{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:FBB4MQK4KO3TK2X4CGXVCZZYGK","short_pith_number":"pith:FBB4MQK4","canonical_record":{"source":{"id":"2607.23474","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-26T05:58:23Z","cross_cats_sorted":[],"title_canon_sha256":"ceea3fb3233fbde9f8f8610dcd9cb570d38f92d8010f14db0d69707fd43fda71","abstract_canon_sha256":"ba70592d6b9d30f629e3cb93ee5a35c821163a9df82c0e299a1ead3769bf113c"},"schema_version":"1.0"},"canonical_sha256":"2843c6415c53b7356afc11af51673832afddb3bf52c988edeee11eb21e609651","source":{"kind":"arxiv","id":"2607.23474","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23474","created_at":"2026-07-28T01:22:54Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23474v1","created_at":"2026-07-28T01:22:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23474","created_at":"2026-07-28T01:22:54Z"},{"alias_kind":"pith_short_12","alias_value":"FBB4MQK4KO3T","created_at":"2026-07-28T01:22:54Z"},{"alias_kind":"pith_short_16","alias_value":"FBB4MQK4KO3TK2X4","created_at":"2026-07-28T01:22:54Z"},{"alias_kind":"pith_short_8","alias_value":"FBB4MQK4","created_at":"2026-07-28T01:22:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:FBB4MQK4KO3TK2X4CGXVCZZYGK","target":"record","payload":{"canonical_record":{"source":{"id":"2607.23474","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-26T05:58:23Z","cross_cats_sorted":[],"title_canon_sha256":"ceea3fb3233fbde9f8f8610dcd9cb570d38f92d8010f14db0d69707fd43fda71","abstract_canon_sha256":"ba70592d6b9d30f629e3cb93ee5a35c821163a9df82c0e299a1ead3769bf113c"},"schema_version":"1.0"},"canonical_sha256":"2843c6415c53b7356afc11af51673832afddb3bf52c988edeee11eb21e609651","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:22:54.346806Z","signature_b64":"2mRPQjlG+35NsxB7P6oWn0CQl2hXsZhdpMZVFDJJXbcvMVa3tlIg/dftxDfzfIIwPBnT9vNAXXRhPBXnD0/VAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2843c6415c53b7356afc11af51673832afddb3bf52c988edeee11eb21e609651","last_reissued_at":"2026-07-28T01:22:54.345983Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:22:54.345983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.23474","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":"2026-07-28T01:22:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2xy8tTvzQMvYegwtVitGpTtjdp8u/HeZlXZaJiirMhyiX0/6eIqUdJt5/Ip8PIouZs/LURter1RLwZ6YHjK4Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:34:04.440478Z"},"content_sha256":"e32f25ac9ebd9819d67cd9605772f604eda7a372124f931589ee6a7254507940","schema_version":"1.0","event_id":"sha256:e32f25ac9ebd9819d67cd9605772f604eda7a372124f931589ee6a7254507940"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:FBB4MQK4KO3TK2X4CGXVCZZYGK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sparse Gaussian-Mixture-Model Q-Functions via Hadamard Overparametrization for Online Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Konstantinos Slavakis, Minh Vu","submitted_at":"2026-07-26T05:58:23Z","abstract_excerpt":"This paper develops an online, off-policy policy-iteration framework for reinforcement learning (RL), based on sparse Gaussian-mixture-model Q-functions (S-GMM-QFs). The framework reconciles streaming, non-stationary data with the Riemannian structure of the parameter space while handling distributional mismatch through experience replay. S-GMM-QFs are introduced via Hadamard overparametrization, enabling interpretable sparsification through smooth regularization that facilitates Riemannian-based optimization. Overparametrization allows the framework to adaptively identify meaningful component"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23474","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/2607.23474/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":"2026-07-28T01:22:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aCitvgOkW94k+ovkbKFHQI5+ASWOesVhrsawEJ2Oml1o8L9AiFSb6S7E8Hhii+Bt+GHHUZjqtYFHdtvgpx0GDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:34:04.441003Z"},"content_sha256":"533e3991659791e79d42bd2124ef83b7e4642a190e961d1c577fb4269141203d","schema_version":"1.0","event_id":"sha256:533e3991659791e79d42bd2124ef83b7e4642a190e961d1c577fb4269141203d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FBB4MQK4KO3TK2X4CGXVCZZYGK/bundle.json","state_url":"https://