{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CMH7LXVQICB6IM3SNC7KZOVVZG","short_pith_number":"pith:CMH7LXVQ","canonical_record":{"source":{"id":"2507.08794","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-11T17:55:22Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"24b7c3089a8d4af7855c55ced66a9562ab4d33366eca01afc366a6bf36a2efb4","abstract_canon_sha256":"512365434a1e22c4653849ea95d0f2099bc9304222b712b9350c49ace49d5531"},"schema_version":"1.0"},"canonical_sha256":"130ff5deb04083e4337268beacbab5c9894f016068cec77710bb4d83238bb6bf","source":{"kind":"arxiv","id":"2507.08794","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.08794","created_at":"2026-06-12T01:08:14Z"},{"alias_kind":"arxiv_version","alias_value":"2507.08794v3","created_at":"2026-06-12T01:08:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08794","created_at":"2026-06-12T01:08:14Z"},{"alias_kind":"pith_short_12","alias_value":"CMH7LXVQICB6","created_at":"2026-06-12T01:08:14Z"},{"alias_kind":"pith_short_16","alias_value":"CMH7LXVQICB6IM3S","created_at":"2026-06-12T01:08:14Z"},{"alias_kind":"pith_short_8","alias_value":"CMH7LXVQ","created_at":"2026-06-12T01:08:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CMH7LXVQICB6IM3SNC7KZOVVZG","target":"record","payload":{"canonical_record":{"source":{"id":"2507.08794","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-11T17:55:22Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"24b7c3089a8d4af7855c55ced66a9562ab4d33366eca01afc366a6bf36a2efb4","abstract_canon_sha256":"512365434a1e22c4653849ea95d0f2099bc9304222b712b9350c49ace49d5531"},"schema_version":"1.0"},"canonical_sha256":"130ff5deb04083e4337268beacbab5c9894f016068cec77710bb4d83238bb6bf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:08:14.773455Z","signature_b64":"rLx0/nWpF259s0QRfwG+Ks/oX4fYrq7tiYkSUZVpNWQ4Tej9ZfoqxD2S710DjLlN1GHKn4pnRMDMQ9BQWIseDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"130ff5deb04083e4337268beacbab5c9894f016068cec77710bb4d83238bb6bf","last_reissued_at":"2026-06-12T01:08:14.772348Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:08:14.772348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.08794","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-12T01:08:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VLD1LLDSOmdBYhRvM+rJGxgPlB5whEgj4sA8swTPN1kOIVxu7EKaBIrIqNdoMbItIc7JCmNB/i+Jcy+foqHRDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T03:59:45.399803Z"},"content_sha256":"c01510243b41647fe76fa3c48e68e710fa45ef3e22497f028bd3667fa7bf1696","schema_version":"1.0","event_id":"sha256:c01510243b41647fe76fa3c48e68e710fa45ef3e22497f028bd3667fa7bf1696"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CMH7LXVQICB6IM3SNC7KZOVVZG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"One Token to Fool LLM-as-a-Judge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Dian Yu, Dong Yu, Haitao Mi, Haolin Liu, Meijia Chen, Sunyuan Kung, Yulai Zhao","submitted_at":"2025-07-11T17:55:22Z","abstract_excerpt":"Large language models (LLMs) are increasingly trusted as automated judges, assisting evaluation and providing reward signals for training other models, particularly in reference-based settings like Reinforcement Learning with Verifiable Rewards (RLVR). However, we uncover a critical vulnerability even in this reference-based paradigm: generative reward models are systematically susceptible to reward hacking. We find that superficial inputs, which we term ''master keys'' such as non-word symbols (e.g., '':'' or ''.'') or generic reasoning openers (e.g., ''Thought process:'' or ''Let's solve thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08794","kind":"arxiv","version":3},"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/2507.08794/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":"2026-06-12T01:08:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"41y/35r/piK6vbpJ+1t5XEJW3b/wdEt+WrJefboiTkiIEmvxIvoUyN5bna2beEAS0Yb4qNY5Z7jzRjAQrIwHAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T03:59:45.400469Z"},"content_sha256":"b24fedeebb5309d24749c6519ed5c079e3e02b2344a9ec2c92712f8d7b2e6b7a","schema_version":"1.0","event_id":"sha256:b24fedeebb5309d24749c6519ed5c079e3e02b2344a9ec2c92712f8d7b2e6b7a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CMH7LXVQICB6IM3SNC7KZOVVZG/bundle.json","state