{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:M4FTDPT44WLCSSA67CPIJJP5GZ","short_pith_number":"pith:M4FTDPT4","canonical_record":{"source":{"id":"2606.31372","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-30T09:05:29Z","cross_cats_sorted":[],"title_canon_sha256":"3c5781a1bb02b59f0d2e206780564b68ee834ae50fc9ff6a9431ef6f154c8437","abstract_canon_sha256":"495e1254a5020694aad070a3528fde6047d19b086572228cc7a8408f61a1f810"},"schema_version":"1.0"},"canonical_sha256":"670b31be7ce59629481ef89e84a5fd36489997c12d50d28b3ce8aef819f3965c","source":{"kind":"arxiv","id":"2606.31372","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.31372","created_at":"2026-07-01T01:18:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.31372v1","created_at":"2026-07-01T01:18:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31372","created_at":"2026-07-01T01:18:01Z"},{"alias_kind":"pith_short_12","alias_value":"M4FTDPT44WLC","created_at":"2026-07-01T01:18:01Z"},{"alias_kind":"pith_short_16","alias_value":"M4FTDPT44WLCSSA6","created_at":"2026-07-01T01:18:01Z"},{"alias_kind":"pith_short_8","alias_value":"M4FTDPT4","created_at":"2026-07-01T01:18:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:M4FTDPT44WLCSSA67CPIJJP5GZ","target":"record","payload":{"canonical_record":{"source":{"id":"2606.31372","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-30T09:05:29Z","cross_cats_sorted":[],"title_canon_sha256":"3c5781a1bb02b59f0d2e206780564b68ee834ae50fc9ff6a9431ef6f154c8437","abstract_canon_sha256":"495e1254a5020694aad070a3528fde6047d19b086572228cc7a8408f61a1f810"},"schema_version":"1.0"},"canonical_sha256":"670b31be7ce59629481ef89e84a5fd36489997c12d50d28b3ce8aef819f3965c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:18:01.032189Z","signature_b64":"x89T1K8N8I2mehFNp7n2NTWPGs/dufJw4z5EUCq1/E28n5Q4uW3adE836fO81QmREOj0WtCT1dIPa/YzZr0tAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"670b31be7ce59629481ef89e84a5fd36489997c12d50d28b3ce8aef819f3965c","last_reissued_at":"2026-07-01T01:18:01.031779Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:18:01.031779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.31372","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":"2026-07-01T01:18:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oWe2vcU+8QSvP4KFN1I8BsLeKLu/vple2IwmkKrtN/lLGBEQ5Zd3238KciEyhSq9x3D1Ss3AERgsYRT5DgjSBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T11:25:12.460647Z"},"content_sha256":"6499d18fb57218bc514dd8fd48ebc98ba311f22b55b8b44710e29a8cff84eae7","schema_version":"1.0","event_id":"sha256:6499d18fb57218bc514dd8fd48ebc98ba311f22b55b8b44710e29a8cff84eae7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:M4FTDPT44WLCSSA67CPIJJP5GZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Failure-Based Testing for Deep Reinforcement Learning Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Jiangtao Meng, Weibin Lin, Zheng Zheng","submitted_at":"2026-06-30T09:05:29Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) agents have been widely adopted across diverse domains to address challenging decision-making problems, such as autonomous driving and robotic control. Given that many of these applications are safety- and security-critical, rigorous testing of DRL agents is indispensable. Existing testing methods are typically guided by reward signals to detect failures. However, for well-trained agents, whose performance approaches optimal levels in standard operating conditions, reward signals remain generally high, making current methods ineffective at uncovering critical "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31372","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/2606.31372/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":"2026-07-01T01:18:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nGWEsYZPhiXzTJYBmx+LmIu4iwP0pGkaGFPg/1STAwZdkv440bKRyAoHA43o8rnSfx6dTSxFgI2T6oS5vyl2DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T11:25:12.461014Z"},"content_sha256":"64390e9a8c9588cdfe19f45fef3501787bbdc780f06fcf96238b3202372d77d5","schema_version":"1.0","event_id":"sha256:64390e9a8c9588cdfe19f45fef3501787bbdc780f06fcf96238b3202372d77d5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M4FTDPT44WLCSSA67CPIJJP5GZ/bundle.json","state_url":"https://pith.science