{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:7LJB5ERE7KALEBQ2E33ZXG6IHQ","short_pith_number":"pith:7LJB5ERE","schema_version":"1.0","canonical_sha256":"fad21e9224fa80b2061a26f79b9bc83c344ea90b402382b868ee430ee30fa61e","source":{"kind":"arxiv","id":"1706.08100","version":1},"attestation_state":"computed","paper":{"title":"Specifying Non-Markovian Rewards in MDPs Using LDL on Finite Traces (Preliminary Version)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fabio Patrizi, Giuseppe De Giacomo, Ronen Brafman","submitted_at":"2017-06-25T13:37:00Z","abstract_excerpt":"In Markov Decision Processes (MDPs), the reward obtained in a state depends on the properties of the last state and action. This state dependency makes it difficult to reward more interesting long-term behaviors, such as always closing a door after it has been opened, or providing coffee only following a request. Extending MDPs to handle such non-Markovian reward function was the subject of two previous lines of work, both using variants of LTL to specify the reward function and then compiling the new model back into a Markovian model. Building upon recent progress in the theories of temporal "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1706.08100","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-06-25T13:37:00Z","cross_cats_sorted":[],"title_canon_sha256":"3054d9f4100d4b0a85c1df06b425196c373cc32b9765a71d6e21926251632ff8","abstract_canon_sha256":"2461f25ef1c70a12cdd98537fa9630e5aa20d655febf366f3c97ff1f83db2a24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:41:43.535330Z","signature_b64":"Zctao6Jzi9DuSO+F4HKK6zWI1KiWMxK5Imhm3T9A/jujKfPubWG7bTDvJ8gVhQ3ZQtwFJkRQhmDlvrXKP7qnDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fad21e9224fa80b2061a26f79b9bc83c344ea90b402382b868ee430ee30fa61e","last_reissued_at":"2026-05-18T00:41:43.534712Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:41:43.534712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Specifying Non-Markovian Rewards in MDPs Using LDL on Finite Traces (Preliminary Version)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fabio Patrizi, Giuseppe De Giacomo, Ronen Brafman","submitted_at":"2017-06-25T13:37:00Z","abstract_excerpt":"In Markov Decision Processes (MDPs), the reward obtained in a state depends on the properties of the last state and action. This state dependency makes it difficult to reward more interesting long-term behaviors, such as always closing a door after it has been opened, or providing coffee only following a request. Extending MDPs to handle such non-Markovian reward function was the subject of two previous lines of work, both using variants of LTL to specify the reward function and then compiling the new model back into a Markovian model. Building upon recent progress in the theories of temporal "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.08100","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1706.08100","created_at":"2026-05-18T00:41:43.534798+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.08100v1","created_at":"2026-05-18T00:41:43.534798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.08100","created_at":"2026-05-18T00:41:43.534798+00:00"},{"alias_kind":"pith_short_12","alias_value":"7LJB5ERE7KAL","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"7LJB5ERE7KALEBQ2","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"7LJB5ERE","created_at":"2026-05-18T12:31:05.417338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7LJB5ERE7KALEBQ2E33ZXG6IHQ","json":"https://pith.science/pith/7LJB5ERE7KALEBQ2E33ZXG6IHQ.json","graph_json":"https://pith.science/api/pith-number/7LJB5ERE7KALEBQ2E33ZXG6IHQ/graph.json","events_json":"https://pith.science/api/pith-number/7LJB5ERE7KALEBQ2E33ZXG6IHQ/events.json","paper":"https://pith.science/paper/7LJB5ERE"},"agent_actions":{"view_html":"https://pith.science/pith/7LJB5ERE7KALEBQ2E33ZXG6IHQ","download_json":"https://pith.science/pith/7LJB5ERE7KALEBQ2E33ZXG6IHQ.json","view_paper":"https://pith.science/paper/7LJB5ERE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.08100&json=true","fetch_graph":"https://pith.science/api/pith-number/7LJB5ERE7KALEBQ2E33ZXG6IHQ/graph.json","fetch_events":"https://pith.science/api/pith-number/7LJB5ERE7KALEBQ2E33ZXG6IHQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7LJB5ERE7KALEBQ2E33ZXG6IHQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7LJB5ERE7KALEBQ2E33ZXG6IHQ/action/storage_attestation","attest_author":"https://pith.science/pith/7LJB5ERE7KALEBQ2E33ZXG6IHQ/action/author_attestation","sign_citation":"https://pith.science/pith/7LJB5ERE7KALEBQ2E33ZXG6IHQ/action/citation_signature","submit_replication":"https://pith.science/pith/7LJB5ERE7KALEBQ2E33ZXG6IHQ/action/replication_record"}},"created_at":"2026-05-18T00:41:43.534798+00:00","updated_at":"2026-05-18T00:41:43.534798+00:00"}