{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:I7O4CQITCPIMNVRF2X7SXPD3XM","short_pith_number":"pith:I7O4CQIT","schema_version":"1.0","canonical_sha256":"47ddc1411313d0c6d625d5ff2bbc7bbb1b4e3af510ffe914a32eb2e40fba35a5","source":{"kind":"arxiv","id":"2502.01839","version":2},"attestation_state":"computed","paper":{"title":"Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Eric Zhao, Pranjal Awasthi, Sreenivas Gollapudi","submitted_at":"2025-02-03T21:31:07Z","abstract_excerpt":"Sampling-based search, a simple paradigm for utilizing test-time compute, involves generating multiple candidate responses and selecting the best one -- typically by having models self-verify each response for correctness. In this paper, we study the scaling trends governing sampling-based search. Among our findings is that simply scaling up a minimalist implementation of sampling-based search, using only random sampling and direct self-verification, provides a practical inference method that, for example, elevates the reasoning capabilities of Gemini v1.5 Pro above that of o1-Preview on popul"},"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":"2502.01839","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-03T21:31:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fb1432fe2cf3bd32523ea6db58db9dc94f5dfed48719a0653f1ac8a74a1b75dd","abstract_canon_sha256":"3d24b3b2ccfda6fd8e5d80590014f0b610aee5451ff201c1e545271cb31b43ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:15.695064Z","signature_b64":"cIsUhYOllqyo3Vu+vF/PVbju3DeWfxDXBAh3mBMQiuN/UcBufiezMUajc9yaxS2DEZYUd3raBFPXd1H+SH87AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47ddc1411313d0c6d625d5ff2bbc7bbb1b4e3af510ffe914a32eb2e40fba35a5","last_reissued_at":"2026-07-05T10:17:15.694529Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:15.694529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Eric Zhao, Pranjal Awasthi, Sreenivas Gollapudi","submitted_at":"2025-02-03T21:31:07Z","abstract_excerpt":"Sampling-based search, a simple paradigm for utilizing test-time compute, involves generating multiple candidate responses and selecting the best one -- typically by having models self-verify each response for correctness. In this paper, we study the scaling trends governing sampling-based search. Among our findings is that simply scaling up a minimalist implementation of sampling-based search, using only random sampling and direct self-verification, provides a practical inference method that, for example, elevates the reasoning capabilities of Gemini v1.5 Pro above that of o1-Preview on popul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01839","kind":"arxiv","version":2},"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/2502.01839/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":"2502.01839","created_at":"2026-07-05T10:17:15.694592+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.01839v2","created_at":"2026-07-05T10:17:15.694592+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01839","created_at":"2026-07-05T10:17:15.694592+00:00"},{"alias_kind":"pith_short_12","alias_value":"I7O4CQITCPIM","created_at":"2026-07-05T10:17:15.694592+00:00"},{"alias_kind":"pith_short_16","alias_value":"I7O4CQITCPIMNVRF","created_at":"2026-07-05T10:17:15.694592+00:00"},{"alias_kind":"pith_short_8","alias_value":"I7O4CQIT","created_at":"2026-07-05T10:17:15.694592+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12402","citing_title":"DIRECT: When and Where Should You Allocate Test-Time Compute in Embodied Planners?","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00817","citing_title":"When LLMs Stop Following Steps: A Diagnostic Study of Procedural Execution in Language Models","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20531","citing_title":"Pseudo-Formalization for Automatic Proof Verification","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20531","citing_title":"Pseudo-Formalization for Automatic Proof Verification","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2506.06941","citing_title":"The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04944","citing_title":"Inclusion-of-Thoughts: Mitigating Preference Instability via Purifying the Decision Space","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00817","citing_title":"When LLMs Stop Following Steps: A Diagnostic Study of Procedural Execution in Language Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18547","citing_title":"FUSE: Ensembling Verifiers with Zero Labeled Data","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I7O4CQITCPIMNVRF2X7SXPD3XM","json":"https://pith.science/pith/I7O4CQITCPIMNVRF2X7SXPD3XM.json","graph_json":"https://pith.science/api/pith-number/I7O4CQITCPIMNVRF2X7SXPD3XM/graph.json","events_json":"https://pith.science/api/pith-number/I7O4CQITCPIMNVRF2X7SXPD3XM/events.json","paper":"https://pith.science/paper/I7O4CQIT"},"agent_actions":{"view_html":"https://pith.science/pith/I7O4CQITCPIMNVRF2X7SXPD3XM","download_json":"https://pith.science/pith/I7O4CQITCPIMNVRF2X7SXPD3XM.json","view_paper":"https://pith.science/paper/I7O4CQIT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.01839&json=true","fetch_graph":"https://pith.science/api/pith-number/I7O4CQITCPIMNVRF2X7SXPD3XM/graph.json","fetch_events":"https://pith.science/api/pith-number/I7O4CQITCPIMNVRF2X7SXPD3XM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I7O4CQITCPIMNVRF2X7SXPD3XM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I7O4CQITCPIMNVRF2X7SXPD3XM/action/storage_attestation","attest_author":"https://pith.science/pith/I7O4CQITCPIMNVRF2X7SXPD3XM/action/author_attestation","sign_citation":"https://pith.science/pith/I7O4CQITCPIMNVRF2X7SXPD3XM/action/citation_signature","submit_replication":"https://pith.science/pith/I7O4CQITCPIMNVRF2X7SXPD3XM/action/replication_record"}},"created_at":"2026-07-05T10:17:15.694592+00:00","updated_at":"2026-07-05T10:17:15.694592+00:00"}