{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UYIXUIQBE4YQZ74GPQ4XYOGEUS","short_pith_number":"pith:UYIXUIQB","canonical_record":{"source":{"id":"2501.00364","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-31T09:31:15Z","cross_cats_sorted":["cs.FL","cs.LO","cs.SC"],"title_canon_sha256":"99ef8ff0689fe73baef75adfb1775108332be95d6a7ae305602d09eb180a17b4","abstract_canon_sha256":"25458d17447c993c1e0847e0960d3bbe1498bb4f3f174c9620748fc3c010a4c5"},"schema_version":"1.0"},"canonical_sha256":"a6117a220127310cff867c397c38c4a48e4070a074c528c6ab8f1bf2b7a34c76","source":{"kind":"arxiv","id":"2501.00364","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00364","created_at":"2026-07-05T10:21:27Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00364v3","created_at":"2026-07-05T10:21:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00364","created_at":"2026-07-05T10:21:27Z"},{"alias_kind":"pith_short_12","alias_value":"UYIXUIQBE4YQ","created_at":"2026-07-05T10:21:27Z"},{"alias_kind":"pith_short_16","alias_value":"UYIXUIQBE4YQZ74G","created_at":"2026-07-05T10:21:27Z"},{"alias_kind":"pith_short_8","alias_value":"UYIXUIQB","created_at":"2026-07-05T10:21:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UYIXUIQBE4YQZ74GPQ4XYOGEUS","target":"record","payload":{"canonical_record":{"source":{"id":"2501.00364","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-31T09:31:15Z","cross_cats_sorted":["cs.FL","cs.LO","cs.SC"],"title_canon_sha256":"99ef8ff0689fe73baef75adfb1775108332be95d6a7ae305602d09eb180a17b4","abstract_canon_sha256":"25458d17447c993c1e0847e0960d3bbe1498bb4f3f174c9620748fc3c010a4c5"},"schema_version":"1.0"},"canonical_sha256":"a6117a220127310cff867c397c38c4a48e4070a074c528c6ab8f1bf2b7a34c76","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:27.808459Z","signature_b64":"N32Flrpak0w6H3LOy3rZDANvofYjI6npIp2CTaG1xgbt9X3mnLYbkkA3/v207V3r7J+FhHdguLtjZ4xbMqvTDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6117a220127310cff867c397c38c4a48e4070a074c528c6ab8f1bf2b7a34c76","last_reissued_at":"2026-07-05T10:21:27.807938Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:27.807938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.00364","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:21:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pjg5wgYQjbvxN09XrA2SRPWSgRJxmcuhyxKqUqW1Qq1xywOiMo79ECeg+nt1hIdfCTDRH8yFsW+uHSb3BP10AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:34:55.720560Z"},"content_sha256":"90ee470d71a9b199785d6910cefbec78fa055e275bb3be6085eba586a38cbe0e","schema_version":"1.0","event_id":"sha256:90ee470d71a9b199785d6910cefbec78fa055e275bb3be6085eba586a38cbe0e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UYIXUIQBE4YQZ74GPQ4XYOGEUS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FORM: Learning Expressive and Transferable First-Order Logic Reward Machines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.FL","cs.LO","cs.SC"],"primary_cat":"cs.AI","authors_text":"Alessandra Russo, Daniel Furelos-Blanco, Leo Ardon, Roko Parac","submitted_at":"2024-12-31T09:31:15Z","abstract_excerpt":"Reward machines (RMs) are an effective approach for addressing non-Markovian rewards in reinforcement learning (RL) through finite-state machines. Traditional RMs, which label edges with propositional logic formulae, inherit the limited expressivity of propositional logic. This limitation hinders the learnability and transferability of RMs since complex tasks will require numerous states and edges. To overcome these challenges, we propose First-Order Reward Machines ($\\texttt{FORM}$s), which use first-order logic to label edges, resulting in more compact and transferable RMs. We introduce a no"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00364","kind":"arxiv","version":3},"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/2501.00364/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":"2026-07-05T10:21:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EiZFceBHM/HCb10CXWA1i9XEzc1DI/6BPGkzo9lb8IzJz6SoIt8+ot26UjmsY0EN8uwsBHH9iTZqWpqlkWvyAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:34:55.720935Z"},"content_sha256":"b69f04e8631442903dfc4756c617ce20e94f806ba137fbd34d9f6199f900be77","schema_version":"1.0","event_id":"sha256:b69f04e8631442903dfc4756c617ce20e94f806ba137fbd34d9f6199f900be77"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UYIXUIQBE4YQZ74GPQ4XYOGEUS/bundle.json","state_url":"https://pith.science/pith/UYIXUIQBE4YQZ74GPQ4XYOGEUS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UYIXUIQBE4YQZ74GPQ4XYOGEUS/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":"2026-07-06T19:34:55Z","links":{"resolver":"https://pith.science/pith/UYIXUIQBE4YQZ74GPQ4XYOGEUS","bundle":"https://pith.science/pith/UYIXUIQBE4YQZ74GPQ4XYOGEUS/bundle.json","state":"https://pith.science/pith/UYIXUIQBE4YQZ74GPQ4XYOGEUS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UYIXUIQBE4YQZ74GPQ4XYOGEUS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UYIXUIQBE4YQZ74GPQ4XYOGEUS","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":"25458d17447c993c1e0847e0960d3bbe1498bb4f3f174c9620748fc3c010a4c5","cross_cats_sorted":["cs.FL","cs.LO","cs.SC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-31T09:31:15Z","title_canon_sha256":"99ef8ff0689fe73baef75adfb1775108332be95d6a7ae305602d09eb180a17b4"},"schema_version":"1.0","source":{"id":"2501.00364","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00364","created_at":"2026-07-05T10:21:27Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00364v3","created_at":"2026-07-05T10:21:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00364","created_at":"2026-07-05T10:21:27Z"},{"alias_kind":"pith_short_12","alias_value":"UYIXUIQBE4YQ","created_at":"2026-07-05T10:21:27Z"},{"alias_kind":"pith_short_16","alias_value":"UYIXUIQBE4YQZ74G","created_at":"2026-07-05T10:21:27Z"},{"alias_kind":"pith_short_8","alias_value":"UYIXUIQB","created_at":"2026-07-05T10:21:27Z"}],"graph_snapshots":[{"event_id":"sha256:b69f04e8631442903dfc4756c617ce20e94f806ba137fbd34d9f6199f900be77","target":"graph","created_at":"2026-07-05T10:21:27Z","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/2501.00364/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reward machines (RMs) are an effective approach for addressing non-Markovian rewards in reinforcement learning (RL) through finite-state machines. Traditional RMs, which label edges with propositional logic formulae, inherit the limited expressivity of propositional logic. This limitation hinders the learnability and transferability of RMs since complex tasks will require numerous states and edges. To overcome these challenges, we propose First-Order Reward Machines ($\\texttt{FORM}$s), which use first-order logic to label edges, resulting in more compact and transferable RMs. We introduce a no","authors_text":"Alessandra Russo, Daniel Furelos-Blanco, Leo Ardon, Roko Parac","cross_cats":["cs.FL","cs.LO","cs.SC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-31T09:31:15Z","title":"FORM: Learning Expressive and Transferable First-Order Logic Reward Machines"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00364","kind":"arxiv","version":3},"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":"sha256:90ee470d71a9b199785d6910cefbec78fa055e275bb3be6085eba586a38cbe0e","target":"record","created_at":"2026-07-05T10:21:27Z","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":"25458d17447c993c1e0847e0960d3bbe1498bb4f3f174c9620748fc3c010a4c5","cross_cats_sorted":["cs.FL","cs.LO","cs.SC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-31T09:31:15Z","title_canon_sha256":"99ef8ff0689fe73baef75adfb1775108332be95d6a7ae305602d09eb180a17b4"},"schema_version":"1.0","source":{"id":"2501.00364","kind":"arxiv","version":3}},"canonical_sha256":"a6117a220127310cff867c397c38c4a48e4070a074c528c6ab8f1bf2b7a34c76","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6117a220127310cff867c397c38c4a48e4070a074c528c6ab8f1bf2b7a34c76","first_computed_at":"2026-07-05T10:21:27.807938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:27.807938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N32Flrpak0w6H3LOy3rZDANvofYjI6npIp2CTaG1xgbt9X3mnLYbkkA3/v207V3r7J+FhHdguLtjZ4xbMqvTDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:27.808459Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.00364","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90ee470d71a9b199785d6910cefbec78fa055e275bb3be6085eba586a38cbe0e","sha256:b69f04e8631442903dfc4756c617ce20e94f806ba137fbd34d9f6199f900be77"],"state_sha256":"cf27ec7c691e11aa19c06e6378d3febed5d3f51850d6e6cd29c48c5bb601c690"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7zHsliay8WB71sIh8P5ULMvr13xqXreQjmw9PSLd4k+fIauK7kzKGJqxDDvCSNytjEv/Snhe2xsON/YRkqE7DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:34:55.722924Z","bundle_sha256":"125a67c4f923c3e65305306a7a15bee2ad40ecf2d84a9267806c042ed90feb33"}}