{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:F3GCK6BL4DCIKQKY65LB4W6SMP","short_pith_number":"pith:F3GCK6BL","canonical_record":{"source":{"id":"2501.13007","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-22T16:49:37Z","cross_cats_sorted":[],"title_canon_sha256":"9d92268e5dfe1d60bce843745a595ef0baa6873ef86f0cda29528cc5b46e3625","abstract_canon_sha256":"59ff0f3aef01faca64a7cbe9e82a96286792025bd1de92d5e0280c5564afce5f"},"schema_version":"1.0"},"canonical_sha256":"2ecc25782be0c4854158f7561e5bd263e6dd257fd53bcf47669d9e9f17f877f6","source":{"kind":"arxiv","id":"2501.13007","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.13007","created_at":"2026-07-05T10:16:41Z"},{"alias_kind":"arxiv_version","alias_value":"2501.13007v2","created_at":"2026-07-05T10:16:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13007","created_at":"2026-07-05T10:16:41Z"},{"alias_kind":"pith_short_12","alias_value":"F3GCK6BL4DCI","created_at":"2026-07-05T10:16:41Z"},{"alias_kind":"pith_short_16","alias_value":"F3GCK6BL4DCIKQKY","created_at":"2026-07-05T10:16:41Z"},{"alias_kind":"pith_short_8","alias_value":"F3GCK6BL","created_at":"2026-07-05T10:16:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:F3GCK6BL4DCIKQKY65LB4W6SMP","target":"record","payload":{"canonical_record":{"source":{"id":"2501.13007","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-22T16:49:37Z","cross_cats_sorted":[],"title_canon_sha256":"9d92268e5dfe1d60bce843745a595ef0baa6873ef86f0cda29528cc5b46e3625","abstract_canon_sha256":"59ff0f3aef01faca64a7cbe9e82a96286792025bd1de92d5e0280c5564afce5f"},"schema_version":"1.0"},"canonical_sha256":"2ecc25782be0c4854158f7561e5bd263e6dd257fd53bcf47669d9e9f17f877f6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:41.075603Z","signature_b64":"eTgRNaEDd5WiHPXk/9zQXl2Xx400jvrv8HJ0i2hOOLUNYoPyTMhq4gikrshTk2OtoaifUOM0Sl3nLXiSsVtwBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ecc25782be0c4854158f7561e5bd263e6dd257fd53bcf47669d9e9f17f877f6","last_reissued_at":"2026-07-05T10:16:41.075174Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:41.075174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.13007","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:16:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IkCnUimX0Pk4QYOHkIUKrn+FdxXhhvYYj6h2Xf1c+GosN0ZJjdM5b/f8S3+0Gfg3KbyOak68aFPsA0M/Ny0QAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:02:14.611080Z"},"content_sha256":"29ecc120d804b2451f7f23cf6254100a7ca143eaa1670d7ed5cdb66f1d9ca98d","schema_version":"1.0","event_id":"sha256:29ecc120d804b2451f7f23cf6254100a7ca143eaa1670d7ed5cdb66f1d9ca98d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:F3GCK6BL4DCIKQKY65LB4W6SMP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PairJudge RM: Perform Best-of-N Sampling with Knockout Tournament","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Juanzi Li, Lei Hou, Rui Min, Yantao Liu, Yixin Cao, Zijun Yao","submitted_at":"2025-01-22T16:49:37Z","abstract_excerpt":"Best-of-N (BoN) sampling, a common strategy for test-time scaling of Large Language Models (LLMs), relies on reward models to select the best candidate solution from multiple generations. However, traditional reward models often assign arbitrary and inconsistent scores, limiting their effectiveness. To address this, we propose a Pairwise Judge Reward Model (PariJudge RM) combined with a knockout tournament for BoN sampling. Instead of assigning absolute scores, given one math problem, PariJudge RM judges two candidate solutions' correctness with chain-of-thought reasoning simultaneously. This "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13007","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/2501.13007/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:16:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RrfIWr9pMDBS0RtYJxZVvYflUkUGoM90vjuxbKzKLxTavoVkulOCYr1FQfwH6jeVU8/RZoVcOnIvQAxcodbiAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:02:14.611459Z"},"content_sha256":"14b6f42b565e3487fedb588344518c791d1f8ae991a0c6b019c2d605c46c7dec","schema_version":"1.0","event_id":"sha256:14b6f42b565e3487fedb588344518c791d1f8ae991a0c6b019c2d605c46c7dec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F3GCK6BL4DCIKQKY65LB4W6SMP/bundle.json","state_url":"https://pith.science/pith/F3GCK6BL4DCIKQKY65LB4W6SMP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F3GCK6BL4DCIKQKY65LB4W6SMP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T10:02:14Z","links":{"resolver":"https://pith.science/pith/F3GCK6BL4DCIKQKY65LB4W6SMP","bundle":"https://pith.science/pith/F3GCK6BL4DCIKQKY65LB4W6SMP/bundle.json","state":"https://pith.science/pith/F3GCK6BL4DCIKQKY65LB4W6SMP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F3GCK6BL4DCIKQKY65LB4W6SMP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:F3GCK6BL4DCIKQKY65LB4W6SMP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"59ff0f3aef01faca64a7cbe9e82a96286792025bd1de92d5e0280c5564afce5f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-22T16:49:37Z","title_canon_sha256":"9d92268e5dfe1d60bce843745a595ef0baa6873ef86f0cda29528cc5b46e3625"},"schema_version":"1.0","source":{"id":"2501.13007","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.13007","created_at":"2026-07-05T10:16:41Z"},{"alias_kind":"arxiv_version","alias_value":"2501.13007v2","created_at":"2026-07-05T10:16:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13007","created_at":"2026-07-05T10:16:41Z"},{"alias_kind":"pith_short_12","alias_value":"F3GCK6BL4DCI","created_at":"2026-07-05T10:16:41Z"},{"alias_kind":"pith_short_16","alias_value":"F3GCK6BL4DCIKQKY","created_at":"2026-07-05T10:16:41Z"},{"alias_kind":"pith_short_8","alias_value":"F3GCK6BL","created_at":"2026-07-05T10:16:41Z"}],"graph_snapshots":[{"event_id":"sha256:14b6f42b565e3487fedb588344518c791d1f8ae991a0c6b019c2d605c46c7dec","target":"graph","created_at":"2026-07-05T10:16:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.13007/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Best-of-N (BoN) sampling, a common strategy for test-time scaling of Large Language Models (LLMs), relies on reward models to select the best candidate solution from multiple generations. However, traditional reward models often assign arbitrary and inconsistent scores, limiting their effectiveness. To address this, we propose a Pairwise Judge Reward Model (PariJudge RM) combined with a knockout tournament for BoN sampling. Instead of assigning absolute scores, given one math problem, PariJudge RM judges two candidate solutions' correctness with chain-of-thought reasoning simultaneously. This ","authors_text":"Juanzi Li, Lei Hou, Rui Min, Yantao Liu, Yixin Cao, Zijun Yao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-22T16:49:37Z","title":"PairJudge RM: Perform Best-of-N Sampling with Knockout Tournament"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13007","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:29ecc120d804b2451f7f23cf6254100a7ca143eaa1670d7ed5cdb66f1d9ca98d","target":"record","created_at":"2026-07-05T10:16:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"59ff0f3aef01faca64a7cbe9e82a96286792025bd1de92d5e0280c5564afce5f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-22T16:49:37Z","title_canon_sha256":"9d92268e5dfe1d60bce843745a595ef0baa6873ef86f0cda29528cc5b46e3625"},"schema_version":"1.0","source":{"id":"2501.13007","kind":"arxiv","version":2}},"canonical_sha256":"2ecc25782be0c4854158f7561e5bd263e6dd257fd53bcf47669d9e9f17f877f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2ecc25782be0c4854158f7561e5bd263e6dd257fd53bcf47669d9e9f17f877f6","first_computed_at":"2026-07-05T10:16:41.075174Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:16:41.075174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eTgRNaEDd5WiHPXk/9zQXl2Xx400jvrv8HJ0i2hOOLUNYoPyTMhq4gikrshTk2OtoaifUOM0Sl3nLXiSsVtwBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:16:41.075603Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.13007","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:29ecc120d804b2451f7f23cf6254100a7ca143eaa1670d7ed5cdb66f1d9ca98d","sha256:14b6f42b565e3487fedb588344518c791d1f8ae991a0c6b019c2d605c46c7dec"],"state_sha256":"bb14847e011bf0e1ae7da5c128ca7fd870e04b86c8cbb34b5755ddf27991991e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eBPO0aQnpigW5sovKkWstJz77CoFA/CpktS8HD0jg8BaiD1s4nz3Hp5BiivV8HIbTKEUQ7l8qiTT4RLmMGjXAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T10:02:14.613383Z","bundle_sha256":"87f6aa7a2239e4b877e9d1762605a0c8eb8ea4231f7beca83c6527073e3a9ac4"}}