{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PUYAYCP4JE6N3EEOMSPDVRFBYN","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":"c820ffa316f2918dfc0199e0954600965a001da915c96240ddd52fb1af5e1ce6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-28T14:06:44Z","title_canon_sha256":"40c83ab6d68c54086337e2cff8ee122a9bed4ea599decefc1c6f6c0d4e571c00"},"schema_version":"1.0","source":{"id":"2507.20853","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.20853","created_at":"2026-07-05T11:44:27Z"},{"alias_kind":"arxiv_version","alias_value":"2507.20853v1","created_at":"2026-07-05T11:44:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20853","created_at":"2026-07-05T11:44:27Z"},{"alias_kind":"pith_short_12","alias_value":"PUYAYCP4JE6N","created_at":"2026-07-05T11:44:27Z"},{"alias_kind":"pith_short_16","alias_value":"PUYAYCP4JE6N3EEO","created_at":"2026-07-05T11:44:27Z"},{"alias_kind":"pith_short_8","alias_value":"PUYAYCP4","created_at":"2026-07-05T11:44:27Z"}],"graph_snapshots":[{"event_id":"sha256:e8adae0e52c22a0b01385cd35268315383d4c4e78bad2fda9378a04c65200bcf","target":"graph","created_at":"2026-07-05T11:44:27Z","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/2507.20853/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Advances in reinforcement learning (RL) have led to its successful application in complex tasks with continuous state and action spaces. Despite these advances in practice, most theoretical work pertains to finite state and action spaces. We propose building a theoretical understanding of continuous state and action spaces by employing a geometric lens to understand the locally attained set of states. The set of all parametrised policies learnt through a semi-gradient based approach induces a set of attainable states in RL. We show that the training dynamics of a two-layer neural policy induce","authors_text":"George Konidaris, Omer Gottesman, Saket Tiwari","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-28T14:06:44Z","title":"Geometry of Neural Reinforcement Learning in Continuous State and Action Spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20853","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":"sha256:67cfd1426c919ca2af40cef7498fb9453f906a8ec030b4e470e68ac3d7764ecf","target":"record","created_at":"2026-07-05T11:44:27Z","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":"c820ffa316f2918dfc0199e0954600965a001da915c96240ddd52fb1af5e1ce6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-28T14:06:44Z","title_canon_sha256":"40c83ab6d68c54086337e2cff8ee122a9bed4ea599decefc1c6f6c0d4e571c00"},"schema_version":"1.0","source":{"id":"2507.20853","kind":"arxiv","version":1}},"canonical_sha256":"7d300c09fc493cdd908e649e3ac4a1c36e2e68fc7f5541985e03e5dc8c9073b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7d300c09fc493cdd908e649e3ac4a1c36e2e68fc7f5541985e03e5dc8c9073b9","first_computed_at":"2026-07-05T11:44:27.021360Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:27.021360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gg4hUy/i85cq3rZaCvIcyeHnFg/7TENDeUTUL176/wAUjXiBGlRA7vSG9P2jV3JP0wL3FsV8GR5i6Jww05XIAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:27.021783Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.20853","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:67cfd1426c919ca2af40cef7498fb9453f906a8ec030b4e470e68ac3d7764ecf","sha256:e8adae0e52c22a0b01385cd35268315383d4c4e78bad2fda9378a04c65200bcf"],"state_sha256":"dba70eeef39ff1a7e60ca373af73ba4e35d71331a17e379f67aa8cc023c35362"}