{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WD36G5GQQVEF4ATTUTZSP4Q7GS","short_pith_number":"pith:WD36G5GQ","schema_version":"1.0","canonical_sha256":"b0f7e374d085485e0273a4f327f21f34a76d12cd86972b7a684290a025e36f0b","source":{"kind":"arxiv","id":"2601.23225","version":2},"attestation_state":"computed","paper":{"title":"Agile Reinforcement Learning through Separable Neural Architecture and Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Rajib Mostakim, Reza T. Batley, Sourav Saha","submitted_at":"2026-01-30T17:47:36Z","abstract_excerpt":"Deep reinforcement learning (RL) is increasingly deployed in resource-constrained environments, yet go-to function approximators - multilayer perceptrons (MLPs) - are often parameter-inefficient due to an imperfect inductive bias for the smooth structure of many value functions. This mismatch can also hinder sample efficiency and slow policy learning in this capacity-limited regime. Although model compression techniques exist, they operate post-hoc and do not improve learning efficiency. Spline-based architectures such as Kolmogorov-Arnold Networks (KANs) have been shown to offer parameter eff"},"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":"2601.23225","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-30T17:47:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c5957caffc8c42973b98471023c4bc8aa52fd002067eda136178ef5e2045d762","abstract_canon_sha256":"b4d9b9bf4289e2381055124277d2f9b64b5e28fc2b90d4a29b648d1fe7f5d26e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:33.370638Z","signature_b64":"mJ4PZ4oSR4SsgISe2HbHNFo0QalyoAB6KlHPLKs8qisZzkJVzZa3Yza0381kp9Ev6V8qeg+TlNDpiSrivueMAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0f7e374d085485e0273a4f327f21f34a76d12cd86972b7a684290a025e36f0b","last_reissued_at":"2026-06-30T01:17:33.370031Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:33.370031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Agile Reinforcement Learning through Separable Neural Architecture and Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Rajib Mostakim, Reza T. Batley, Sourav Saha","submitted_at":"2026-01-30T17:47:36Z","abstract_excerpt":"Deep reinforcement learning (RL) is increasingly deployed in resource-constrained environments, yet go-to function approximators - multilayer perceptrons (MLPs) - are often parameter-inefficient due to an imperfect inductive bias for the smooth structure of many value functions. This mismatch can also hinder sample efficiency and slow policy learning in this capacity-limited regime. Although model compression techniques exist, they operate post-hoc and do not improve learning efficiency. Spline-based architectures such as Kolmogorov-Arnold Networks (KANs) have been shown to offer parameter eff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.23225","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/2601.23225/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":"2601.23225","created_at":"2026-06-30T01:17:33.370086+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.23225v2","created_at":"2026-06-30T01:17:33.370086+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.23225","created_at":"2026-06-30T01:17:33.370086+00:00"},{"alias_kind":"pith_short_12","alias_value":"WD36G5GQQVEF","created_at":"2026-06-30T01:17:33.370086+00:00"},{"alias_kind":"pith_short_16","alias_value":"WD36G5GQQVEF4ATT","created_at":"2026-06-30T01:17:33.370086+00:00"},{"alias_kind":"pith_short_8","alias_value":"WD36G5GQ","created_at":"2026-06-30T01:17:33.370086+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/WD36G5GQQVEF4ATTUTZSP4Q7GS","json":"https://pith.science/pith/WD36G5GQQVEF4ATTUTZSP4Q7GS.json","graph_json":"https://pith.science/api/pith-number/WD36G5GQQVEF4ATTUTZSP4Q7GS/graph.json","events_json":"https://pith.science/api/pith-number/WD36G5GQQVEF4ATTUTZSP4Q7GS/events.json","paper":"https://pith.science/paper/WD36G5GQ"},"agent_actions":{"view_html":"https://pith.science/pith/WD36G5GQQVEF4ATTUTZSP4Q7GS","download_json":"https://pith.science/pith/WD36G5GQQVEF4ATTUTZSP4Q7GS.json","view_paper":"https://pith.science/paper/WD36G5GQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.23225&json=true","fetch_graph":"https://pith.science/api/pith-number/WD36G5GQQVEF4ATTUTZSP4Q7GS/graph.json","fetch_events":"https://pith.science/api/pith-number/WD36G5GQQVEF4ATTUTZSP4Q7GS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WD36G5GQQVEF4ATTUTZSP4Q7GS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WD36G5GQQVEF4ATTUTZSP4Q7GS/action/storage_attestation","attest_author":"https://pith.science/pith/WD36G5GQQVEF4ATTUTZSP4Q7GS/action/author_attestation","sign_citation":"https://pith.science/pith/WD36G5GQQVEF4ATTUTZSP4Q7GS/action/citation_signature","submit_replication":"https://pith.science/pith/WD36G5GQQVEF4ATTUTZSP4Q7GS/action/replication_record"}},"created_at":"2026-06-30T01:17:33.370086+00:00","updated_at":"2026-06-30T01:17:33.370086+00:00"}