{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:A3G2TL4F66AZ5Q3IVIQLYCXYFK","short_pith_number":"pith:A3G2TL4F","canonical_record":{"source":{"id":"2607.05904","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-07T06:59:30Z","cross_cats_sorted":[],"title_canon_sha256":"3e2f066b7e345d2cecadd0c5a19a90b3a2d08bc757c19e27d5c340ad0ac4c80f","abstract_canon_sha256":"79b0082dbd69e42b8bbd591f7a2b252fc50197612e224cc9fbd7c424e56d527d"},"schema_version":"1.0"},"canonical_sha256":"06cda9af85f7819ec368aa20bc0af82ab1d8f7fc93a62ed22db78ccd72573d61","source":{"kind":"arxiv","id":"2607.05904","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.05904","created_at":"2026-07-08T01:18:49Z"},{"alias_kind":"arxiv_version","alias_value":"2607.05904v1","created_at":"2026-07-08T01:18:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05904","created_at":"2026-07-08T01:18:49Z"},{"alias_kind":"pith_short_12","alias_value":"A3G2TL4F66AZ","created_at":"2026-07-08T01:18:49Z"},{"alias_kind":"pith_short_16","alias_value":"A3G2TL4F66AZ5Q3I","created_at":"2026-07-08T01:18:49Z"},{"alias_kind":"pith_short_8","alias_value":"A3G2TL4F","created_at":"2026-07-08T01:18:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:A3G2TL4F66AZ5Q3IVIQLYCXYFK","target":"record","payload":{"canonical_record":{"source":{"id":"2607.05904","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-07T06:59:30Z","cross_cats_sorted":[],"title_canon_sha256":"3e2f066b7e345d2cecadd0c5a19a90b3a2d08bc757c19e27d5c340ad0ac4c80f","abstract_canon_sha256":"79b0082dbd69e42b8bbd591f7a2b252fc50197612e224cc9fbd7c424e56d527d"},"schema_version":"1.0"},"canonical_sha256":"06cda9af85f7819ec368aa20bc0af82ab1d8f7fc93a62ed22db78ccd72573d61","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:18:49.784423Z","signature_b64":"tl6Jq9utChAveHhmOFrhADDWx0K/Cpn2ZA7SREKp39fbJhxhTmMnAgfaxTJXWlBtFBOXQalSkALkgRKZZvaFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06cda9af85f7819ec368aa20bc0af82ab1d8f7fc93a62ed22db78ccd72573d61","last_reissued_at":"2026-07-08T01:18:49.783970Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:18:49.783970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.05904","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":"2026-07-08T01:18:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OItj6oP74gtZqIw2uUzcuImQswruKj0WlGjrt7OTUnscU81o3xRV+1XJycLjyS4SkLm+pDub3H80BdElFDBgAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T10:45:22.339706Z"},"content_sha256":"8a502facd851b3e75f78b62bf952be45a2b79b5480b940c7f0e04ec831b99c65","schema_version":"1.0","event_id":"sha256:8a502facd851b3e75f78b62bf952be45a2b79b5480b940c7f0e04ec831b99c65"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:A3G2TL4F66AZ5Q3IVIQLYCXYFK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chenyu Zhou","submitted_at":"2026-07-07T06:59:30Z","abstract_excerpt":"Training a language model against its own reference-free judgments (the premise of self-rewarding, self-play, and LLM-as-a-judge pipelines) assumes a model's verdict on a shown answer tracks correctness. We show it fails structurally: conditioned on a candidate, a judge scores plausibility, not correctness, leaving false-positive basins a policy learns to exploit. We measure this with a hidden-anchor audit: a held-out, cross-source exact-match check the judge never sees. On GSM8K with Qwen3 policies, self-play drives the judge's pass rate from 0.72 to 0.94 while true accuracy stays at 0.20 (th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05904","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/2607.05904/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":"2026-07-08T01:18:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7LClKTMYMDDuPORi1qr8Ghgw9RPJpoPXEllGjmDTu+KUA+qqcUaa8RhabYeZ+nbBuLs7Zl+/uA385XnODX8bAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T10:45:22.340078Z"},"content_sha256":"4d0ecc2650fc1911c674493c28f5d120c0ca7cafea769f0e70a637ff67cd6e38","schema_version":"1.0","event_id":"sha256:4d0ecc2650fc1911c674493c28f5d120c0ca7cafea769f0e70a637ff67cd6e38"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A3G2TL4F66AZ5Q3IVIQLYCXYFK/bundle.json","state_url":"https://pith.science/pith/A3G2TL4F66AZ5Q3IVIQLYCXYFK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