{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:QXLP7LLAJ3EY2MFHR6WRNLYXPP","short_pith_number":"pith:QXLP7LLA","canonical_record":{"source":{"id":"1706.01417","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-05T16:48:23Z","cross_cats_sorted":[],"title_canon_sha256":"f24b94a7168b0f719560c9e9430315783d90f0193bb3bf529fa10dd3f5a2abbf","abstract_canon_sha256":"45aae3ba42ad908e33cb5185406590b724ae391f578e3a40a1e65070ff0c4915"},"schema_version":"1.0"},"canonical_sha256":"85d6ffad604ec98d30a78fad16af177bcfdad00f4370480c9da0ad3e4846ba3b","source":{"kind":"arxiv","id":"1706.01417","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.01417","created_at":"2026-05-18T00:43:03Z"},{"alias_kind":"arxiv_version","alias_value":"1706.01417v1","created_at":"2026-05-18T00:43:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.01417","created_at":"2026-05-18T00:43:03Z"},{"alias_kind":"pith_short_12","alias_value":"QXLP7LLAJ3EY","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"QXLP7LLAJ3EY2MFH","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"QXLP7LLA","created_at":"2026-05-18T12:31:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:QXLP7LLAJ3EY2MFHR6WRNLYXPP","target":"record","payload":{"canonical_record":{"source":{"id":"1706.01417","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-05T16:48:23Z","cross_cats_sorted":[],"title_canon_sha256":"f24b94a7168b0f719560c9e9430315783d90f0193bb3bf529fa10dd3f5a2abbf","abstract_canon_sha256":"45aae3ba42ad908e33cb5185406590b724ae391f578e3a40a1e65070ff0c4915"},"schema_version":"1.0"},"canonical_sha256":"85d6ffad604ec98d30a78fad16af177bcfdad00f4370480c9da0ad3e4846ba3b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:03.633946Z","signature_b64":"7IFIhiwUKA4KVMp48BsCVuLfiJqXHjraDcfNA9Ac2UAiUYuqo2qvifTkVEu6qMnhBMhnXF4kAI7EDgWIHxPwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85d6ffad604ec98d30a78fad16af177bcfdad00f4370480c9da0ad3e4846ba3b","last_reissued_at":"2026-05-18T00:43:03.633282Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:03.633282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.01417","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":"2026-05-18T00:43:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F8DF+sqQVZNTWXMjdfrPpe7n6kd/6LWeBMtKiwGyRMs1EmE7YZ5a3qwmj6uo/bH1i4dDZbS3EShkoN/6CdrkBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T16:35:32.631045Z"},"content_sha256":"e83571c6e59aa6c5cb4840b56b0a222fb32d551a3855957199c7b0263516eaf9","schema_version":"1.0","event_id":"sha256:e83571c6e59aa6c5cb4840b56b0a222fb32d551a3855957199c7b0263516eaf9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:QXLP7LLAJ3EY2MFHR6WRNLYXPP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A method for the online construction of the set of states of a Markov Decision Process using Answer Set Programming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Leonardo A. Ferreira, Paulo E. Santos, Ramon Lopez de Mantaras, Reinaldo A. C. Bianchi","submitted_at":"2017-06-05T16:48:23Z","abstract_excerpt":"Non-stationary domains, that change in unpredicted ways, are a challenge for agents searching for optimal policies in sequential decision-making problems. This paper presents a combination of Markov Decision Processes (MDP) with Answer Set Programming (ASP), named {\\em Online ASP for MDP} (oASP(MDP)), which is a method capable of constructing the set of domain states while the agent interacts with a changing environment. oASP(MDP) updates previously obtained policies, learnt by means of Reinforcement Learning (RL), using rules that represent the domain changes observed by the agent. These rule"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.01417","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":""},"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":"2026-05-18T00:43:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UIBcuMyVos6g6Cy5EGCGDPbjR9eNmOZ6Cl8ULdEEcW52EY033NYYnTzDJBezEu2hJoG3En4AzCI125FRi3xFDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T16:35:32.631465Z"},"content_sha256":"c3e61c4b9a1c04938e8c3d7de6e802219ac748f76344fbe0146637199241acdb","schema_version":"1.0","event_id":"sha256:c3e61c4b9a1c04938e8c3d7de6e802219ac748f76344fbe0146637199241acdb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QXLP7LLAJ3EY2MFHR6WRNLYXPP/bundle.json","state_url":