{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:L5IHLUCBEDTXWFQ3HINUOLIVPW","short_pith_number":"pith:L5IHLUCB","canonical_record":{"source":{"id":"2606.01066","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-31T07:18:07Z","cross_cats_sorted":[],"title_canon_sha256":"93b3a9d241a0aa5e14635560e7e9508ab3f657e724682b65e946937da02a3b39","abstract_canon_sha256":"599f87103d250cf9e05ed757cd2b5d5ab979ef231cb7682a5ef4a3dbfe7f00f7"},"schema_version":"1.0"},"canonical_sha256":"5f5075d04120e77b161b3a1b472d157db02cb79e29388dab8364ca18f8cf2cfa","source":{"kind":"arxiv","id":"2606.01066","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01066","created_at":"2026-06-02T01:04:20Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01066v1","created_at":"2026-06-02T01:04:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01066","created_at":"2026-06-02T01:04:20Z"},{"alias_kind":"pith_short_12","alias_value":"L5IHLUCBEDTX","created_at":"2026-06-02T01:04:20Z"},{"alias_kind":"pith_short_16","alias_value":"L5IHLUCBEDTXWFQ3","created_at":"2026-06-02T01:04:20Z"},{"alias_kind":"pith_short_8","alias_value":"L5IHLUCB","created_at":"2026-06-02T01:04:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:L5IHLUCBEDTXWFQ3HINUOLIVPW","target":"record","payload":{"canonical_record":{"source":{"id":"2606.01066","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-31T07:18:07Z","cross_cats_sorted":[],"title_canon_sha256":"93b3a9d241a0aa5e14635560e7e9508ab3f657e724682b65e946937da02a3b39","abstract_canon_sha256":"599f87103d250cf9e05ed757cd2b5d5ab979ef231cb7682a5ef4a3dbfe7f00f7"},"schema_version":"1.0"},"canonical_sha256":"5f5075d04120e77b161b3a1b472d157db02cb79e29388dab8364ca18f8cf2cfa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:20.323698Z","signature_b64":"zk+K/+8mnPUKy8cuP1AxIQYbstNIm58+/akopWLIyODa3MdkPcaFW457jnaglTG2oLhlYzM1P8Igcju25go5AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f5075d04120e77b161b3a1b472d157db02cb79e29388dab8364ca18f8cf2cfa","last_reissued_at":"2026-06-02T01:04:20.323143Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:20.323143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.01066","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":"2026-06-02T01:04:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4o4dkHRv5v5DBsLp+vMcaom5F/JbOulRJESEt9mrY8fid1BaPKvH/fYS9V4hOkNTCKcispxOsmUMBsRgqXgtDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T00:49:19.342693Z"},"content_sha256":"9754746836a6a020f8c3d3e2fe089346422df7c51d8593730b85ea6692ab7fc1","schema_version":"1.0","event_id":"sha256:9754746836a6a020f8c3d3e2fe089346422df7c51d8593730b85ea6692ab7fc1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:L5IHLUCBEDTXWFQ3HINUOLIVPW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Before the Model Learns the Bug:Fuzzing RLVR Verifiers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jaideep Ray","submitted_at":"2026-05-31T07:18:07Z","abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) replaces human preference labels with executable reward functions such as math answer checkers, JSON tool-call validators, and code unit-test harnesses. That makes the reward partly a software artifact: if the verifier is wrong, optimization can learn the bug. We study this failure mode with a lightweight verifier-fuzzing framework that generates adversarial completions, compares buggy and stricter reference verifiers, logs paired decisions, and reports false-positive, false-negative, disagreement, exploit, and uncertainty metrics."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01066","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/2606.01066/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":"2026-06-02T01:04:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WR8BKSUtffCUsMMmB3OyWVUGVjijKn1Mo8UIGNemFfYTACRmaZd78u0Q8pg1nK1fzADVk8aCVzMoRF3H7OmwDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T00:49:19.343055Z"},"content_sha256":"3b49f4d77e00553d71b184656a2d5370078b9f565f0b51620cb2600d94de0da8","schema_version":"1.0","event_id":"sha256:3b49f4d77e00553d71b184656a2d5370078b9f565f0b51620cb2600d94de0da8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L5IHLUCBEDTXWFQ3HINUOLIVPW/bundle.json","state_url":"https