{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GYXMUCT6OELZ57M6HJSONTCIJF","short_pith_number":"pith:GYXMUCT6","canonical_record":{"source":{"id":"2509.05852","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-09-06T22:29:17Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"9587fcce22b46f96d69369734f93262b540c7e8a55e6e0479f08756f9ddaef3e","abstract_canon_sha256":"a414a863f1fbcbbb5c082b3d0b6c3b4758bf2374e60b7c7fef63dbfeb92aaf80"},"schema_version":"1.0"},"canonical_sha256":"362eca0a7e71179efd9e3a64e6cc484946ece0c2e13964eef38ef13cce018422","source":{"kind":"arxiv","id":"2509.05852","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.05852","created_at":"2026-07-05T12:06:25Z"},{"alias_kind":"arxiv_version","alias_value":"2509.05852v1","created_at":"2026-07-05T12:06:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05852","created_at":"2026-07-05T12:06:25Z"},{"alias_kind":"pith_short_12","alias_value":"GYXMUCT6OELZ","created_at":"2026-07-05T12:06:25Z"},{"alias_kind":"pith_short_16","alias_value":"GYXMUCT6OELZ57M6","created_at":"2026-07-05T12:06:25Z"},{"alias_kind":"pith_short_8","alias_value":"GYXMUCT6","created_at":"2026-07-05T12:06:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GYXMUCT6OELZ57M6HJSONTCIJF","target":"record","payload":{"canonical_record":{"source":{"id":"2509.05852","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-09-06T22:29:17Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"9587fcce22b46f96d69369734f93262b540c7e8a55e6e0479f08756f9ddaef3e","abstract_canon_sha256":"a414a863f1fbcbbb5c082b3d0b6c3b4758bf2374e60b7c7fef63dbfeb92aaf80"},"schema_version":"1.0"},"canonical_sha256":"362eca0a7e71179efd9e3a64e6cc484946ece0c2e13964eef38ef13cce018422","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:25.205521Z","signature_b64":"YwY2/udpK4Osdg26cq4VUOMUhbUnt1nJSNDTwiI2kKNmjNGVNdsZ4mm4YNXNFs6PZIhGeWfZ7sQUJL78ioHgBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"362eca0a7e71179efd9e3a64e6cc484946ece0c2e13964eef38ef13cce018422","last_reissued_at":"2026-07-05T12:06:25.204976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:25.204976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.05852","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:06:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1UgUT7PZTiwScdkX1hXJgjQlKZjd/W2jdk0h5w5T7i7YDUjbmBuvSfMW2hwc4TUg+oirwe+McXYu4aFq8Pc4DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T00:59:47.269376Z"},"content_sha256":"895940b1ae3150001ff47694599f4d7f0dbc949832291f7d077a8c64c8636d3f","schema_version":"1.0","event_id":"sha256:895940b1ae3150001ff47694599f4d7f0dbc949832291f7d077a8c64c8636d3f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GYXMUCT6OELZ57M6HJSONTCIJF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fisher Random Walk: Automatic Debiasing Contextual Preference Inference for Large Language Model Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Alexander Belloni, Ethan X. Fang, Junwei Lu, Xiaoan Xu, Yichi Zhang","submitted_at":"2025-09-06T22:29:17Z","abstract_excerpt":"Motivated by the need for rigorous and scalable evaluation of large language models, we study contextual preference inference for pairwise comparison functionals of context-dependent preference score functions across domains. Focusing on the contextual Bradley-Terry-Luce model, we develop a semiparametric efficient estimator that automates the debiased estimation through aggregating weighted residual balancing terms across the comparison graph. We show that the efficiency is achieved when the weights are derived from a novel strategy called Fisher random walk. We also propose a computationally"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05852","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/2509.05852/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":"2026-07-05T12:06:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zkk4Iz4gJDfRDSmJ2IzvbJyJaoMhbjeJekOMZzOhCQir2yQjHY4Kz7LgznoB5pVzthkCcZK0rswCj03nK+OJAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T00:59:47.269993Z"},"content_sha256":"62df3507917646babb067edcb60f855b6a5f6e07a4987d6db1a63aab57bf5230","schema_version":"1.0","event_id":"sha256:62df3507917646babb067edcb60f855b6a5f6e07a4987d6db1a63aab57bf5230"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GYXMUCT6OELZ57M6HJSONTCIJF/bundle.json","state_url":"https://pith.science/pith/GYXMUCT6OELZ57M6HJSONTCIJF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GYXMUCT6OELZ57M6HJSONTCIJF/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":"2026-07-09T00:59:47Z","links":{"resolver":"https://pith.science/pith/GYXMUCT6OELZ57M6HJSONTCIJF","bundle":"https://pith.science/pith/GYXMUCT6OELZ57M6HJSONTCIJF/bundle.json","state":"https://pith.science/pith/GYXMUCT6OELZ57M6HJSONTCIJF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GYXMUCT6OELZ57M6HJSONTCIJF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GYXMUCT6OELZ57M6HJSONTCIJF","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":"a414a863f1fbcbbb5c082b3d0b6c3b4758bf2374e60b7c7fef63dbfeb92aaf80","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-09-06T22:29:17Z","title_canon_sha256":"9587fcce22b46f96d69369734f93262b540c7e8a55e6e0479f08756f9ddaef3e"},"schema_version":"1.0","source":{"id":"2509.05852","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.05852","created_at":"2026-07-05T12:06:25Z"},{"alias_kind":"arxiv_version","alias_value":"2509.05852v1","created_at":"2026-07-05T12:06:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05852","created_at":"2026-07-05T12:06:25Z"},{"alias_kind":"pith_short_12","alias_value":"GYXMUCT6OELZ","created_at":"2026-07-05T12:06:25Z"},{"alias_kind":"pith_short_16","alias_value":"GYXMUCT6OELZ57M6","created_at":"2026-07-05T12:06:25Z"},{"alias_kind":"pith_short_8","alias_value":"GYXMUCT6","created_at":"2026-07-05T12:06:25Z"}],"graph_snapshots":[{"event_id":"sha256:62df3507917646babb067edcb60f855b6a5f6e07a4987d6db1a63aab57bf5230","target":"graph","created_at":"2026-07-05T12:06:25Z","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/2509.05852/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Motivated by the need for rigorous and scalable evaluation of large language models, we study contextual preference inference for pairwise comparison functionals of context-dependent preference score functions across domains. Focusing on the contextual Bradley-Terry-Luce model, we develop a semiparametric efficient estimator that automates the debiased estimation through aggregating weighted residual balancing terms across the comparison graph. We show that the efficiency is achieved when the weights are derived from a novel strategy called Fisher random walk. We also propose a computationally","authors_text":"Alexander Belloni, Ethan X. Fang, Junwei Lu, Xiaoan Xu, Yichi Zhang","cross_cats":["cs.LG","math.ST","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-09-06T22:29:17Z","title":"Fisher Random Walk: Automatic Debiasing Contextual Preference Inference for Large Language Model Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05852","kind":"arxiv","version":1},"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":"sha256:895940b1ae3150001ff47694599f4d7f0dbc949832291f7d077a8c64c8636d3f","target":"record","created_at":"2026-07-05T12:06:25Z","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":"a414a863f1fbcbbb5c082b3d0b6c3b4758bf2374e60b7c7fef63dbfeb92aaf80","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-09-06T22:29:17Z","title_canon_sha256":"9587fcce22b46f96d69369734f93262b540c7e8a55e6e0479f08756f9ddaef3e"},"schema_version":"1.0","source":{"id":"2509.05852","kind":"arxiv","version":1}},"canonical_sha256":"362eca0a7e71179efd9e3a64e6cc484946ece0c2e13964eef38ef13cce018422","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"362eca0a7e71179efd9e3a64e6cc484946ece0c2e13964eef38ef13cce018422","first_computed_at":"2026-07-05T12:06:25.204976Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:25.204976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YwY2/udpK4Osdg26cq4VUOMUhbUnt1nJSNDTwiI2kKNmjNGVNdsZ4mm4YNXNFs6PZIhGeWfZ7sQUJL78ioHgBA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:25.205521Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.05852","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:895940b1ae3150001ff47694599f4d7f0dbc949832291f7d077a8c64c8636d3f","sha256:62df3507917646babb067edcb60f855b6a5f6e07a4987d6db1a63aab57bf5230"],"state_sha256":"f1407cab874397aab3c2271cc3f3ce320f75ac5376b5e3b1575fcc343bc83d73"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d3VbMjbm/PZUAG7fzcnCBYGr5bTYCvlP/u+kUydkVG2aSam8qlbUp0wA9Qt+4jCDJkOevKQYSmwBlnvFFS4sDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T00:59:47.272495Z","bundle_sha256":"0c6d6269c1f61b310b3e63d8cb6ab5d986e212f8601099266d64c86d6d112145"}}