pith.science/pith/FBB4MQK4KO3TK2X4CGXVCZZYGK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FBB4MQK4KO3TK2X4CGXVCZZYGK/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":"2026-08-09T04:34:04Z","links":{"resolver":"https://pith.science/pith/FBB4MQK4KO3TK2X4CGXVCZZYGK","bundle":"https://pith.science/pith/FBB4MQK4KO3TK2X4CGXVCZZYGK/bundle.json","state":"https://pith.science/pith/FBB4MQK4KO3TK2X4CGXVCZZYGK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FBB4MQK4KO3TK2X4CGXVCZZYGK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FBB4MQK4KO3TK2X4CGXVCZZYGK","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":"ba70592d6b9d30f629e3cb93ee5a35c821163a9df82c0e299a1ead3769bf113c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-26T05:58:23Z","title_canon_sha256":"ceea3fb3233fbde9f8f8610dcd9cb570d38f92d8010f14db0d69707fd43fda71"},"schema_version":"1.0","source":{"id":"2607.23474","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23474","created_at":"2026-07-28T01:22:54Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23474v1","created_at":"2026-07-28T01:22:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23474","created_at":"2026-07-28T01:22:54Z"},{"alias_kind":"pith_short_12","alias_value":"FBB4MQK4KO3T","created_at":"2026-07-28T01:22:54Z"},{"alias_kind":"pith_short_16","alias_value":"FBB4MQK4KO3TK2X4","created_at":"2026-07-28T01:22:54Z"},{"alias_kind":"pith_short_8","alias_value":"FBB4MQK4","created_at":"2026-07-28T01:22:54Z"}],"graph_snapshots":[{"event_id":"sha256:533e3991659791e79d42bd2124ef83b7e4642a190e961d1c577fb4269141203d","target":"graph","created_at":"2026-07-28T01:22:54Z","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/2607.23474/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper develops an online, off-policy policy-iteration framework for reinforcement learning (RL), based on sparse Gaussian-mixture-model Q-functions (S-GMM-QFs). The framework reconciles streaming, non-stationary data with the Riemannian structure of the parameter space while handling distributional mismatch through experience replay. S-GMM-QFs are introduced via Hadamard overparametrization, enabling interpretable sparsification through smooth regularization that facilitates Riemannian-based optimization. Overparametrization allows the framework to adaptively identify meaningful component","authors_text":"Konstantinos Slavakis, Minh Vu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-26T05:58:23Z","title":"Sparse Gaussian-Mixture-Model Q-Functions via Hadamard Overparametrization for Online Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23474","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:e32f25ac9ebd9819d67cd9605772f604eda7a372124f931589ee6a7254507940","target":"record","created_at":"2026-07-28T01:22:54Z","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":"ba70592d6b9d30f629e3cb93ee5a35c821163a9df82c0e299a1ead3769bf113c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-26T05:58:23Z","title_canon_sha256":"ceea3fb3233fbde9f8f8610dcd9cb570d38f92d8010f14db0d69707fd43fda71"},"schema_version":"1.0","source":{"id":"2607.23474","kind":"arxiv","version":1}},"canonical_sha256":"2843c6415c53b7356afc11af51673832afddb3bf52c988edeee11eb21e609651","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2843c6415c53b7356afc11af51673832afddb3bf52c988edeee11eb21e609651","first_computed_at":"2026-07-28T01:22:54.345983Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:22:54.345983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2mRPQjlG+35NsxB7P6oWn0CQl2hXsZhdpMZVFDJJXbcvMVa3tlIg/dftxDfzfIIwPBnT9vNAXXRhPBXnD0/VAg==","signature_status":"signed_v1","signed_at":"2026-07-28T01:22:54.346806Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.23474","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e32f25ac9ebd9819d67cd9605772f604eda7a372124f931589ee6a7254507940","sha256:533e3991659791e79d42bd2124ef83b7e4642a190e961d1c577fb4269141203d"],"state_sha256":"b2a9143f9f630c69e50671382261ce2472153eb5c2e7477480854534eeb9effe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BJmFUp8uFfg93f3SEd/swe9Bl51842eqL8nMkKmh9GO4/Nk3WLnp1D81bzKVH4silhQsTMZ5liz0LwxR9KV4AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:34:04.446584Z","bundle_sha256":"9e9c0968b72e5437639f8e6d9ee3559dc29eb52463ecc1480ef0d2c8a8607a83"}}