{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:ZXEALUM5VXS564J5T6YD3LSMCM","short_pith_number":"pith:ZXEALUM5","canonical_record":{"source":{"id":"2001.09293","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-01-25T10:51:42Z","cross_cats_sorted":[],"title_canon_sha256":"1d1ea8f2f2ccc7c9afbb783fb59fc833ca8f4f9c47b59b505dd14ac8a48e1557","abstract_canon_sha256":"f7b70948ba95f51cc0528be24c6830795eb1c78f36cd370f4f13e26df49d9421"},"schema_version":"1.0"},"canonical_sha256":"cdc805d19dade5df713d9fb03dae4c1315628424b9b4db2cb366fd40dcdc4d4b","source":{"kind":"arxiv","id":"2001.09293","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.09293","created_at":"2026-07-05T00:35:57Z"},{"alias_kind":"arxiv_version","alias_value":"2001.09293v1","created_at":"2026-07-05T00:35:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.09293","created_at":"2026-07-05T00:35:57Z"},{"alias_kind":"pith_short_12","alias_value":"ZXEALUM5VXS5","created_at":"2026-07-05T00:35:57Z"},{"alias_kind":"pith_short_16","alias_value":"ZXEALUM5VXS564J5","created_at":"2026-07-05T00:35:57Z"},{"alias_kind":"pith_short_8","alias_value":"ZXEALUM5","created_at":"2026-07-05T00:35:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:ZXEALUM5VXS564J5T6YD3LSMCM","target":"record","payload":{"canonical_record":{"source":{"id":"2001.09293","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-01-25T10:51:42Z","cross_cats_sorted":[],"title_canon_sha256":"1d1ea8f2f2ccc7c9afbb783fb59fc833ca8f4f9c47b59b505dd14ac8a48e1557","abstract_canon_sha256":"f7b70948ba95f51cc0528be24c6830795eb1c78f36cd370f4f13e26df49d9421"},"schema_version":"1.0"},"canonical_sha256":"cdc805d19dade5df713d9fb03dae4c1315628424b9b4db2cb366fd40dcdc4d4b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:35:57.961596Z","signature_b64":"qzTkzIvbdc0Ck3if+XnBDiXGXPL6LrKoRxzBiAg4lGxy0HULSQeXGXqXsYvBTfEH8vyHlcA2rphpJUPohv/cDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdc805d19dade5df713d9fb03dae4c1315628424b9b4db2cb366fd40dcdc4d4b","last_reissued_at":"2026-07-05T00:35:57.961175Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:35:57.961175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2001.09293","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":"2026-07-05T00:35:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CJV61OAxLaxhu0GVAqogWfOUjrQSrNUL9zrTEOcg2AMUldZHvKeJezIUKQy6YISyoI3LKZaaUeFztLH2y4LwAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T06:45:10.350572Z"},"content_sha256":"45b7577c3dfc7fbf5b9a4aa2861df662d19f09031950dfdd1aa11c520eab5f08","schema_version":"1.0","event_id":"sha256:45b7577c3dfc7fbf5b9a4aa2861df662d19f09031950dfdd1aa11c520eab5f08"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:ZXEALUM5VXS564J5T6YD3LSMCM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Non-Markovian Reward Models in MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Gavin Rens, Jean-Fran\\c{c}ois Raskin","submitted_at":"2020-01-25T10:51:42Z","abstract_excerpt":"There are situations in which an agent should receive rewards only after having accomplished a series of previous tasks. In other words, the reward that the agent receives is non-Markovian. One natural and quite general way to represent history-dependent rewards is via a Mealy machine; a finite state automaton that produces output sequences (rewards in our case) from input sequences (state/action observations in our case). In our formal setting, we consider a Markov decision process (MDP) that models the dynamic of the environment in which the agent evolves and a Mealy machine synchronised wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.09293","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/2001.09293/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":"2026-07-05T00:35:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"laZBAy71grN4uW97UiiSlBOODB6btQq2CyRR+Ybuw09L+EtZ1mziLbfOWLG47PnzOAO24CS/XBrzgsvE7PHjDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T06:45:10.351334Z"},"content_sha256":"373afe64956ece1c1ac041fe1405125cc0607f53f0ddfadaf79c8f4518d27d49","schema_version":"1.0","event_id":"sha256:373afe64956ece1c1ac041fe1405125cc0607f53f0ddfadaf79c8f4518d27d49"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZXEALUM5VXS564J5T6YD3LSMCM/bundle.json","state_url":"https://pith.science