{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IBMTD3HFY6WFFJWNOJGBMGLIWV","short_pith_number":"pith:IBMTD3HF","canonical_record":{"source":{"id":"2607.24577","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-27T15:46:57Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"ecf7bd4b1545e652b1da91ddb1c07d4962af9d3f6cf7e4b68082bc6aa663fa15","abstract_canon_sha256":"a33639d1805010397f0eda85fbc3316d556552425f3e53e13882ab8d749263d3"},"schema_version":"1.0"},"canonical_sha256":"405931ece5c7ac52a6cd724c161968b57231b62e7392a051b62bb7ee2aeb2f65","source":{"kind":"arxiv","id":"2607.24577","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24577","created_at":"2026-07-28T02:24:11Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24577v1","created_at":"2026-07-28T02:24:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24577","created_at":"2026-07-28T02:24:11Z"},{"alias_kind":"pith_short_12","alias_value":"IBMTD3HFY6WF","created_at":"2026-07-28T02:24:11Z"},{"alias_kind":"pith_short_16","alias_value":"IBMTD3HFY6WFFJWN","created_at":"2026-07-28T02:24:11Z"},{"alias_kind":"pith_short_8","alias_value":"IBMTD3HF","created_at":"2026-07-28T02:24:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IBMTD3HFY6WFFJWNOJGBMGLIWV","target":"record","payload":{"canonical_record":{"source":{"id":"2607.24577","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-27T15:46:57Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"ecf7bd4b1545e652b1da91ddb1c07d4962af9d3f6cf7e4b68082bc6aa663fa15","abstract_canon_sha256":"a33639d1805010397f0eda85fbc3316d556552425f3e53e13882ab8d749263d3"},"schema_version":"1.0"},"canonical_sha256":"405931ece5c7ac52a6cd724c161968b57231b62e7392a051b62bb7ee2aeb2f65","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T02:24:11.065509Z","signature_b64":"xMpH0HvMlcQFKaPK7reOLrGxtELTBM3OncAxygnjQFVmZhkIkaVtiLw5J8EJXMYXfBVdLvYUtz2l8n9J1lfhDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"405931ece5c7ac52a6cd724c161968b57231b62e7392a051b62bb7ee2aeb2f65","last_reissued_at":"2026-07-28T02:24:11.064685Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T02:24:11.064685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.24577","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":"2026-07-28T02:24:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0JBTpiPEEIvCRGbyxrNUBhT80Q3RfNmCN0gd7V5lKrs6dzec6Lyig4cfEGtE/IF1SoHD/+Cvp8z3eyAbgd9kBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:13:01.317892Z"},"content_sha256":"f062f16e5f626b66951dbda88830abe556a822db68cb0febfba111114c11529d","schema_version":"1.0","event_id":"sha256:f062f16e5f626b66951dbda88830abe556a822db68cb0febfba111114c11529d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IBMTD3HFY6WFFJWNOJGBMGLIWV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluating Fuzz Testing for Reinforcement Learning Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Dong Wang, Haiming Zheng, Hanmo You, Junjie Chen, Zhibin Kang","submitted_at":"2026-07-27T15:46:57Z","abstract_excerpt":"Reinforcement Learning (RL) agents are increasingly deployed in safety-critical domains such as robotics, autonomous driving, and drone control, where unexpected behaviors may lead to severe real-world consequences. Fuzz testing has recently emerged as a promising method for exploring the vast state spaces of RL agents and exposing crashes. Although numerous RL fuzzing methods have been proposed, existing studies often differ in evaluation settings, baselines, and metrics, making it difficult to draw reliable conclusions about their relative effectiveness and practical usefulness. To address t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24577","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/2607.24577/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":"2026-07-28T02:24:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vqgXAiNUPtRt3r6n4vKQENtCyeEN02pBLTdMVPzfSGT0rOcGtVtPAodUB2rVTh/WRTd+W51/vVzXOmKOpngjAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:13:01.318407Z"},"content_sha256":"60aaf496fd19c018abcc6d047e2e2996274153733eb1ff2ef91d8d7243c10dd1","schema_version":"1.0","event_id":"sha256:60aaf496fd19c018abcc6d047e2e2996274153733eb1ff2ef91d8d7243c10dd1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IBMTD3HFY6WFFJWNOJGBMGLIWV/bundle.json","state_url":"https://