{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UQEABDTDSSZUSEKVSBWK6WZHWI","short_pith_number":"pith:UQEABDTD","schema_version":"1.0","canonical_sha256":"a408008e6394b3491155906caf5b27b20aa41189193778d6c85bf741816a139e","source":{"kind":"arxiv","id":"2505.23857","version":2},"attestation_state":"computed","paper":{"title":"A Convolution and Attention Based Encoder for Reinforcement Learning under Partial Observability","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Wuhao Wang, Zhiyong Chen","submitted_at":"2025-05-29T06:22:06Z","abstract_excerpt":"Partially Observable Markov Decision Processes (POMDPs) remain a core challenge in reinforcement learning due to incomplete state information. We address this by reformulating POMDPs as fully observable processes with fixed-length observation histories as augmented states. To efficiently encode these histories, we propose a lightweight temporal encoder based on depthwise separable convolution and self-attention, avoiding the overhead of recurrent and Transformer-based models. Integrated into an actor-critic framework, our method achieves superior performance on continuous control benchmarks un"},"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":"2505.23857","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T06:22:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2f9fee096eef7b7a7aa783d8c7670eee98e4bdaa8ea1562b8073a0517896213b","abstract_canon_sha256":"12c465d1a66f28edb1a033d3462326f192b1786682289ce580eba42dc5a97d61"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:11:18.297666Z","signature_b64":"qw+D8R1/88TwMfqdD7otQ9UKGndEqVRmxlxEKE1rPnmwb2Kws+Aq7xHQYzpBBehnEH2rxO6UpWYMTl3ZNKrCDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a408008e6394b3491155906caf5b27b20aa41189193778d6c85bf741816a139e","last_reissued_at":"2026-07-05T12:11:18.297105Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:11:18.297105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Convolution and Attention Based Encoder for Reinforcement Learning under Partial Observability","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Wuhao Wang, Zhiyong Chen","submitted_at":"2025-05-29T06:22:06Z","abstract_excerpt":"Partially Observable Markov Decision Processes (POMDPs) remain a core challenge in reinforcement learning due to incomplete state information. We address this by reformulating POMDPs as fully observable processes with fixed-length observation histories as augmented states. To efficiently encode these histories, we propose a lightweight temporal encoder based on depthwise separable convolution and self-attention, avoiding the overhead of recurrent and Transformer-based models. Integrated into an actor-critic framework, our method achieves superior performance on continuous control benchmarks un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23857","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/2505.23857/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":"2505.23857","created_at":"2026-07-05T12:11:18.297167+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23857v2","created_at":"2026-07-05T12:11:18.297167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23857","created_at":"2026-07-05T12:11:18.297167+00:00"},{"alias_kind":"pith_short_12","alias_value":"UQEABDTDSSZU","created_at":"2026-07-05T12:11:18.297167+00:00"},{"alias_kind":"pith_short_16","alias_value":"UQEABDTDSSZUSEKV","created_at":"2026-07-05T12:11:18.297167+00:00"},{"alias_kind":"pith_short_8","alias_value":"UQEABDTD","created_at":"2026-07-05T12:11:18.297167+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/UQEABDTDSSZUSEKVSBWK6WZHWI","json":"https://pith.science/pith/UQEABDTDSSZUSEKVSBWK6WZHWI.json","graph_json":"https://pith.science/api/pith-number/UQEABDTDSSZUSEKVSBWK6WZHWI/graph.json","events_json":"https://pith.science/api/pith-number/UQEABDTDSSZUSEKVSBWK6WZHWI/events.json","paper":"https://pith.science/paper/UQEABDTD"},"agent_actions":{"view_html":"https://pith.science/pith/UQEABDTDSSZUSEKVSBWK6WZHWI","download_json":"https://pith.science/pith/UQEABDTDSSZUSEKVSBWK6WZHWI.json","view_paper":"https://pith.science/paper/UQEABDTD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23857&json=true","fetch_graph":"https://pith.science/api/pith-number/UQEABDTDSSZUSEKVSBWK6WZHWI/graph.json","fetch_events":"https://pith.science/api/pith-number/UQEABDTDSSZUSEKVSBWK6WZHWI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UQEABDTDSSZUSEKVSBWK6WZHWI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UQEABDTDSSZUSEKVSBWK6WZHWI/action/storage_attestation","attest_author":"https://pith.science/pith/UQEABDTDSSZUSEKVSBWK6WZHWI/action/author_attestation","sign_citation":"https://pith.science/pith/UQEABDTDSSZUSEKVSBWK6WZHWI/action/citation_signature","submit_replication":"https://pith.science/pith/UQEABDTDSSZUSEKVSBWK6WZHWI/action/replication_record"}},"created_at":"2026-07-05T12:11:18.297167+00:00","updated_at":"2026-07-05T12:11:18.297167+00:00"}