{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:L3G37NI52FTUEVHRTROSCZCEID","short_pith_number":"pith:L3G37NI5","canonical_record":{"source":{"id":"2311.09014","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-15T14:56:49Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"6637872433420365264fbd6a9ac8fa763904703b32af7703cca71087cd90687c","abstract_canon_sha256":"b20d8b6339ae0888edf73bec3c88bef356544b0a8d1443d4eeb7322d236eee08"},"schema_version":"1.0"},"canonical_sha256":"5ecdbfb51dd1674254f19c5d21644440ffb5b2e4d391881392c61acd394b46ff","source":{"kind":"arxiv","id":"2311.09014","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.09014","created_at":"2026-07-05T07:13:07Z"},{"alias_kind":"arxiv_version","alias_value":"2311.09014v1","created_at":"2026-07-05T07:13:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09014","created_at":"2026-07-05T07:13:07Z"},{"alias_kind":"pith_short_12","alias_value":"L3G37NI52FTU","created_at":"2026-07-05T07:13:07Z"},{"alias_kind":"pith_short_16","alias_value":"L3G37NI52FTUEVHR","created_at":"2026-07-05T07:13:07Z"},{"alias_kind":"pith_short_8","alias_value":"L3G37NI5","created_at":"2026-07-05T07:13:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:L3G37NI52FTUEVHRTROSCZCEID","target":"record","payload":{"canonical_record":{"source":{"id":"2311.09014","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-15T14:56:49Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"6637872433420365264fbd6a9ac8fa763904703b32af7703cca71087cd90687c","abstract_canon_sha256":"b20d8b6339ae0888edf73bec3c88bef356544b0a8d1443d4eeb7322d236eee08"},"schema_version":"1.0"},"canonical_sha256":"5ecdbfb51dd1674254f19c5d21644440ffb5b2e4d391881392c61acd394b46ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:13:07.717304Z","signature_b64":"Acttdn9+5fVCGe7nvCUMUtSG7zQBdQ58+f2ChZ0GFjd4uUdT+ayiCJm0vJU6H5ohMoFOxvsh/g6Gd6PbF8X1Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ecdbfb51dd1674254f19c5d21644440ffb5b2e4d391881392c61acd394b46ff","last_reissued_at":"2026-07-05T07:13:07.716818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:13:07.716818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.09014","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":"2026-07-05T07:13:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lP5R197jyp/XcWzkHk28sP7GMyP/Nv4gNzoNZEA6LNwPD15Bm039V29/a4LVEgy7syvHwrn1Znl5Td5MErP+AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:06:10.391816Z"},"content_sha256":"4f10c0107864262c1619ae5c9f51ef6063ee96a8dd850bf87de89cdcf65469ab","schema_version":"1.0","event_id":"sha256:4f10c0107864262c1619ae5c9f51ef6063ee96a8dd850bf87de89cdcf65469ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:L3G37NI52FTUEVHRTROSCZCEID","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adversarial Attacks to Reward Machine-based Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Lorenzo Nodari","submitted_at":"2023-11-15T14:56:49Z","abstract_excerpt":"In recent years, Reward Machines (RMs) have stood out as a simple yet effective automata-based formalism for exposing and exploiting task structure in reinforcement learning settings. Despite their relevance, little to no attention has been directed to the study of their security implications and robustness to adversarial scenarios, likely due to their recent appearance in the literature. With my thesis, I aim to provide the first analysis of the security of RM-based reinforcement learning techniques, with the hope of motivating further research in the field, and I propose and evaluate a novel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09014","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/2311.09014/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":"2026-07-05T07:13:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1LdaeFcNHkEyKFieYElrA5zIFFCdEmzStLjMHdO1XbdHaKulOkkT2GHyV/ZD8EIp30t0y7HxwWmmg1mXn+yJCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:06:10.392185Z"},"content_sha256":"9a1aa9e8c47406d6affa5312b7c3007066ee907dcb30c0dc4a6ef3a73270122a","schema_version":"1.0","event_id":"sha256:9a1aa9e8c47406d6affa5312b7c3007066ee907dcb30c0dc4a6ef3a73270122a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L3G37NI52FTUEVHRTROSCZCEID/bundle.json","state_url":"https://pith.science/pith/L3G37NI52FTUEVHRTROSCZCEID/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L3G37NI52FTUEVHRTROSCZCEID/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":"2026-07-06T19:06:10Z","links":{"resolver":"https://pith.science/pith/L3G37NI52FTUEVHRTROSCZCEID","bundle":"https://pith.science/pith/L3G37NI52FTUEVHRTROSCZCEID/bundle.json","state":"https://pith.science/pith/L3G37NI52FTUEVHRTROSCZCEID/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L3G37NI52FTUEVHRTROSCZCEID/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:L3G37NI52FTUEVHRTROSCZCEID","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":"b20d8b6339ae0888edf73bec3c88bef356544b0a8d1443d4eeb7322d236eee08","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-15T14:56:49Z","title_canon_sha256":"6637872433420365264fbd6a9ac8fa763904703b32af7703cca71087cd90687c"},"schema_version":"1.0","source":{"id":"2311.09014","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.09014","created_at":"2026-07-05T07:13:07Z"},{"alias_kind":"arxiv_version","alias_value":"2311.09014v1","created_at":"2026-07-05T07:13:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09014","created_at":"2026-07-05T07:13:07Z"},{"alias_kind":"pith_short_12","alias_value":"L3G37NI52FTU","created_at":"2026-07-05T07:13:07Z"},{"alias_kind":"pith_short_16","alias_value":"L3G37NI52FTUEVHR","created_at":"2026-07-05T07:13:07Z"},{"alias_kind":"pith_short_8","alias_value":"L3G37NI5","created_at":"2026-07-05T07:13:07Z"}],"graph_snapshots":[{"event_id":"sha256:9a1aa9e8c47406d6affa5312b7c3007066ee907dcb30c0dc4a6ef3a73270122a","target":"graph","created_at":"2026-07-05T07:13:07Z","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/2311.09014/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, Reward Machines (RMs) have stood out as a simple yet effective automata-based formalism for exposing and exploiting task structure in reinforcement learning settings. Despite their relevance, little to no attention has been directed to the study of their security implications and robustness to adversarial scenarios, likely due to their recent appearance in the literature. With my thesis, I aim to provide the first analysis of the security of RM-based reinforcement learning techniques, with the hope of motivating further research in the field, and I propose and evaluate a novel","authors_text":"Lorenzo Nodari","cross_cats":["cs.AI","cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-15T14:56:49Z","title":"Adversarial Attacks to Reward Machine-based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09014","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":"sha256:4f10c0107864262c1619ae5c9f51ef6063ee96a8dd850bf87de89cdcf65469ab","target":"record","created_at":"2026-07-05T07:13:07Z","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":"b20d8b6339ae0888edf73bec3c88bef356544b0a8d1443d4eeb7322d236eee08","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-15T14:56:49Z","title_canon_sha256":"6637872433420365264fbd6a9ac8fa763904703b32af7703cca71087cd90687c"},"schema_version":"1.0","source":{"id":"2311.09014","kind":"arxiv","version":1}},"canonical_sha256":"5ecdbfb51dd1674254f19c5d21644440ffb5b2e4d391881392c61acd394b46ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ecdbfb51dd1674254f19c5d21644440ffb5b2e4d391881392c61acd394b46ff","first_computed_at":"2026-07-05T07:13:07.716818Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:13:07.716818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Acttdn9+5fVCGe7nvCUMUtSG7zQBdQ58+f2ChZ0GFjd4uUdT+ayiCJm0vJU6H5ohMoFOxvsh/g6Gd6PbF8X1Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:13:07.717304Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.09014","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f10c0107864262c1619ae5c9f51ef6063ee96a8dd850bf87de89cdcf65469ab","sha256:9a1aa9e8c47406d6affa5312b7c3007066ee907dcb30c0dc4a6ef3a73270122a"],"state_sha256":"976252d4bc5e1a7990f4414da3aba092c21a59dc9687dadd38eccd40bed4f62c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v5ykXjYNuE2+SRJ3BVqhHXSdIKwXmono9wHf0TSLQz+q+iyNVGQy6K29ZKITY/uPLCkbImImtqQYbV00sbc1Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:06:10.394091Z","bundle_sha256":"443097200be2687caceb7b6f2f7a081d639e03cf762371a089e3fd53fbeaf21d"}}