{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BGEVVV3QKICAFZOKC2VOEMDR4X","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":"8f96387dfc1caac9980419a21a6be34695a6620a0a643368797ab7bc68a8f53e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-27T23:16:27Z","title_canon_sha256":"d62174e3cf3e46fc96e7be67fb770d83fdb758be2c51073c6454585bc3bd5e46"},"schema_version":"1.0","source":{"id":"2603.27044","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.27044","created_at":"2026-07-07T02:18:39Z"},{"alias_kind":"arxiv_version","alias_value":"2603.27044v3","created_at":"2026-07-07T02:18:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.27044","created_at":"2026-07-07T02:18:39Z"},{"alias_kind":"pith_short_12","alias_value":"BGEVVV3QKICA","created_at":"2026-07-07T02:18:39Z"},{"alias_kind":"pith_short_16","alias_value":"BGEVVV3QKICAFZOK","created_at":"2026-07-07T02:18:39Z"},{"alias_kind":"pith_short_8","alias_value":"BGEVVV3Q","created_at":"2026-07-07T02:18:39Z"}],"graph_snapshots":[{"event_id":"sha256:48de3b509dae008bb6262994cceee9f9c0eca4452df555b5dea1ad43dede0a9c","target":"graph","created_at":"2026-07-07T02:18:39Z","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/2603.27044/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep Reinforcement Learning (DRL) is widely recognized as sample-inefficient, a limitation attributable in part to the high dimensionality and substantial functional redundancy inherent to the policy parameter space. A recent framework, which we refer to as Action-based Policy Compression (APC), mitigates this issue by compressing the parameter space $\\Theta$ into a low-dimensional latent manifold $\\mathcal Z$ using a learned generative mapping $g:\\mathcal Z \\to \\Theta$. However, its performance is severely constrained by relying on immediate action-matching as a reconstruction loss, a myopic ","authors_text":"Andrea Fraschini, Davide Tenedini, Marcello Restelli, Mirco Mutti, Riccardo Zamboni","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-27T23:16:27Z","title":"Unsupervised Behavioral Compression: Learning Low-Dimensional Policy Manifolds through State-Occupancy Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.27044","kind":"arxiv","version":3},"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":"sha256:8bd88db8ca4239fb103aa43bc42b0215d3a7cd6280d08c44bf5c15741b31f775","target":"record","created_at":"2026-07-07T02:18:39Z","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":"8f96387dfc1caac9980419a21a6be34695a6620a0a643368797ab7bc68a8f53e","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-27T23:16:27Z","title_canon_sha256":"d62174e3cf3e46fc96e7be67fb770d83fdb758be2c51073c6454585bc3bd5e46"},"schema_version":"1.0","source":{"id":"2603.27044","kind":"arxiv","version":3}},"canonical_sha256":"09895ad770520402e5ca16aae23071e5ea0ead277bfc910407a9ea260c9182b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09895ad770520402e5ca16aae23071e5ea0ead277bfc910407a9ea260c9182b1","first_computed_at":"2026-07-07T02:18:39.189567Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:18:39.189567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oMOfF1mc2UXVZ9l8tYRmJHXNRb8BtBVUWcCpHH96tcIi0pxoppogIG+vKfa7H+rBDy5qDb8u9oeoOTDCk6+eCw==","signature_status":"signed_v1","signed_at":"2026-07-07T02:18:39.190507Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.27044","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8bd88db8ca4239fb103aa43bc42b0215d3a7cd6280d08c44bf5c15741b31f775","sha256:48de3b509dae008bb6262994cceee9f9c0eca4452df555b5dea1ad43dede0a9c"],"state_sha256":"a5ba0157bf294ffd7a4be78ae13e736a993609d996bca5d7e49569c01ef2105f"}