{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:N3GAZFPCVV6X4AUOQ46YVI3OY5","short_pith_number":"pith:N3GAZFPC","schema_version":"1.0","canonical_sha256":"6ecc0c95e2ad7d7e028e873d8aa36ec77d7caba57ef2fdb7350750ef64334fb9","source":{"kind":"arxiv","id":"2111.08102","version":2},"attestation_state":"computed","paper":{"title":"The Partially Observable History Process","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.AI","authors_text":"Amy R. Greenwald, Dustin Morrill, Michael Bowling","submitted_at":"2021-11-15T22:00:14Z","abstract_excerpt":"We introduce the partially observable history process (POHP) formalism for reinforcement learning. POHP centers around the actions and observations of a single agent and abstracts away the presence of other players without reducing them to stochastic processes. Our formalism provides a streamlined interface for designing algorithms that defy categorization as exclusively single or multi-agent, and for developing theory that applies across these domains. We show how the POHP formalism unifies traditional models including the Markov decision process, the Markov game, the extensive-form game, and"},"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":"2111.08102","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-11-15T22:00:14Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"83f7bb7e233cf876066a9b47cf0ba4c015087f2537f74e269c0ddc9e355a155a","abstract_canon_sha256":"26602793bce8132ebc76b0fa00c665899f686d0db91d40410c3966ef337133e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:59:42.447060Z","signature_b64":"Oc7eNGhoj108bczIi+ergfX2XJt7ST8FpNcyr9m07HrRWNWKBjPuRUwXTIreICkOWvjDQEXI+HxzkH4Ah2LiDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ecc0c95e2ad7d7e028e873d8aa36ec77d7caba57ef2fdb7350750ef64334fb9","last_reissued_at":"2026-07-05T03:59:42.446603Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:59:42.446603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Partially Observable History Process","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.AI","authors_text":"Amy R. Greenwald, Dustin Morrill, Michael Bowling","submitted_at":"2021-11-15T22:00:14Z","abstract_excerpt":"We introduce the partially observable history process (POHP) formalism for reinforcement learning. POHP centers around the actions and observations of a single agent and abstracts away the presence of other players without reducing them to stochastic processes. Our formalism provides a streamlined interface for designing algorithms that defy categorization as exclusively single or multi-agent, and for developing theory that applies across these domains. We show how the POHP formalism unifies traditional models including the Markov decision process, the Markov game, the extensive-form game, and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.08102","kind":"arxiv","version":2},"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/2111.08102/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2111.08102","created_at":"2026-07-05T03:59:42.446674+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.08102v2","created_at":"2026-07-05T03:59:42.446674+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.08102","created_at":"2026-07-05T03:59:42.446674+00:00"},{"alias_kind":"pith_short_12","alias_value":"N3GAZFPCVV6X","created_at":"2026-07-05T03:59:42.446674+00:00"},{"alias_kind":"pith_short_16","alias_value":"N3GAZFPCVV6X4AUO","created_at":"2026-07-05T03:59:42.446674+00:00"},{"alias_kind":"pith_short_8","alias_value":"N3GAZFPC","created_at":"2026-07-05T03:59:42.446674+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/N3GAZFPCVV6X4AUOQ46YVI3OY5","json":"https://pith.science/pith/N3GAZFPCVV6X4AUOQ46YVI3OY5.json","graph_json":"https://pith.science/api/pith-number/N3GAZFPCVV6X4AUOQ46YVI3OY5/graph.json","events_json":"https://pith.science/api/pith-number/N3GAZFPCVV6X4AUOQ46YVI3OY5/events.json","paper":"https://pith.science/paper/N3GAZFPC"},"agent_actions":{"view_html":"https://pith.science/pith/N3GAZFPCVV6X4AUOQ46YVI3OY5","download_json":"https://pith.science/pith/N3GAZFPCVV6X4AUOQ46YVI3OY5.json","view_paper":"https://pith.science/paper/N3GAZFPC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.08102&json=true","fetch_graph":"https://pith.science/api/pith-number/N3GAZFPCVV6X4AUOQ46YVI3OY5/graph.json","fetch_events":"https://pith.science/api/pith-number/N3GAZFPCVV6X4AUOQ46YVI3OY5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N3GAZFPCVV6X4AUOQ46YVI3OY5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N3GAZFPCVV6X4AUOQ46YVI3OY5/action/storage_attestation","attest_author":"https://pith.science/pith/N3GAZFPCVV6X4AUOQ46YVI3OY5/action/author_attestation","sign_citation":"https://pith.science/pith/N3GAZFPCVV6X4AUOQ46YVI3OY5/action/citation_signature","submit_replication":"https://pith.science/pith/N3GAZFPCVV6X4AUOQ46YVI3OY5/action/replication_record"}},"created_at":"2026-07-05T03:59:42.446674+00:00","updated_at":"2026-07-05T03:59:42.446674+00:00"}