{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WP6OPLHGKD7FH4XMFFLKDSEECP","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":"798bd4e0287bd314beb51e37a25845b93f2a5b36241918407c2455c3b4c6a283","cross_cats_sorted":["econ.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-19T16:01:04Z","title_canon_sha256":"648dd181abd5832d5198c814951fc95e34c94b0239146ed0de97134244cb8eb4"},"schema_version":"1.0","source":{"id":"2607.17316","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.17316","created_at":"2026-07-21T01:21:26Z"},{"alias_kind":"arxiv_version","alias_value":"2607.17316v1","created_at":"2026-07-21T01:21:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17316","created_at":"2026-07-21T01:21:26Z"},{"alias_kind":"pith_short_12","alias_value":"WP6OPLHGKD7F","created_at":"2026-07-21T01:21:26Z"},{"alias_kind":"pith_short_16","alias_value":"WP6OPLHGKD7FH4XM","created_at":"2026-07-21T01:21:26Z"},{"alias_kind":"pith_short_8","alias_value":"WP6OPLHG","created_at":"2026-07-21T01:21:26Z"}],"graph_snapshots":[{"event_id":"sha256:e7614207987a9d278794579c4cc7d0c41f8b7b88742935ff4a2783f5c3a094ee","target":"graph","created_at":"2026-07-21T01:21:26Z","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/2607.17316/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The softmax policy $\\pi(a \\mid s) \\propto \\exp(\\beta Q(s,a))$ is the default model of stochastic choice in reinforcement learning (RL). Various justifications based on robustness, exploration, and optimization have been offered in the RL literature, but none uniquely derives the softmax form from first principles. This leaves a basic tension unresolved: the entropy bonus in the soft Bellman equation violates the Independence axiom that underwrites the Markov decision process (MDP) reward structure. We dissolve this tension by distinguishing two kinds of randomness: chance and choice. By restri","authors_text":"Silviu Pitis","cross_cats":["econ.TH"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-19T16:01:04Z","title":"Rationalizing Boltzmann Rationality: An Axiomatic Characterization of Entropy-Regularized Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17316","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":"sha256:6ae13637ab68f356f46edb56cf646f06a7f2d4c924ec58415ed5712db4305de8","target":"record","created_at":"2026-07-21T01:21:26Z","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":"798bd4e0287bd314beb51e37a25845b93f2a5b36241918407c2455c3b4c6a283","cross_cats_sorted":["econ.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-19T16:01:04Z","title_canon_sha256":"648dd181abd5832d5198c814951fc95e34c94b0239146ed0de97134244cb8eb4"},"schema_version":"1.0","source":{"id":"2607.17316","kind":"arxiv","version":1}},"canonical_sha256":"b3fce7ace650fe53f2ec2956a1c88413fc3dee1feaf07a72ab5257b5f5466a96","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b3fce7ace650fe53f2ec2956a1c88413fc3dee1feaf07a72ab5257b5f5466a96","first_computed_at":"2026-07-21T01:21:26.944810Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T01:21:26.944810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8prZ4c/kjsxhLMCD4cnIVmcd3f1wm7+L5deVRpNqC1xEIzlNW6XP/IWI8olnAGQDt07mCgNnDh4ORiwIUj46Cg==","signature_status":"signed_v1","signed_at":"2026-07-21T01:21:26.945671Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.17316","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ae13637ab68f356f46edb56cf646f06a7f2d4c924ec58415ed5712db4305de8","sha256:e7614207987a9d278794579c4cc7d0c41f8b7b88742935ff4a2783f5c3a094ee"],"state_sha256":"785afe3eca1309208afad81d94f45f94c279268ba64ad4bc687552570fe68ab2"}