{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FZFG4CUPL7O3U2OU7HMTB7LP5N","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":"ed279ba4633ff39fe4900683d22fab6728c6dca42f04ff73e39e76bf8cc72250","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-21T15:00:32Z","title_canon_sha256":"66bf220f879e093de26b84a320a65431d68c1c954406d022e5667e45b332ad1d"},"schema_version":"1.0","source":{"id":"2512.18763","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.18763","created_at":"2026-07-22T01:22:17Z"},{"alias_kind":"arxiv_version","alias_value":"2512.18763v2","created_at":"2026-07-22T01:22:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.18763","created_at":"2026-07-22T01:22:17Z"},{"alias_kind":"pith_short_12","alias_value":"FZFG4CUPL7O3","created_at":"2026-07-22T01:22:17Z"},{"alias_kind":"pith_short_16","alias_value":"FZFG4CUPL7O3U2OU","created_at":"2026-07-22T01:22:17Z"},{"alias_kind":"pith_short_8","alias_value":"FZFG4CUP","created_at":"2026-07-22T01:22:17Z"}],"graph_snapshots":[{"event_id":"sha256:983fcdd4869e285e5b5552fdfeb5d400e2220a9d7946b0eb88b035f52df07ac8","target":"graph","created_at":"2026-07-22T01:22:17Z","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/2512.18763/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unlike their conventional use as estimators of probability density functions in reinforcement learning (RL), this paper introduces a novel function-approximation role for Gaussian mixture models (GMMs) as direct surrogates for Q-function losses. The proposed estimators, termed GMM-QFs, possess substantial representational capacity, as they are shown to be universal approximators over a broad class of functions. They are further embedded within Bellman residuals, where their learnable parameters--a fixed number of mixing weights, together with Gaussian mean vectors and covariance matrices--are ","authors_text":"Konstantinos Slavakis, Minh Vu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-21T15:00:32Z","title":"Gaussian-Mixture-Model Q-Functions for Policy Iteration in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.18763","kind":"arxiv","version":2},"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":"sha256:504de035f319cb198b8f27419494627db23a138b4bfec5d49663243cdf5bf4a6","target":"record","created_at":"2026-07-22T01:22:17Z","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":"ed279ba4633ff39fe4900683d22fab6728c6dca42f04ff73e39e76bf8cc72250","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-21T15:00:32Z","title_canon_sha256":"66bf220f879e093de26b84a320a65431d68c1c954406d022e5667e45b332ad1d"},"schema_version":"1.0","source":{"id":"2512.18763","kind":"arxiv","version":2}},"canonical_sha256":"2e4a6e0a8f5fddba69d4f9d930fd6feb7ec9124aa4937180152c801b9c6405c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e4a6e0a8f5fddba69d4f9d930fd6feb7ec9124aa4937180152c801b9c6405c3","first_computed_at":"2026-07-22T01:22:17.962860Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-22T01:22:17.962860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a37df4MrvJHFuscETSHZPjm/R1G36JXjXCB0ysfRnewdeDAXHbaduTX+Y0mDdBFegcKVBg8l5AAn9/zDFs2nAg==","signature_status":"signed_v1","signed_at":"2026-07-22T01:22:17.963780Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.18763","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:504de035f319cb198b8f27419494627db23a138b4bfec5d49663243cdf5bf4a6","sha256:983fcdd4869e285e5b5552fdfeb5d400e2220a9d7946b0eb88b035f52df07ac8"],"state_sha256":"558e694ebc7fdb364003435b5864d249ef4a1ed616b73d8c18b9c4ac612c3ccd"}