://pith.science/pith/L5IHLUCBEDTXWFQ3HINUOLIVPW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L5IHLUCBEDTXWFQ3HINUOLIVPW/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":"2026-06-27T00:49:19Z","links":{"resolver":"https://pith.science/pith/L5IHLUCBEDTXWFQ3HINUOLIVPW","bundle":"https://pith.science/pith/L5IHLUCBEDTXWFQ3HINUOLIVPW/bundle.json","state":"https://pith.science/pith/L5IHLUCBEDTXWFQ3HINUOLIVPW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L5IHLUCBEDTXWFQ3HINUOLIVPW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:L5IHLUCBEDTXWFQ3HINUOLIVPW","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":"599f87103d250cf9e05ed757cd2b5d5ab979ef231cb7682a5ef4a3dbfe7f00f7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-31T07:18:07Z","title_canon_sha256":"93b3a9d241a0aa5e14635560e7e9508ab3f657e724682b65e946937da02a3b39"},"schema_version":"1.0","source":{"id":"2606.01066","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01066","created_at":"2026-06-02T01:04:20Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01066v1","created_at":"2026-06-02T01:04:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01066","created_at":"2026-06-02T01:04:20Z"},{"alias_kind":"pith_short_12","alias_value":"L5IHLUCBEDTX","created_at":"2026-06-02T01:04:20Z"},{"alias_kind":"pith_short_16","alias_value":"L5IHLUCBEDTXWFQ3","created_at":"2026-06-02T01:04:20Z"},{"alias_kind":"pith_short_8","alias_value":"L5IHLUCB","created_at":"2026-06-02T01:04:20Z"}],"graph_snapshots":[{"event_id":"sha256:3b49f4d77e00553d71b184656a2d5370078b9f565f0b51620cb2600d94de0da8","target":"graph","created_at":"2026-06-02T01:04:20Z","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/2606.01066/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) replaces human preference labels with executable reward functions such as math answer checkers, JSON tool-call validators, and code unit-test harnesses. That makes the reward partly a software artifact: if the verifier is wrong, optimization can learn the bug. We study this failure mode with a lightweight verifier-fuzzing framework that generates adversarial completions, compares buggy and stricter reference verifiers, logs paired decisions, and reports false-positive, false-negative, disagreement, exploit, and uncertainty metrics.","authors_text":"Jaideep Ray","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-31T07:18:07Z","title":"Before the Model Learns the Bug:Fuzzing RLVR Verifiers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01066","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":"sha256:9754746836a6a020f8c3d3e2fe089346422df7c51d8593730b85ea6692ab7fc1","target":"record","created_at":"2026-06-02T01:04:20Z","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":"599f87103d250cf9e05ed757cd2b5d5ab979ef231cb7682a5ef4a3dbfe7f00f7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-31T07:18:07Z","title_canon_sha256":"93b3a9d241a0aa5e14635560e7e9508ab3f657e724682b65e946937da02a3b39"},"schema_version":"1.0","source":{"id":"2606.01066","kind":"arxiv","version":1}},"canonical_sha256":"5f5075d04120e77b161b3a1b472d157db02cb79e29388dab8364ca18f8cf2cfa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f5075d04120e77b161b3a1b472d157db02cb79e29388dab8364ca18f8cf2cfa","first_computed_at":"2026-06-02T01:04:20.323143Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:04:20.323143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zk+K/+8mnPUKy8cuP1AxIQYbstNIm58+/akopWLIyODa3MdkPcaFW457jnaglTG2oLhlYzM1P8Igcju25go5AA==","signature_status":"signed_v1","signed_at":"2026-06-02T01:04:20.323698Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01066","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9754746836a6a020f8c3d3e2fe089346422df7c51d8593730b85ea6692ab7fc1","sha256:3b49f4d77e00553d71b184656a2d5370078b9f565f0b51620cb2600d94de0da8"],"state_sha256":"c7ca7eaca75cee3b53b48dd28b4c866e534b763d93e3ca248a4fb7d2c4980e86"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ycz/DaKHBDh6Ox1FqDl6FBxhuS6INd0lKAfPLiDAfJv44rLPk7n8PwxMcT/FNfwZvx0X1h04O+TX3vxy6+h7Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T00:49:19.345009Z","bundle_sha256":"3a7276e44aede74f0577de764aa7abda6f5a1d6c5af627c129470bbf375bfc8e"}}