{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5NFA33AX3J4HAD5C2AYR7A7F2J","short_pith_number":"pith:5NFA33AX","schema_version":"1.0","canonical_sha256":"eb4a0dec17da78700fa2d0311f83e5d266047ff0fd0694401b845e200a30873b","source":{"kind":"arxiv","id":"2502.11157","version":1},"attestation_state":"computed","paper":{"title":"Dyve: Thinking Fast and Slow for Dynamic Process Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jianyuan Zhong, Qiang Xu, XiangYu Wen, Zeju Li, Zhijian Xu","submitted_at":"2025-02-16T15:11:19Z","abstract_excerpt":"We present Dyve, a dynamic process verifier that enhances reasoning error detection in large language models by integrating fast and slow thinking, inspired by Kahneman's Systems Theory. Dyve adaptively applies immediate token-level confirmation System 1 for straightforward steps and comprehensive analysis System 2 for complex ones. Leveraging a novel step-wise consensus-filtered process supervision technique, combining Monte Carlo estimation with LLM based evaluation, Dyve curates high-quality supervision signals from noisy data. Experimental results on ProcessBench and the MATH dataset confi"},"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":"2502.11157","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-16T15:11:19Z","cross_cats_sorted":[],"title_canon_sha256":"80b9e03e19130c6b491ec75c43df9f4527c24eeaa20759c3414b5f35330d69bb","abstract_canon_sha256":"92ad2bbc5d3bb1fe405667f24817853257f66372b3d7424864506165871effdf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:04.509735Z","signature_b64":"Bs/7UHokCIzsmAPomorYxN3jwyqhuxs58o0CIsH24XIOOp4eAAFwgdb19ZqKEDBit4ZHDn1RYfYu9EGhLzkhCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb4a0dec17da78700fa2d0311f83e5d266047ff0fd0694401b845e200a30873b","last_reissued_at":"2026-07-05T10:15:04.509231Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:04.509231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dyve: Thinking Fast and Slow for Dynamic Process Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jianyuan Zhong, Qiang Xu, XiangYu Wen, Zeju Li, Zhijian Xu","submitted_at":"2025-02-16T15:11:19Z","abstract_excerpt":"We present Dyve, a dynamic process verifier that enhances reasoning error detection in large language models by integrating fast and slow thinking, inspired by Kahneman's Systems Theory. Dyve adaptively applies immediate token-level confirmation System 1 for straightforward steps and comprehensive analysis System 2 for complex ones. Leveraging a novel step-wise consensus-filtered process supervision technique, combining Monte Carlo estimation with LLM based evaluation, Dyve curates high-quality supervision signals from noisy data. Experimental results on ProcessBench and the MATH dataset confi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11157","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/2502.11157/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":"2502.11157","created_at":"2026-07-05T10:15:04.509294+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.11157v1","created_at":"2026-07-05T10:15:04.509294+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11157","created_at":"2026-07-05T10:15:04.509294+00:00"},{"alias_kind":"pith_short_12","alias_value":"5NFA33AX3J4H","created_at":"2026-07-05T10:15:04.509294+00:00"},{"alias_kind":"pith_short_16","alias_value":"5NFA33AX3J4HAD5C","created_at":"2026-07-05T10:15:04.509294+00:00"},{"alias_kind":"pith_short_8","alias_value":"5NFA33AX","created_at":"2026-07-05T10:15:04.509294+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.11966","citing_title":"Solve-Detect-Verify: Inference-Time Scaling with Flexible Generative Verifier","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5NFA33AX3J4HAD5C2AYR7A7F2J","json":"https://pith.science/pith/5NFA33AX3J4HAD5C2AYR7A7F2J.json","graph_json":"https://pith.science/api/pith-number/5NFA33AX3J4HAD5C2AYR7A7F2J/graph.json","events_json":"https://pith.science/api/pith-number/5NFA33AX3J4HAD5C2AYR7A7F2J/events.json","paper":"https://pith.science/paper/5NFA33AX"},"agent_actions":{"view_html":"https://pith.science/pith/5NFA33AX3J4HAD5C2AYR7A7F2J","download_json":"https://pith.science/pith/5NFA33AX3J4HAD5C2AYR7A7F2J.json","view_paper":"https://pith.science/paper/5NFA33AX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.11157&json=true","fetch_graph":"https://pith.science/api/pith-number/5NFA33AX3J4HAD5C2AYR7A7F2J/graph.json","fetch_events":"https://pith.science/api/pith-number/5NFA33AX3J4HAD5C2AYR7A7F2J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5NFA33AX3J4HAD5C2AYR7A7F2J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5NFA33AX3J4HAD5C2AYR7A7F2J/action/storage_attestation","attest_author":"https://pith.science/pith/5NFA33AX3J4HAD5C2AYR7A7F2J/action/author_attestation","sign_citation":"https://pith.science/pith/5NFA33AX3J4HAD5C2AYR7A7F2J/action/citation_signature","submit_replication":"https://pith.science/pith/5NFA33AX3J4HAD5C2AYR7A7F2J/action/replication_record"}},"created_at":"2026-07-05T10:15:04.509294+00:00","updated_at":"2026-07-05T10:15:04.509294+00:00"}