{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WUWTAUVNEJAE6ZWW2FDAVQ46SQ","short_pith_number":"pith:WUWTAUVN","schema_version":"1.0","canonical_sha256":"b52d3052ad22404f66d6d1460ac39e9428c9f99d1f8e2bcdcb81266a0b931b42","source":{"kind":"arxiv","id":"2606.00660","version":1},"attestation_state":"computed","paper":{"title":"FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bryan Hooi, Hui Chen, James Xu Zhao, See-kiong Ng","submitted_at":"2026-05-30T10:21:20Z","abstract_excerpt":"Agentic search requires language model agents to explore many sources and answer complex information-seeking questions. Scaling test-time compute is a promising way to improve these agents, but current approaches can fail, because correct answers are often sparse and score-based selection depends on model calibration. We propose FineVerify, a fine-grained self-verification framework that decomposes each question into checkable sub-questions, verifies sampled candidates against each sub-question, and selects the candidate with the highest aggregated score. This per-check structure turns selecti"},"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":"2606.00660","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-30T10:21:20Z","cross_cats_sorted":[],"title_canon_sha256":"bc71989a67dca06ba81d902564950d37f15d83878cc1323156c81d9ef4e308d9","abstract_canon_sha256":"1e0242cd48931b3430fd17b2a5be3d9931aef32501724a33e7e78e494c051aa3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:01.372650Z","signature_b64":"x5tdOIQlOMOwY1KPL2oePoI9FUlMzuB1d4aC/dkvScVla5f3v/VAQv/bVdtG790uh8J5jLZLqp0IMOteLHp3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b52d3052ad22404f66d6d1460ac39e9428c9f99d1f8e2bcdcb81266a0b931b42","last_reissued_at":"2026-06-02T01:04:01.372222Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:01.372222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bryan Hooi, Hui Chen, James Xu Zhao, See-kiong Ng","submitted_at":"2026-05-30T10:21:20Z","abstract_excerpt":"Agentic search requires language model agents to explore many sources and answer complex information-seeking questions. Scaling test-time compute is a promising way to improve these agents, but current approaches can fail, because correct answers are often sparse and score-based selection depends on model calibration. We propose FineVerify, a fine-grained self-verification framework that decomposes each question into checkable sub-questions, verifies sampled candidates against each sub-question, and selects the candidate with the highest aggregated score. This per-check structure turns selecti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00660","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/2606.00660/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":"2606.00660","created_at":"2026-06-02T01:04:01.372272+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00660v1","created_at":"2026-06-02T01:04:01.372272+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00660","created_at":"2026-06-02T01:04:01.372272+00:00"},{"alias_kind":"pith_short_12","alias_value":"WUWTAUVNEJAE","created_at":"2026-06-02T01:04:01.372272+00:00"},{"alias_kind":"pith_short_16","alias_value":"WUWTAUVNEJAE6ZWW","created_at":"2026-06-02T01:04:01.372272+00:00"},{"alias_kind":"pith_short_8","alias_value":"WUWTAUVN","created_at":"2026-06-02T01:04:01.372272+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/WUWTAUVNEJAE6ZWW2FDAVQ46SQ","json":"https://pith.science/pith/WUWTAUVNEJAE6ZWW2FDAVQ46SQ.json","graph_json":"https://pith.science/api/pith-number/WUWTAUVNEJAE6ZWW2FDAVQ46SQ/graph.json","events_json":"https://pith.science/api/pith-number/WUWTAUVNEJAE6ZWW2FDAVQ46SQ/events.json","paper":"https://pith.science/paper/WUWTAUVN"},"agent_actions":{"view_html":"https://pith.science/pith/WUWTAUVNEJAE6ZWW2FDAVQ46SQ","download_json":"https://pith.science/pith/WUWTAUVNEJAE6ZWW2FDAVQ46SQ.json","view_paper":"https://pith.science/paper/WUWTAUVN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00660&json=true","fetch_graph":"https://pith.science/api/pith-number/WUWTAUVNEJAE6ZWW2FDAVQ46SQ/graph.json","fetch_events":"https://pith.science/api/pith-number/WUWTAUVNEJAE6ZWW2FDAVQ46SQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WUWTAUVNEJAE6ZWW2FDAVQ46SQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WUWTAUVNEJAE6ZWW2FDAVQ46SQ/action/storage_attestation","attest_author":"https://pith.science/pith/WUWTAUVNEJAE6ZWW2FDAVQ46SQ/action/author_attestation","sign_citation":"https://pith.science/pith/WUWTAUVNEJAE6ZWW2FDAVQ46SQ/action/citation_signature","submit_replication":"https://pith.science/pith/WUWTAUVNEJAE6ZWW2FDAVQ46SQ/action/replication_record"}},"created_at":"2026-06-02T01:04:01.372272+00:00","updated_at":"2026-06-02T01:04:01.372272+00:00"}