A3G2TL4F66AZ5Q3IVIQLYCXYFK/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":"2026-07-12T10:45:22Z","links":{"resolver":"https://pith.science/pith/A3G2TL4F66AZ5Q3IVIQLYCXYFK","bundle":"https://pith.science/pith/A3G2TL4F66AZ5Q3IVIQLYCXYFK/bundle.json","state":"https://pith.science/pith/A3G2TL4F66AZ5Q3IVIQLYCXYFK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A3G2TL4F66AZ5Q3IVIQLYCXYFK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:A3G2TL4F66AZ5Q3IVIQLYCXYFK","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":"79b0082dbd69e42b8bbd591f7a2b252fc50197612e224cc9fbd7c424e56d527d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-07T06:59:30Z","title_canon_sha256":"3e2f066b7e345d2cecadd0c5a19a90b3a2d08bc757c19e27d5c340ad0ac4c80f"},"schema_version":"1.0","source":{"id":"2607.05904","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.05904","created_at":"2026-07-08T01:18:49Z"},{"alias_kind":"arxiv_version","alias_value":"2607.05904v1","created_at":"2026-07-08T01:18:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05904","created_at":"2026-07-08T01:18:49Z"},{"alias_kind":"pith_short_12","alias_value":"A3G2TL4F66AZ","created_at":"2026-07-08T01:18:49Z"},{"alias_kind":"pith_short_16","alias_value":"A3G2TL4F66AZ5Q3I","created_at":"2026-07-08T01:18:49Z"},{"alias_kind":"pith_short_8","alias_value":"A3G2TL4F","created_at":"2026-07-08T01:18:49Z"}],"graph_snapshots":[{"event_id":"sha256:4d0ecc2650fc1911c674493c28f5d120c0ca7cafea769f0e70a637ff67cd6e38","target":"graph","created_at":"2026-07-08T01:18:49Z","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/2607.05904/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training a language model against its own reference-free judgments (the premise of self-rewarding, self-play, and LLM-as-a-judge pipelines) assumes a model's verdict on a shown answer tracks correctness. We show it fails structurally: conditioned on a candidate, a judge scores plausibility, not correctness, leaving false-positive basins a policy learns to exploit. We measure this with a hidden-anchor audit: a held-out, cross-source exact-match check the judge never sees. On GSM8K with Qwen3 policies, self-play drives the judge's pass rate from 0.72 to 0.94 while true accuracy stays at 0.20 (th","authors_text":"Chenyu Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-07T06:59:30Z","title":"More Convincing, Not More Correct: Self-Play Reward Hacking of Reference-Free LLM Judges"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05904","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":"sha256:8a502facd851b3e75f78b62bf952be45a2b79b5480b940c7f0e04ec831b99c65","target":"record","created_at":"2026-07-08T01:18:49Z","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":"79b0082dbd69e42b8bbd591f7a2b252fc50197612e224cc9fbd7c424e56d527d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-07T06:59:30Z","title_canon_sha256":"3e2f066b7e345d2cecadd0c5a19a90b3a2d08bc757c19e27d5c340ad0ac4c80f"},"schema_version":"1.0","source":{"id":"2607.05904","kind":"arxiv","version":1}},"canonical_sha256":"06cda9af85f7819ec368aa20bc0af82ab1d8f7fc93a62ed22db78ccd72573d61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06cda9af85f7819ec368aa20bc0af82ab1d8f7fc93a62ed22db78ccd72573d61","first_computed_at":"2026-07-08T01:18:49.783970Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-08T01:18:49.783970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tl6Jq9utChAveHhmOFrhADDWx0K/Cpn2ZA7SREKp39fbJhxhTmMnAgfaxTJXWlBtFBOXQalSkALkgRKZZvaFDQ==","signature_status":"signed_v1","signed_at":"2026-07-08T01:18:49.784423Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.05904","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a502facd851b3e75f78b62bf952be45a2b79b5480b940c7f0e04ec831b99c65","sha256:4d0ecc2650fc1911c674493c28f5d120c0ca7cafea769f0e70a637ff67cd6e38"],"state_sha256":"0d0cdd1a43c6e2a392a4200360c707c7b2dab32d3103e104037ef75eb75d9233"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U+awr/aCOCTtVIs83/cwudEC4ZzOO4oVT96fkUSstyTG6Z5zP1+huwWOYf2QdiX2XPglsf5NfGteNzsdRgetAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T10:45:22.342654Z","bundle_sha256":"b6f90ae5f0818cc8475676849bb018d2c32eea775d8da7ff210b8a535f7787d1"}}