{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6HTFXFSX6SHHDYDESFUN34P5KT","short_pith_number":"pith:6HTFXFSX","canonical_record":{"source":{"id":"2408.14871","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-27T08:41:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8d835645f893f98a764072875fc8bbb1cbcf5a932647e6853166d820c4c03fa1","abstract_canon_sha256":"a06f017811a1974673a55f77313568f96cbd5348d6183f386f38a3503dec6e25"},"schema_version":"1.0"},"canonical_sha256":"f1e65b9657f48e71e0649168ddf1fd54fe65c48d42e8a1755573d8e8a94968d4","source":{"kind":"arxiv","id":"2408.14871","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.14871","created_at":"2026-07-05T10:36:27Z"},{"alias_kind":"arxiv_version","alias_value":"2408.14871v2","created_at":"2026-07-05T10:36:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14871","created_at":"2026-07-05T10:36:27Z"},{"alias_kind":"pith_short_12","alias_value":"6HTFXFSX6SHH","created_at":"2026-07-05T10:36:27Z"},{"alias_kind":"pith_short_16","alias_value":"6HTFXFSX6SHHDYDE","created_at":"2026-07-05T10:36:27Z"},{"alias_kind":"pith_short_8","alias_value":"6HTFXFSX","created_at":"2026-07-05T10:36:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6HTFXFSX6SHHDYDESFUN34P5KT","target":"record","payload":{"canonical_record":{"source":{"id":"2408.14871","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-27T08:41:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8d835645f893f98a764072875fc8bbb1cbcf5a932647e6853166d820c4c03fa1","abstract_canon_sha256":"a06f017811a1974673a55f77313568f96cbd5348d6183f386f38a3503dec6e25"},"schema_version":"1.0"},"canonical_sha256":"f1e65b9657f48e71e0649168ddf1fd54fe65c48d42e8a1755573d8e8a94968d4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:27.691591Z","signature_b64":"slUee7GtfZd0LbC8+ZqygP54bHxaHRielL5bNsW3hYU2nG4IegqocKV7bTMDXg7usFoZMkimT68OFqanEITXBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1e65b9657f48e71e0649168ddf1fd54fe65c48d42e8a1755573d8e8a94968d4","last_reissued_at":"2026-07-05T10:36:27.690962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:27.690962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.14871","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:36:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vCHxtFxP+KR/FkYIwAj069LeZW2vHzOxZn4m0uXXhvzqGSrd/6vLCBHwJgqcYw/eFA4so9hAcS1G0RFs7dGRCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:09:09.270817Z"},"content_sha256":"633e4e3811d0acde89ee097d478f91cbb5092891213adf50e9356f9b89529544","schema_version":"1.0","event_id":"sha256:633e4e3811d0acde89ee097d478f91cbb5092891213adf50e9356f9b89529544"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6HTFXFSX6SHHDYDESFUN34P5KT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Robust Reward Machines from Noisy Labels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Alessandra Russo, Daniel Furelos-Blanco, Federico Cerutti, Leo Ardon, Lorenzo Nodari, Roko Parac","submitted_at":"2024-08-27T08:41:42Z","abstract_excerpt":"This paper presents PROB-IRM, an approach that learns robust reward machines (RMs) for reinforcement learning (RL) agents from noisy execution traces. The key aspect of RM-driven RL is the exploitation of a finite-state machine that decomposes the agent's task into different subtasks. PROB-IRM uses a state-of-the-art inductive logic programming framework robust to noisy examples to learn RMs from noisy traces using the Bayesian posterior degree of beliefs, thus ensuring robustness against inconsistencies. Pivotal for the results is the interleaving between RM learning and policy learning: a ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14871","kind":"arxiv","version":2},"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/2408.14871/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":"2026-07-05T10:36:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ie8GQdQLAmbE6nVWP4486bQMw2ZiRZjXppPskg8noksTwxYNGblh+uIViZRGgaoXUvTHJaHSrTaDs43RK8rTAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:09:09.271187Z"},"content_sha256":"16e1ca848a7254f872ff362ddfd61bd63c0dea339012cc82f9d12e381bea5084","schema_version":"1.0","event_id":"sha256:16e1ca848a7254f872ff362ddfd61bd63c0dea339012cc82f9d12e381bea5084"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6HTFXFSX6SHHDYDESFUN34P5KT/bundle.json","state_url":"https://pith.science/pith/6HTFXFSX6SHHDYDESFUN34P5KT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6HTFXFSX6SHHDYDESFUN34P5KT/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":"2026-07-06T18:09:09Z","links":{"resolver":"https://pith.science/pith/6HTFXFSX6SHHDYDESFUN34P5KT","bundle":"https://pith.science/pith/6HTFXFSX6SHHDYDESFUN34P5KT/bundle.json","state":"https://pith.science/pith/6HTFXFSX6SHHDYDESFUN34P5KT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6HTFXFSX6SHHDYDESFUN34P5KT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6HTFXFSX6SHHDYDESFUN34P5KT","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":"a06f017811a1974673a55f77313568f96cbd5348d6183f386f38a3503dec6e25","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-27T08:41:42Z","title_canon_sha256":"8d835645f893f98a764072875fc8bbb1cbcf5a932647e6853166d820c4c03fa1"},"schema_version":"1.0","source":{"id":"2408.14871","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.14871","created_at":"2026-07-05T10:36:27Z"},{"alias_kind":"arxiv_version","alias_value":"2408.14871v2","created_at":"2026-07-05T10:36:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14871","created_at":"2026-07-05T10:36:27Z"},{"alias_kind":"pith_short_12","alias_value":"6HTFXFSX6SHH","created_at":"2026-07-05T10:36:27Z"},{"alias_kind":"pith_short_16","alias_value":"6HTFXFSX6SHHDYDE","created_at":"2026-07-05T10:36:27Z"},{"alias_kind":"pith_short_8","alias_value":"6HTFXFSX","created_at":"2026-07-05T10:36:27Z"}],"graph_snapshots":[{"event_id":"sha256:16e1ca848a7254f872ff362ddfd61bd63c0dea339012cc82f9d12e381bea5084","target":"graph","created_at":"2026-07-05T10:36:27Z","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/2408.14871/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents PROB-IRM, an approach that learns robust reward machines (RMs) for reinforcement learning (RL) agents from noisy execution traces. The key aspect of RM-driven RL is the exploitation of a finite-state machine that decomposes the agent's task into different subtasks. PROB-IRM uses a state-of-the-art inductive logic programming framework robust to noisy examples to learn RMs from noisy traces using the Bayesian posterior degree of beliefs, thus ensuring robustness against inconsistencies. Pivotal for the results is the interleaving between RM learning and policy learning: a ne","authors_text":"Alessandra Russo, Daniel Furelos-Blanco, Federico Cerutti, Leo Ardon, Lorenzo Nodari, Roko Parac","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-27T08:41:42Z","title":"Learning Robust Reward Machines from Noisy Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14871","kind":"arxiv","version":2},"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":"sha256:633e4e3811d0acde89ee097d478f91cbb5092891213adf50e9356f9b89529544","target":"record","created_at":"2026-07-05T10:36:27Z","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":"a06f017811a1974673a55f77313568f96cbd5348d6183f386f38a3503dec6e25","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-08-27T08:41:42Z","title_canon_sha256":"8d835645f893f98a764072875fc8bbb1cbcf5a932647e6853166d820c4c03fa1"},"schema_version":"1.0","source":{"id":"2408.14871","kind":"arxiv","version":2}},"canonical_sha256":"f1e65b9657f48e71e0649168ddf1fd54fe65c48d42e8a1755573d8e8a94968d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1e65b9657f48e71e0649168ddf1fd54fe65c48d42e8a1755573d8e8a94968d4","first_computed_at":"2026-07-05T10:36:27.690962Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:36:27.690962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"slUee7GtfZd0LbC8+ZqygP54bHxaHRielL5bNsW3hYU2nG4IegqocKV7bTMDXg7usFoZMkimT68OFqanEITXBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:36:27.691591Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.14871","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:633e4e3811d0acde89ee097d478f91cbb5092891213adf50e9356f9b89529544","sha256:16e1ca848a7254f872ff362ddfd61bd63c0dea339012cc82f9d12e381bea5084"],"state_sha256":"a724fb18c7985ab25e100f6600fc39c77c3ba94a7816ef3e534d2c26d034d605"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z04NiZ5Cd5l/b31Pk27ojPIugATW3TziA6LdSuYX7/nlTAaLOzB0ew6X1MdCyTtLousBq/wxvh+vt7ca18kfAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:09:09.273144Z","bundle_sha256":"cffdfe23c9dedf03f291c9238a6ebc5b4c30f40bb9d095c9abfad106eae7bb79"}}