"https://pith.science/pith/QXLP7LLAJ3EY2MFHR6WRNLYXPP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QXLP7LLAJ3EY2MFHR6WRNLYXPP/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":"2026-06-06T16:35:32Z","links":{"resolver":"https://pith.science/pith/QXLP7LLAJ3EY2MFHR6WRNLYXPP","bundle":"https://pith.science/pith/QXLP7LLAJ3EY2MFHR6WRNLYXPP/bundle.json","state":"https://pith.science/pith/QXLP7LLAJ3EY2MFHR6WRNLYXPP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QXLP7LLAJ3EY2MFHR6WRNLYXPP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:QXLP7LLAJ3EY2MFHR6WRNLYXPP","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":"45aae3ba42ad908e33cb5185406590b724ae391f578e3a40a1e65070ff0c4915","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-05T16:48:23Z","title_canon_sha256":"f24b94a7168b0f719560c9e9430315783d90f0193bb3bf529fa10dd3f5a2abbf"},"schema_version":"1.0","source":{"id":"1706.01417","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.01417","created_at":"2026-05-18T00:43:03Z"},{"alias_kind":"arxiv_version","alias_value":"1706.01417v1","created_at":"2026-05-18T00:43:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.01417","created_at":"2026-05-18T00:43:03Z"},{"alias_kind":"pith_short_12","alias_value":"QXLP7LLAJ3EY","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"QXLP7LLAJ3EY2MFH","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"QXLP7LLA","created_at":"2026-05-18T12:31:39Z"}],"graph_snapshots":[{"event_id":"sha256:c3e61c4b9a1c04938e8c3d7de6e802219ac748f76344fbe0146637199241acdb","target":"graph","created_at":"2026-05-18T00:43:03Z","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"},"paper":{"abstract_excerpt":"Non-stationary domains, that change in unpredicted ways, are a challenge for agents searching for optimal policies in sequential decision-making problems. This paper presents a combination of Markov Decision Processes (MDP) with Answer Set Programming (ASP), named {\\em Online ASP for MDP} (oASP(MDP)), which is a method capable of constructing the set of domain states while the agent interacts with a changing environment. oASP(MDP) updates previously obtained policies, learnt by means of Reinforcement Learning (RL), using rules that represent the domain changes observed by the agent. These rule","authors_text":"Leonardo A. Ferreira, Paulo E. Santos, Ramon Lopez de Mantaras, Reinaldo A. C. Bianchi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-05T16:48:23Z","title":"A method for the online construction of the set of states of a Markov Decision Process using Answer Set Programming"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.01417","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:e83571c6e59aa6c5cb4840b56b0a222fb32d551a3855957199c7b0263516eaf9","target":"record","created_at":"2026-05-18T00:43:03Z","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":"45aae3ba42ad908e33cb5185406590b724ae391f578e3a40a1e65070ff0c4915","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-05T16:48:23Z","title_canon_sha256":"f24b94a7168b0f719560c9e9430315783d90f0193bb3bf529fa10dd3f5a2abbf"},"schema_version":"1.0","source":{"id":"1706.01417","kind":"arxiv","version":1}},"canonical_sha256":"85d6ffad604ec98d30a78fad16af177bcfdad00f4370480c9da0ad3e4846ba3b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85d6ffad604ec98d30a78fad16af177bcfdad00f4370480c9da0ad3e4846ba3b","first_computed_at":"2026-05-18T00:43:03.633282Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:43:03.633282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7IFIhiwUKA4KVMp48BsCVuLfiJqXHjraDcfNA9Ac2UAiUYuqo2qvifTkVEu6qMnhBMhnXF4kAI7EDgWIHxPwAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:43:03.633946Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.01417","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e83571c6e59aa6c5cb4840b56b0a222fb32d551a3855957199c7b0263516eaf9","sha256:c3e61c4b9a1c04938e8c3d7de6e802219ac748f76344fbe0146637199241acdb"],"state_sha256":"2a75b15fb735f53f648ee05a0f3d6c5a2f927d6d2f4261838d936e6a56312a1b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s+EYuRbycjDUtdZMmG+JYRUZHDavYQG/cSW+sRwzPj+T90bCkcw5Pg8/QiSP1SkQiNu0i7vu4ooWfH33eRCqAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T16:35:32.634407Z","bundle_sha256":"f43d960f5177faed7197b5edaeb92ce464c6b08757a08bc7762a8db531b4004c"}}