pith.science/pith/IBMTD3HFY6WFFJWNOJGBMGLIWV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IBMTD3HFY6WFFJWNOJGBMGLIWV/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":"2026-08-06T03:13:01Z","links":{"resolver":"https://pith.science/pith/IBMTD3HFY6WFFJWNOJGBMGLIWV","bundle":"https://pith.science/pith/IBMTD3HFY6WFFJWNOJGBMGLIWV/bundle.json","state":"https://pith.science/pith/IBMTD3HFY6WFFJWNOJGBMGLIWV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IBMTD3HFY6WFFJWNOJGBMGLIWV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IBMTD3HFY6WFFJWNOJGBMGLIWV","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":"a33639d1805010397f0eda85fbc3316d556552425f3e53e13882ab8d749263d3","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-27T15:46:57Z","title_canon_sha256":"ecf7bd4b1545e652b1da91ddb1c07d4962af9d3f6cf7e4b68082bc6aa663fa15"},"schema_version":"1.0","source":{"id":"2607.24577","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24577","created_at":"2026-07-28T02:24:11Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24577v1","created_at":"2026-07-28T02:24:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24577","created_at":"2026-07-28T02:24:11Z"},{"alias_kind":"pith_short_12","alias_value":"IBMTD3HFY6WF","created_at":"2026-07-28T02:24:11Z"},{"alias_kind":"pith_short_16","alias_value":"IBMTD3HFY6WFFJWN","created_at":"2026-07-28T02:24:11Z"},{"alias_kind":"pith_short_8","alias_value":"IBMTD3HF","created_at":"2026-07-28T02:24:11Z"}],"graph_snapshots":[{"event_id":"sha256:60aaf496fd19c018abcc6d047e2e2996274153733eb1ff2ef91d8d7243c10dd1","target":"graph","created_at":"2026-07-28T02:24:11Z","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/2607.24577/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) agents are increasingly deployed in safety-critical domains such as robotics, autonomous driving, and drone control, where unexpected behaviors may lead to severe real-world consequences. Fuzz testing has recently emerged as a promising method for exploring the vast state spaces of RL agents and exposing crashes. Although numerous RL fuzzing methods have been proposed, existing studies often differ in evaluation settings, baselines, and metrics, making it difficult to draw reliable conclusions about their relative effectiveness and practical usefulness. To address t","authors_text":"Dong Wang, Haiming Zheng, Hanmo You, Junjie Chen, Zhibin Kang","cross_cats":["cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-27T15:46:57Z","title":"Evaluating Fuzz Testing for Reinforcement Learning Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24577","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:f062f16e5f626b66951dbda88830abe556a822db68cb0febfba111114c11529d","target":"record","created_at":"2026-07-28T02:24:11Z","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":"a33639d1805010397f0eda85fbc3316d556552425f3e53e13882ab8d749263d3","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-27T15:46:57Z","title_canon_sha256":"ecf7bd4b1545e652b1da91ddb1c07d4962af9d3f6cf7e4b68082bc6aa663fa15"},"schema_version":"1.0","source":{"id":"2607.24577","kind":"arxiv","version":1}},"canonical_sha256":"405931ece5c7ac52a6cd724c161968b57231b62e7392a051b62bb7ee2aeb2f65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"405931ece5c7ac52a6cd724c161968b57231b62e7392a051b62bb7ee2aeb2f65","first_computed_at":"2026-07-28T02:24:11.064685Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T02:24:11.064685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xMpH0HvMlcQFKaPK7reOLrGxtELTBM3OncAxygnjQFVmZhkIkaVtiLw5J8EJXMYXfBVdLvYUtz2l8n9J1lfhDA==","signature_status":"signed_v1","signed_at":"2026-07-28T02:24:11.065509Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.24577","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f062f16e5f626b66951dbda88830abe556a822db68cb0febfba111114c11529d","sha256:60aaf496fd19c018abcc6d047e2e2996274153733eb1ff2ef91d8d7243c10dd1"],"state_sha256":"9649766270a76be05fc84f77946d34778ca2098a065bbd1732f6ecd0251f4e03"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d/zyQn4hwgtyzsNKgf4FoWfrK0+Y+NS3H3sgkoBH7IxB8qzWt3HcATe7CJ0eciO4UuC9p/kvsBbC7deU12rwBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T03:13:01.322366Z","bundle_sha256":"a4880673d396dce288dde09349bce480faa2701b8ec6c5afd7e0a52c4fe14ccd"}}