zhou, Wanjun Zhong, Wei Ye, Wenhao Huang","submitted_at":"2025-09-07T18:07:58Z","abstract_excerpt":"While the ``deep reasoning'' paradigm has spurred significant advances in verifiable domains like mathematics, its application to open-ended, creative generation remains a critical challenge. The two dominant methods for instilling reasoning -- reinforcement learning (RL) and instruction distillation -- falter in this area; RL struggles with the absence of clear reward signals and high-quality reward models, while distillation is prohibitively expensive and capped by the teacher model's capabilities. To overcome these limitations, we introduce REverse-Engineered Reasoning (REER), a new paradig"},"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":"2509.06160","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-07T18:07:58Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f809fb960e0266ce0df36c8a17d5c81a7a1c65dd01cf961837493ce4c0afb98d","abstract_canon_sha256":"4f5e95ec2d6ab670748d076dcb614b17510e2b69df585ccb14c6dad59bba8653"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:30.821105Z","signature_b64":"2oKHS6vTW1wkuR1aU7iQHpDq9XWGAWJxWKFN8T+S5ZV6GwnambnHoLgPFeVnqAvgDrCX1rYIexPIlkFiZjoHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9cf060786d40fc11a2466db687bc4d4b6cb4b8e82ac7909a8aa0b76d353a077d","last_reissued_at":"2026-07-05T12:06:30.820608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:30.820608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reverse-Engineered Reasoning for Open-Ended Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Fangzhen Lin, Ge Zhang, Haoran Que, Haozhe Wang, Jiazhan Feng, Minghao Liu, Qixin Xu, Tong Yang, Wangchunshu Zhou, Wanjun Zhong, Wei Ye, Wenhao Huang","submitted_at":"2025-09-07T18:07:58Z","abstract_excerpt":"While the ``deep reasoning'' paradigm has spurred significant advances in verifiable domains like mathematics, its application to open-ended, creative generation remains a critical challenge. The two dominant methods for instilling reasoning -- reinforcement learning (RL) and instruction distillation -- falter in this area; RL struggles with the absence of clear reward signals and high-quality reward models, while distillation is prohibitively expensive and capped by the teacher model's capabilities. To overcome these limitations, we introduce REverse-Engineered Reasoning (REER), a new paradig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06160","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/2509.06160/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":"2509.06160","created_at":"2026-07-05T12:06:30.820670+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.06160v1","created_at":"2026-07-05T12:06:30.820670+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06160","created_at":"2026-07-05T12:06:30.820670+00:00"},{"alias_kind":"pith_short_12","alias_value":"TTYGA6DNID6B","created_at":"2026-07-05T12:06:30.820670+00:00"},{"alias_kind":"pith_short_16","alias_value":"TTYGA6DNID6BDISG","created_at":"2026-07-05T12:06:30.820670+00:00"},{"alias_kind":"pith_short_8","alias_value":"TTYGA6DN","created_at":"2026-07-05T12:06:30.820670+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08326","citing_title":"Diagnosing and Repairing Persona Collapse in LLM Advice","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25757","citing_title":"OPERA: Aligning Open-Ended Reasoning via Objective Perplexity-based Reinforcement Learning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18089","citing_title":"From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning","ref_index":151,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09709","citing_title":"IS-CoT: Breaking the Long-form Generation Collapse via Interleaved Structural Thinking","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03866","citing_title":"Taiji: Pareto Optimal Policy Optimization with Semantics-IDs Trade-off for Industrial LLM-Enhanced Recommendation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2510.25741","citing_title":"Scaling Latent Reasoning via Looped Language Models","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14054","citing_title":"Bad Seeing or Bad Thinking? Rewarding Perception for Multimodal Reasoning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14518","citing_title":"Mind DeepResearch Technical Report","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TTYGA6DNID6BDISGNW3IPPCNJN","json":"https://pith.science/pith/TTYGA6DNID6BDISGNW3IPPCNJN.json","graph_json":"https://pith.science/api/pith-number/TTYGA6DNID6BDISGNW3IPPCNJN/graph.json","events_json":"https://pith.science/api/pith-number/TTYGA6DNID6BDISGNW3IPPCNJN/events.json","paper":"https://pith.science/paper/TTYGA6DN"},"agent_actions":{"view_html":"https://pith.science/pith/TTYGA6DNID6BDISGNW3IPPCNJN","download_json":"https://pith.science/pith/TTYGA6DNID6BDISGNW3IPPCNJN.json","view_paper":"https://pith.science/paper/TTYGA6DN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.06160&json=true","fetch_graph":"https://pith.science/api/pith-number/TTYGA6DNID6BDISGNW3IPPCNJN/graph.json","fetch_events":"https://pith.science/api/pith-number/TTYGA6DNID6BDISGNW3IPPCNJN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TTYGA6DNID6BDISGNW3IPPCNJN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TTYGA6DNID6BDISGNW3IPPCNJN/action/storage_attestation","attest_author":"https://pith.science/pith/TTYGA6DNID6BDISGNW3IPPCNJN/action/author_attestation","sign_citation":"https://pith.science/pith/TTYGA6DNID6BDISGNW3IPPCNJN/action/citation_signature","submit_replication":"https://pith.science/pith/TTYGA6DNID6BDISGNW3IPPCNJN/action/replication_record"}},"created_at":"2026-07-05T12:06:30.820670+00:00","updated_at":"2026-07-05T12:06:30.820670+00:00"}