/pith/M4FTDPT44WLCSSA67CPIJJP5GZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M4FTDPT44WLCSSA67CPIJJP5GZ/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":"2026-07-02T11:25:12Z","links":{"resolver":"https://pith.science/pith/M4FTDPT44WLCSSA67CPIJJP5GZ","bundle":"https://pith.science/pith/M4FTDPT44WLCSSA67CPIJJP5GZ/bundle.json","state":"https://pith.science/pith/M4FTDPT44WLCSSA67CPIJJP5GZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M4FTDPT44WLCSSA67CPIJJP5GZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:M4FTDPT44WLCSSA67CPIJJP5GZ","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":"495e1254a5020694aad070a3528fde6047d19b086572228cc7a8408f61a1f810","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-30T09:05:29Z","title_canon_sha256":"3c5781a1bb02b59f0d2e206780564b68ee834ae50fc9ff6a9431ef6f154c8437"},"schema_version":"1.0","source":{"id":"2606.31372","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.31372","created_at":"2026-07-01T01:18:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.31372v1","created_at":"2026-07-01T01:18:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31372","created_at":"2026-07-01T01:18:01Z"},{"alias_kind":"pith_short_12","alias_value":"M4FTDPT44WLC","created_at":"2026-07-01T01:18:01Z"},{"alias_kind":"pith_short_16","alias_value":"M4FTDPT44WLCSSA6","created_at":"2026-07-01T01:18:01Z"},{"alias_kind":"pith_short_8","alias_value":"M4FTDPT4","created_at":"2026-07-01T01:18:01Z"}],"graph_snapshots":[{"event_id":"sha256:64390e9a8c9588cdfe19f45fef3501787bbdc780f06fcf96238b3202372d77d5","target":"graph","created_at":"2026-07-01T01:18:01Z","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/2606.31372/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep Reinforcement Learning (DRL) agents have been widely adopted across diverse domains to address challenging decision-making problems, such as autonomous driving and robotic control. Given that many of these applications are safety- and security-critical, rigorous testing of DRL agents is indispensable. Existing testing methods are typically guided by reward signals to detect failures. However, for well-trained agents, whose performance approaches optimal levels in standard operating conditions, reward signals remain generally high, making current methods ineffective at uncovering critical ","authors_text":"Jiangtao Meng, Weibin Lin, Zheng Zheng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-30T09:05:29Z","title":"Failure-Based Testing for Deep Reinforcement Learning Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31372","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":"sha256:6499d18fb57218bc514dd8fd48ebc98ba311f22b55b8b44710e29a8cff84eae7","target":"record","created_at":"2026-07-01T01:18:01Z","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":"495e1254a5020694aad070a3528fde6047d19b086572228cc7a8408f61a1f810","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-30T09:05:29Z","title_canon_sha256":"3c5781a1bb02b59f0d2e206780564b68ee834ae50fc9ff6a9431ef6f154c8437"},"schema_version":"1.0","source":{"id":"2606.31372","kind":"arxiv","version":1}},"canonical_sha256":"670b31be7ce59629481ef89e84a5fd36489997c12d50d28b3ce8aef819f3965c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"670b31be7ce59629481ef89e84a5fd36489997c12d50d28b3ce8aef819f3965c","first_computed_at":"2026-07-01T01:18:01.031779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:18:01.031779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x89T1K8N8I2mehFNp7n2NTWPGs/dufJw4z5EUCq1/E28n5Q4uW3adE836fO81QmREOj0WtCT1dIPa/YzZr0tAw==","signature_status":"signed_v1","signed_at":"2026-07-01T01:18:01.032189Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.31372","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6499d18fb57218bc514dd8fd48ebc98ba311f22b55b8b44710e29a8cff84eae7","sha256:64390e9a8c9588cdfe19f45fef3501787bbdc780f06fcf96238b3202372d77d5"],"state_sha256":"2b0811847e2692ba332ab0bee7c140e7c2d60d84a1bf153527a4f68eab6f8ebf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vL4nAFs3C74F5KH7ttkYFL1pWpKnhruczjpzIwc0MFKL14S5dIA9V1D4F8G+c6teBokXhbVBuIRH9UMObIuJCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T11:25:12.462985Z","bundle_sha256":"12ada1867a5d9886232020a254f33e3c8b5b04db791c557da8203093ec655e7d"}}