_url":"https://pith.science/pith/CMH7LXVQICB6IM3SNC7KZOVVZG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CMH7LXVQICB6IM3SNC7KZOVVZG/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":"2026-06-30T03:59:45Z","links":{"resolver":"https://pith.science/pith/CMH7LXVQICB6IM3SNC7KZOVVZG","bundle":"https://pith.science/pith/CMH7LXVQICB6IM3SNC7KZOVVZG/bundle.json","state":"https://pith.science/pith/CMH7LXVQICB6IM3SNC7KZOVVZG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CMH7LXVQICB6IM3SNC7KZOVVZG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CMH7LXVQICB6IM3SNC7KZOVVZG","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":"512365434a1e22c4653849ea95d0f2099bc9304222b712b9350c49ace49d5531","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-11T17:55:22Z","title_canon_sha256":"24b7c3089a8d4af7855c55ced66a9562ab4d33366eca01afc366a6bf36a2efb4"},"schema_version":"1.0","source":{"id":"2507.08794","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.08794","created_at":"2026-06-12T01:08:14Z"},{"alias_kind":"arxiv_version","alias_value":"2507.08794v3","created_at":"2026-06-12T01:08:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08794","created_at":"2026-06-12T01:08:14Z"},{"alias_kind":"pith_short_12","alias_value":"CMH7LXVQICB6","created_at":"2026-06-12T01:08:14Z"},{"alias_kind":"pith_short_16","alias_value":"CMH7LXVQICB6IM3S","created_at":"2026-06-12T01:08:14Z"},{"alias_kind":"pith_short_8","alias_value":"CMH7LXVQ","created_at":"2026-06-12T01:08:14Z"}],"graph_snapshots":[{"event_id":"sha256:b24fedeebb5309d24749c6519ed5c079e3e02b2344a9ec2c92712f8d7b2e6b7a","target":"graph","created_at":"2026-06-12T01:08:14Z","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/2507.08794/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly trusted as automated judges, assisting evaluation and providing reward signals for training other models, particularly in reference-based settings like Reinforcement Learning with Verifiable Rewards (RLVR). However, we uncover a critical vulnerability even in this reference-based paradigm: generative reward models are systematically susceptible to reward hacking. We find that superficial inputs, which we term ''master keys'' such as non-word symbols (e.g., '':'' or ''.'') or generic reasoning openers (e.g., ''Thought process:'' or ''Let's solve thi","authors_text":"Dian Yu, Dong Yu, Haitao Mi, Haolin Liu, Meijia Chen, Sunyuan Kung, Yulai Zhao","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-11T17:55:22Z","title":"One Token to Fool LLM-as-a-Judge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08794","kind":"arxiv","version":3},"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:c01510243b41647fe76fa3c48e68e710fa45ef3e22497f028bd3667fa7bf1696","target":"record","created_at":"2026-06-12T01:08:14Z","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":"512365434a1e22c4653849ea95d0f2099bc9304222b712b9350c49ace49d5531","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-11T17:55:22Z","title_canon_sha256":"24b7c3089a8d4af7855c55ced66a9562ab4d33366eca01afc366a6bf36a2efb4"},"schema_version":"1.0","source":{"id":"2507.08794","kind":"arxiv","version":3}},"canonical_sha256":"130ff5deb04083e4337268beacbab5c9894f016068cec77710bb4d83238bb6bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"130ff5deb04083e4337268beacbab5c9894f016068cec77710bb4d83238bb6bf","first_computed_at":"2026-06-12T01:08:14.772348Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:08:14.772348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rLx0/nWpF259s0QRfwG+Ks/oX4fYrq7tiYkSUZVpNWQ4Tej9ZfoqxD2S710DjLlN1GHKn4pnRMDMQ9BQWIseDA==","signature_status":"signed_v1","signed_at":"2026-06-12T01:08:14.773455Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.08794","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c01510243b41647fe76fa3c48e68e710fa45ef3e22497f028bd3667fa7bf1696","sha256:b24fedeebb5309d24749c6519ed5c079e3e02b2344a9ec2c92712f8d7b2e6b7a"],"state_sha256":"2d43649557083e299e4585491c71898ac83e5bcf001ad64aeae050b1ad9b3bb6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6wAgeGjhP4DoRm1UjKmjurMklLzhWWKSRkj6Ftl8JYqWMU22OtWKqivcY0HiugKKT1PFcFTKJX4xWXXtKglEDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T03:59:45.403821Z","bundle_sha256":"b2271640fda2f25416c3cf17c13e8e9c47c3a76037931615e6a170c7d83dda1e"}}