{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HHK6FSKDO4S55XJB4K5NQ57X6C","short_pith_number":"pith:HHK6FSKD","schema_version":"1.0","canonical_sha256":"39d5e2c9437725dedd21e2bad877f7f089e0f03fedf39452d648f5a6f94c7c24","source":{"kind":"arxiv","id":"2605.20075","version":1},"attestation_state":"computed","paper":{"title":"CopT: Contrastive On-Policy Thinking with Continuous Spaces for General and Agentic Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dachuan Shi, Hanlin Zhu, Kejing Xia, Wanjia Zhao, Wenke Lee, Wen Xiao, Xiangchi Yuan","submitted_at":"2026-05-19T16:28:53Z","abstract_excerpt":"Chain-of-thought (CoT) is a standard approach for eliciting reasoning capabilities from large language models (LLMs). However, the common CoT paradigm treats thinking as a prerequisite for answering, which can delay access to plausible answers and incur unnecessary token costs even when the model is able to identify an answer before extended thinking, a behavior known as performative reasoning. In this paper, we introduce CopT, a reformulated reasoning pipeline that reverses the usual order of thinking and answering. Instead of thinking before answering, CopT first elicits a draft answer and t"},"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":"2605.20075","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-19T16:28:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"738cd4f190d0aa415b974cdd042e9caff4cca1f2408b114afa053836a392423d","abstract_canon_sha256":"41f150b0b2b799f53fa2770dc6c4e9d3f8c85f0f87707065714a091c081220ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T02:06:01.121203Z","signature_b64":"JXQlquNDYFAnpTztqXFUYAVLWdhT7wmRrQde2NZZ0pfmAYE1LisDzW0daHg04h6ecT8uNZhs6X4mHHrs4xlZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39d5e2c9437725dedd21e2bad877f7f089e0f03fedf39452d648f5a6f94c7c24","last_reissued_at":"2026-05-20T02:06:01.120725Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T02:06:01.120725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CopT: Contrastive On-Policy Thinking with Continuous Spaces for General and Agentic Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dachuan Shi, Hanlin Zhu, Kejing Xia, Wanjia Zhao, Wenke Lee, Wen Xiao, Xiangchi Yuan","submitted_at":"2026-05-19T16:28:53Z","abstract_excerpt":"Chain-of-thought (CoT) is a standard approach for eliciting reasoning capabilities from large language models (LLMs). However, the common CoT paradigm treats thinking as a prerequisite for answering, which can delay access to plausible answers and incur unnecessary token costs even when the model is able to identify an answer before extended thinking, a behavior known as performative reasoning. In this paper, we introduce CopT, a reformulated reasoning pipeline that reverses the usual order of thinking and answering. Instead of thinking before answering, CopT first elicits a draft answer and t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20075","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/2605.20075/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":"2605.20075","created_at":"2026-05-20T02:06:01.120798+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20075v1","created_at":"2026-05-20T02:06:01.120798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20075","created_at":"2026-05-20T02:06:01.120798+00:00"},{"alias_kind":"pith_short_12","alias_value":"HHK6FSKDO4S5","created_at":"2026-05-20T02:06:01.120798+00:00"},{"alias_kind":"pith_short_16","alias_value":"HHK6FSKDO4S55XJB","created_at":"2026-05-20T02:06:01.120798+00:00"},{"alias_kind":"pith_short_8","alias_value":"HHK6FSKD","created_at":"2026-05-20T02:06:01.120798+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/HHK6FSKDO4S55XJB4K5NQ57X6C","json":"https://pith.science/pith/HHK6FSKDO4S55XJB4K5NQ57X6C.json","graph_json":"https://pith.science/api/pith-number/HHK6FSKDO4S55XJB4K5NQ57X6C/graph.json","events_json":"https://pith.science/api/pith-number/HHK6FSKDO4S55XJB4K5NQ57X6C/events.json","paper":"https://pith.science/paper/HHK6FSKD"},"agent_actions":{"view_html":"https://pith.science/pith/HHK6FSKDO4S55XJB4K5NQ57X6C","download_json":"https://pith.science/pith/HHK6FSKDO4S55XJB4K5NQ57X6C.json","view_paper":"https://pith.science/paper/HHK6FSKD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20075&json=true","fetch_graph":"https://pith.science/api/pith-number/HHK6FSKDO4S55XJB4K5NQ57X6C/graph.json","fetch_events":"https://pith.science/api/pith-number/HHK6FSKDO4S55XJB4K5NQ57X6C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HHK6FSKDO4S55XJB4K5NQ57X6C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HHK6FSKDO4S55XJB4K5NQ57X6C/action/storage_attestation","attest_author":"https://pith.science/pith/HHK6FSKDO4S55XJB4K5NQ57X6C/action/author_attestation","sign_citation":"https://pith.science/pith/HHK6FSKDO4S55XJB4K5NQ57X6C/action/citation_signature","submit_replication":"https://pith.science/pith/HHK6FSKDO4S55XJB4K5NQ57X6C/action/replication_record"}},"created_at":"2026-05-20T02:06:01.120798+00:00","updated_at":"2026-05-20T02:06:01.120798+00:00"}