/pith/ZXEALUM5VXS564J5T6YD3LSMCM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZXEALUM5VXS564J5T6YD3LSMCM/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":"2026-08-22T06:45:10Z","links":{"resolver":"https://pith.science/pith/ZXEALUM5VXS564J5T6YD3LSMCM","bundle":"https://pith.science/pith/ZXEALUM5VXS564J5T6YD3LSMCM/bundle.json","state":"https://pith.science/pith/ZXEALUM5VXS564J5T6YD3LSMCM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZXEALUM5VXS564J5T6YD3LSMCM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ZXEALUM5VXS564J5T6YD3LSMCM","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":"f7b70948ba95f51cc0528be24c6830795eb1c78f36cd370f4f13e26df49d9421","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-01-25T10:51:42Z","title_canon_sha256":"1d1ea8f2f2ccc7c9afbb783fb59fc833ca8f4f9c47b59b505dd14ac8a48e1557"},"schema_version":"1.0","source":{"id":"2001.09293","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.09293","created_at":"2026-07-05T00:35:57Z"},{"alias_kind":"arxiv_version","alias_value":"2001.09293v1","created_at":"2026-07-05T00:35:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.09293","created_at":"2026-07-05T00:35:57Z"},{"alias_kind":"pith_short_12","alias_value":"ZXEALUM5VXS5","created_at":"2026-07-05T00:35:57Z"},{"alias_kind":"pith_short_16","alias_value":"ZXEALUM5VXS564J5","created_at":"2026-07-05T00:35:57Z"},{"alias_kind":"pith_short_8","alias_value":"ZXEALUM5","created_at":"2026-07-05T00:35:57Z"}],"graph_snapshots":[{"event_id":"sha256:373afe64956ece1c1ac041fe1405125cc0607f53f0ddfadaf79c8f4518d27d49","target":"graph","created_at":"2026-07-05T00:35:57Z","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/2001.09293/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There are situations in which an agent should receive rewards only after having accomplished a series of previous tasks. In other words, the reward that the agent receives is non-Markovian. One natural and quite general way to represent history-dependent rewards is via a Mealy machine; a finite state automaton that produces output sequences (rewards in our case) from input sequences (state/action observations in our case). In our formal setting, we consider a Markov decision process (MDP) that models the dynamic of the environment in which the agent evolves and a Mealy machine synchronised wit","authors_text":"Gavin Rens, Jean-Fran\\c{c}ois Raskin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-01-25T10:51:42Z","title":"Learning Non-Markovian Reward Models in MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.09293","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":"sha256:45b7577c3dfc7fbf5b9a4aa2861df662d19f09031950dfdd1aa11c520eab5f08","target":"record","created_at":"2026-07-05T00:35:57Z","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":"f7b70948ba95f51cc0528be24c6830795eb1c78f36cd370f4f13e26df49d9421","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-01-25T10:51:42Z","title_canon_sha256":"1d1ea8f2f2ccc7c9afbb783fb59fc833ca8f4f9c47b59b505dd14ac8a48e1557"},"schema_version":"1.0","source":{"id":"2001.09293","kind":"arxiv","version":1}},"canonical_sha256":"cdc805d19dade5df713d9fb03dae4c1315628424b9b4db2cb366fd40dcdc4d4b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cdc805d19dade5df713d9fb03dae4c1315628424b9b4db2cb366fd40dcdc4d4b","first_computed_at":"2026-07-05T00:35:57.961175Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:35:57.961175Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qzTkzIvbdc0Ck3if+XnBDiXGXPL6LrKoRxzBiAg4lGxy0HULSQeXGXqXsYvBTfEH8vyHlcA2rphpJUPohv/cDA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:35:57.961596Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.09293","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:45b7577c3dfc7fbf5b9a4aa2861df662d19f09031950dfdd1aa11c520eab5f08","sha256:373afe64956ece1c1ac041fe1405125cc0607f53f0ddfadaf79c8f4518d27d49"],"state_sha256":"bdf5a47f1e8e54a639af27578d3ec81a334e86e779606f1a2e54bdd2c245a555"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NnF3Wq5y6p256AM1+aMgXNeqytjdszAVzUrHNpo4mbTbrtIxdH4Aclc4JLFw19wsezX2Mb67MDgB/b7Nb653DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T06:45:10.356187Z","bundle_sha256":"36bdef4aa79edd169b78ee71307065028dd7cace84612fe981ed243d9403b025"}}