{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:R3IMTZTDN5S6FQOWGTFO7CEQDQ","short_pith_number":"pith:R3IMTZTD","canonical_record":{"source":{"id":"2508.14093","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-14T18:46:54Z","cross_cats_sorted":[],"title_canon_sha256":"cc3874762e35832678aa08d327c7be33aeb2c081819c3df1b419d8dbcdc67eb1","abstract_canon_sha256":"bcb8d22d934aac5f35ed32388fca38821e57fd0e0e86ad855bcdc7a70e48915e"},"schema_version":"1.0"},"canonical_sha256":"8ed0c9e6636f65e2c1d634caef88901c1195a83e81b24243dd3181d7796a0a52","source":{"kind":"arxiv","id":"2508.14093","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.14093","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"arxiv_version","alias_value":"2508.14093v1","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.14093","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"pith_short_12","alias_value":"R3IMTZTDN5S6","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"pith_short_16","alias_value":"R3IMTZTDN5S6FQOW","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"pith_short_8","alias_value":"R3IMTZTD","created_at":"2026-07-05T11:56:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:R3IMTZTDN5S6FQOWGTFO7CEQDQ","target":"record","payload":{"canonical_record":{"source":{"id":"2508.14093","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-14T18:46:54Z","cross_cats_sorted":[],"title_canon_sha256":"cc3874762e35832678aa08d327c7be33aeb2c081819c3df1b419d8dbcdc67eb1","abstract_canon_sha256":"bcb8d22d934aac5f35ed32388fca38821e57fd0e0e86ad855bcdc7a70e48915e"},"schema_version":"1.0"},"canonical_sha256":"8ed0c9e6636f65e2c1d634caef88901c1195a83e81b24243dd3181d7796a0a52","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:24.923387Z","signature_b64":"TZxbgmb/WY48Be8GYvWuETaBN2DLAjLyQJCgijUgt1u0LL9fbcCyrUH4b0/R0+Spixy5cBIWAjcTM3J33PoBCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ed0c9e6636f65e2c1d634caef88901c1195a83e81b24243dd3181d7796a0a52","last_reissued_at":"2026-07-05T11:56:24.922961Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:24.922961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.14093","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":"2026-07-05T11:56:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"222ET4MzSXy1ByRxytcsbbrdBVgboc713DQ4AC4Iu6TexSG1NRZ6VfyNLDlg3AM9B4CWm1/ZXuWLtMNBkymgAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T07:47:11.177946Z"},"content_sha256":"d8cfbae4bab62fc7a11df20f6118612109fbe237ea79f5728b66e4fedc7d1bcf","schema_version":"1.0","event_id":"sha256:d8cfbae4bab62fc7a11df20f6118612109fbe237ea79f5728b66e4fedc7d1bcf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:R3IMTZTDN5S6FQOWGTFO7CEQDQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Physics-Informed Reward Machines","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ashutosh Trivedi, Daniel Ajeleye, Majid Zamani","submitted_at":"2025-08-14T18:46:54Z","abstract_excerpt":"Reward machines (RMs) provide a structured way to specify non-Markovian rewards in reinforcement learning (RL), thereby improving both expressiveness and programmability. Viewed more broadly, they separate what is known about the environment, captured by the reward mechanism, from what remains unknown and must be discovered through sampling. This separation supports techniques such as counterfactual experience generation and reward shaping, which reduce sample complexity and speed up learning. We introduce physics-informed reward machines (pRMs), a symbolic machine designed to express complex "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.14093","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/2508.14093/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":"2026-07-05T11:56:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HrYP7K6XXjFpOPgEJxo8O2kYXOPGuzYAVUG13J4hZ7xihcLYj7d2ZAOjXBkypPxvFe0TpIhGWZb2RLeZI4oVBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T07:47:11.178491Z"},"content_sha256":"d68e53f3bbcbb7a176cb3a5a15d6612504e4b0c5cafa6b155b82686a40b2e7c3","schema_version":"1.0","event_id":"sha256:d68e53f3bbcbb7a176cb3a5a15d6612504e4b0c5cafa6b155b82686a40b2e7c3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R3IMTZTDN5S6FQOWGTFO7CEQDQ/bundle.json","state_url":"https://pith.science/pith/R3IMTZTDN5S6FQOWGTFO7CEQDQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R3IMTZTDN5S6FQOWGTFO7CEQDQ/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":"2026-08-21T07:47:11Z","links":{"resolver":"https://pith.science/pith/R3IMTZTDN5S6FQOWGTFO7CEQDQ","bundle":"https://pith.science/pith/R3IMTZTDN5S6FQOWGTFO7CEQDQ/bundle.json","state":"https://pith.science/pith/R3IMTZTDN5S6FQOWGTFO7CEQDQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R3IMTZTDN5S6FQOWGTFO7CEQDQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:R3IMTZTDN5S6FQOWGTFO7CEQDQ","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":"bcb8d22d934aac5f35ed32388fca38821e57fd0e0e86ad855bcdc7a70e48915e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-14T18:46:54Z","title_canon_sha256":"cc3874762e35832678aa08d327c7be33aeb2c081819c3df1b419d8dbcdc67eb1"},"schema_version":"1.0","source":{"id":"2508.14093","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.14093","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"arxiv_version","alias_value":"2508.14093v1","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.14093","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"pith_short_12","alias_value":"R3IMTZTDN5S6","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"pith_short_16","alias_value":"R3IMTZTDN5S6FQOW","created_at":"2026-07-05T11:56:24Z"},{"alias_kind":"pith_short_8","alias_value":"R3IMTZTD","created_at":"2026-07-05T11:56:24Z"}],"graph_snapshots":[{"event_id":"sha256:d68e53f3bbcbb7a176cb3a5a15d6612504e4b0c5cafa6b155b82686a40b2e7c3","target":"graph","created_at":"2026-07-05T11:56:24Z","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/2508.14093/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reward machines (RMs) provide a structured way to specify non-Markovian rewards in reinforcement learning (RL), thereby improving both expressiveness and programmability. Viewed more broadly, they separate what is known about the environment, captured by the reward mechanism, from what remains unknown and must be discovered through sampling. This separation supports techniques such as counterfactual experience generation and reward shaping, which reduce sample complexity and speed up learning. We introduce physics-informed reward machines (pRMs), a symbolic machine designed to express complex ","authors_text":"Ashutosh Trivedi, Daniel Ajeleye, Majid Zamani","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-14T18:46:54Z","title":"Physics-Informed Reward Machines"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.14093","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:d8cfbae4bab62fc7a11df20f6118612109fbe237ea79f5728b66e4fedc7d1bcf","target":"record","created_at":"2026-07-05T11:56:24Z","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":"bcb8d22d934aac5f35ed32388fca38821e57fd0e0e86ad855bcdc7a70e48915e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-14T18:46:54Z","title_canon_sha256":"cc3874762e35832678aa08d327c7be33aeb2c081819c3df1b419d8dbcdc67eb1"},"schema_version":"1.0","source":{"id":"2508.14093","kind":"arxiv","version":1}},"canonical_sha256":"8ed0c9e6636f65e2c1d634caef88901c1195a83e81b24243dd3181d7796a0a52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ed0c9e6636f65e2c1d634caef88901c1195a83e81b24243dd3181d7796a0a52","first_computed_at":"2026-07-05T11:56:24.922961Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:56:24.922961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TZxbgmb/WY48Be8GYvWuETaBN2DLAjLyQJCgijUgt1u0LL9fbcCyrUH4b0/R0+Spixy5cBIWAjcTM3J33PoBCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:56:24.923387Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.14093","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d8cfbae4bab62fc7a11df20f6118612109fbe237ea79f5728b66e4fedc7d1bcf","sha256:d68e53f3bbcbb7a176cb3a5a15d6612504e4b0c5cafa6b155b82686a40b2e7c3"],"state_sha256":"8afbff1bd825969764cd0991eb4ba98de0fcf5d3b3f4f46fb82eb16ce038ef52"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AGy+X2pUvhy2gVMhGsrpjEaeNgQAcC2U0gbFWjk5RCclZoh/vf+7Zq720E9tohQyfuRlq3Rxp/a+rQdf2k31AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T07:47:11.183233Z","bundle_sha256":"655454e4dc78497af89320d646ceeb397ec5b4d9892b83d0f861b25dad2c2ce6"}}