{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GYF35QAHRV6X47RXAK6ND45HAZ","short_pith_number":"pith:GYF35QAH","schema_version":"1.0","canonical_sha256":"360bbec0078d7d7e7e3702bcd1f3a70659ff19c8241ac805b4b3d6390dca10db","source":{"kind":"arxiv","id":"2505.11966","version":1},"attestation_state":"computed","paper":{"title":"Solve-Detect-Verify: Inference-Time Scaling with Flexible Generative Verifier","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jianyuan Zhong, Kezhi Li, Qiang Xu, XiangYu Wen, Zeju Li, Zhijian Xu","submitted_at":"2025-05-17T11:41:44Z","abstract_excerpt":"Large Language Model (LLM) reasoning for complex tasks inherently involves a trade-off between solution accuracy and computational efficiency. The subsequent step of verification, while intended to improve performance, further complicates this landscape by introducing its own challenging trade-off: sophisticated Generative Reward Models (GenRMs) can be computationally prohibitive if naively integrated with LLMs at test-time, while simpler, faster methods may lack reliability. To overcome these challenges, we introduce FlexiVe, a novel generative verifier that flexibly balances computational re"},"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":"2505.11966","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-17T11:41:44Z","cross_cats_sorted":[],"title_canon_sha256":"613c3154f5ab88ae81c2568fa58dd61c9a8356838ff53df5f190cac7e315c690","abstract_canon_sha256":"0e0c2cecacb49b9d8e61378ce5d8c2e6d424c1593df6dd87e2ffcedbea48fef6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:55.577986Z","signature_b64":"b+tOTRvlFG3fadSn5Sj/2BNNfBCV5qnOd+SZ7x4vKnQDjkEvrHEl6buHCrd5L/fjJFSK+h5km8H43anhwC4RBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"360bbec0078d7d7e7e3702bcd1f3a70659ff19c8241ac805b4b3d6390dca10db","last_reissued_at":"2026-07-05T11:04:55.577586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:55.577586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Solve-Detect-Verify: Inference-Time Scaling with Flexible Generative Verifier","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jianyuan Zhong, Kezhi Li, Qiang Xu, XiangYu Wen, Zeju Li, Zhijian Xu","submitted_at":"2025-05-17T11:41:44Z","abstract_excerpt":"Large Language Model (LLM) reasoning for complex tasks inherently involves a trade-off between solution accuracy and computational efficiency. The subsequent step of verification, while intended to improve performance, further complicates this landscape by introducing its own challenging trade-off: sophisticated Generative Reward Models (GenRMs) can be computationally prohibitive if naively integrated with LLMs at test-time, while simpler, faster methods may lack reliability. To overcome these challenges, we introduce FlexiVe, a novel generative verifier that flexibly balances computational re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11966","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/2505.11966/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":"2505.11966","created_at":"2026-07-05T11:04:55.577652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11966v1","created_at":"2026-07-05T11:04:55.577652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11966","created_at":"2026-07-05T11:04:55.577652+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYF35QAHRV6X","created_at":"2026-07-05T11:04:55.577652+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYF35QAHRV6X47RX","created_at":"2026-07-05T11:04:55.577652+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYF35QAH","created_at":"2026-07-05T11:04:55.577652+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/GYF35QAHRV6X47RXAK6ND45HAZ","json":"https://pith.science/pith/GYF35QAHRV6X47RXAK6ND45HAZ.json","graph_json":"https://pith.science/api/pith-number/GYF35QAHRV6X47RXAK6ND45HAZ/graph.json","events_json":"https://pith.science/api/pith-number/GYF35QAHRV6X47RXAK6ND45HAZ/events.json","paper":"https://pith.science/paper/GYF35QAH"},"agent_actions":{"view_html":"https://pith.science/pith/GYF35QAHRV6X47RXAK6ND45HAZ","download_json":"https://pith.science/pith/GYF35QAHRV6X47RXAK6ND45HAZ.json","view_paper":"https://pith.science/paper/GYF35QAH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11966&json=true","fetch_graph":"https://pith.science/api/pith-number/GYF35QAHRV6X47RXAK6ND45HAZ/graph.json","fetch_events":"https://pith.science/api/pith-number/GYF35QAHRV6X47RXAK6ND45HAZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYF35QAHRV6X47RXAK6ND45HAZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYF35QAHRV6X47RXAK6ND45HAZ/action/storage_attestation","attest_author":"https://pith.science/pith/GYF35QAHRV6X47RXAK6ND45HAZ/action/author_attestation","sign_citation":"https://pith.science/pith/GYF35QAHRV6X47RXAK6ND45HAZ/action/citation_signature","submit_replication":"https://pith.science/pith/GYF35QAHRV6X47RXAK6ND45HAZ/action/replication_record"}},"created_at":"2026-07-05T11:04:55.577652+00:00","updated_at":"2026-07-05T11:04:55.577652+00:00"}