{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZVXQMPBXUKAGDRDINYPSZTDIBZ","short_pith_number":"pith:ZVXQMPBX","canonical_record":{"source":{"id":"2605.24357","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T02:41:07Z","cross_cats_sorted":[],"title_canon_sha256":"5fffcfa5e1a3c34d06a123424309c9578e7ccebc9441ec8827862cb7555c132a","abstract_canon_sha256":"31d67085d3cec2e5bf0553559dd5f7d9ab886474b31a4fcb91c88bcfd0b737ab"},"schema_version":"1.0"},"canonical_sha256":"cd6f063c37a28061c4686e1f2ccc680e736c8cb86fc1fa45af0a6aceffd6cf98","source":{"kind":"arxiv","id":"2605.24357","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24357","created_at":"2026-05-26T01:03:01Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24357v1","created_at":"2026-05-26T01:03:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24357","created_at":"2026-05-26T01:03:01Z"},{"alias_kind":"pith_short_12","alias_value":"ZVXQMPBXUKAG","created_at":"2026-05-26T01:03:01Z"},{"alias_kind":"pith_short_16","alias_value":"ZVXQMPBXUKAGDRDI","created_at":"2026-05-26T01:03:01Z"},{"alias_kind":"pith_short_8","alias_value":"ZVXQMPBX","created_at":"2026-05-26T01:03:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZVXQMPBXUKAGDRDINYPSZTDIBZ","target":"record","payload":{"canonical_record":{"source":{"id":"2605.24357","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T02:41:07Z","cross_cats_sorted":[],"title_canon_sha256":"5fffcfa5e1a3c34d06a123424309c9578e7ccebc9441ec8827862cb7555c132a","abstract_canon_sha256":"31d67085d3cec2e5bf0553559dd5f7d9ab886474b31a4fcb91c88bcfd0b737ab"},"schema_version":"1.0"},"canonical_sha256":"cd6f063c37a28061c4686e1f2ccc680e736c8cb86fc1fa45af0a6aceffd6cf98","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:01.669101Z","signature_b64":"jP4jA4hOLDhybAdemVqaHQ2SLVs44+JcoFWd7aqf8J3AbhuxFsg6jOdONeNjSWOhq1T9/5B1P2qIn+mh194DCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd6f063c37a28061c4686e1f2ccc680e736c8cb86fc1fa45af0a6aceffd6cf98","last_reissued_at":"2026-05-26T01:03:01.668505Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:01.668505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.24357","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":"2026-05-26T01:03:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cB9yVRbSyZt5EvsvOHOFSbED3Pn+JuDzciKEM/lJAp1NCxZiOqnyKAU95ikNqRvESnt/9tnADTijoi7oHJ7CDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T19:15:44.217718Z"},"content_sha256":"c6470005dd1d1f4d9bf0aa77d2aa1fd775710ebd877e910b7260868b7527f3f9","schema_version":"1.0","event_id":"sha256:c6470005dd1d1f4d9bf0aa77d2aa1fd775710ebd877e910b7260868b7527f3f9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZVXQMPBXUKAGDRDINYPSZTDIBZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Refined Analysis of Entropy-Regularized Actor-Critic","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniil Tiapkin, Eric Moulines, Paul Mangold, Safwan Labbi","submitted_at":"2026-05-23T02:41:07Z","abstract_excerpt":"In this paper, we study the role of the critic in actor--critic for entropy-regularized, finite, discounted environments. We establish that, when the critic is exact, using the latter as a baseline is a variance-reduction method in a strong sense. In this case, actor--critic with stochastic gradients matches the sample complexity of deterministic policy gradient, reaching an $\\epsilon$-optimal regularized value with $\\tilde{O}(\\log(1/\\epsilon))$ samples. In practice, the critic is learned alongside the actor: the variance of the actor update is then influenced by the critic's variance and bias"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24357","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/2605.24357/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":"2026-05-26T01:03:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hh8hsctngS8B7OcHufvBXz+SlOoe5oyEHjW6hfHEsy3jFr5zk+R3t5GGAoXrcyyJEIyuVgS5lDDgGc3kgThiBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T19:15:44.218094Z"},"content_sha256":"e238b9f5e827f3a2ec68ff01cdda8c161dc135442f8c8a29fb1836c824469307","schema_version":"1.0","event_id":"sha256:e238b9f5e827f3a2ec68ff01cdda8c161dc135442f8c8a29fb1836c824469307"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZVXQMPBXUKAGDRDINYPSZTDIBZ/bundle.json","state_url":"https://pith.science/pith/ZVXQMPBXUKAGDRDINYPSZTDIBZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZVXQMPBXUKAGDRDINYPSZTDIBZ/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":"2026-07-02T19:15:44Z","links":{"resolver":"https://pith.science/pith/ZVXQMPBXUKAGDRDINYPSZTDIBZ","bundle":"https://pith.science/pith/ZVXQMPBXUKAGDRDINYPSZTDIBZ/bundle.json","state":"https://pith.science/pith/ZVXQMPBXUKAGDRDINYPSZTDIBZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZVXQMPBXUKAGDRDINYPSZTDIBZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZVXQMPBXUKAGDRDINYPSZTDIBZ","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":"31d67085d3cec2e5bf0553559dd5f7d9ab886474b31a4fcb91c88bcfd0b737ab","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T02:41:07Z","title_canon_sha256":"5fffcfa5e1a3c34d06a123424309c9578e7ccebc9441ec8827862cb7555c132a"},"schema_version":"1.0","source":{"id":"2605.24357","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24357","created_at":"2026-05-26T01:03:01Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24357v1","created_at":"2026-05-26T01:03:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24357","created_at":"2026-05-26T01:03:01Z"},{"alias_kind":"pith_short_12","alias_value":"ZVXQMPBXUKAG","created_at":"2026-05-26T01:03:01Z"},{"alias_kind":"pith_short_16","alias_value":"ZVXQMPBXUKAGDRDI","created_at":"2026-05-26T01:03:01Z"},{"alias_kind":"pith_short_8","alias_value":"ZVXQMPBX","created_at":"2026-05-26T01:03:01Z"}],"graph_snapshots":[{"event_id":"sha256:e238b9f5e827f3a2ec68ff01cdda8c161dc135442f8c8a29fb1836c824469307","target":"graph","created_at":"2026-05-26T01:03:01Z","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/2605.24357/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we study the role of the critic in actor--critic for entropy-regularized, finite, discounted environments. We establish that, when the critic is exact, using the latter as a baseline is a variance-reduction method in a strong sense. In this case, actor--critic with stochastic gradients matches the sample complexity of deterministic policy gradient, reaching an $\\epsilon$-optimal regularized value with $\\tilde{O}(\\log(1/\\epsilon))$ samples. In practice, the critic is learned alongside the actor: the variance of the actor update is then influenced by the critic's variance and bias","authors_text":"Daniil Tiapkin, Eric Moulines, Paul Mangold, Safwan Labbi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T02:41:07Z","title":"Refined Analysis of Entropy-Regularized Actor-Critic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24357","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:c6470005dd1d1f4d9bf0aa77d2aa1fd775710ebd877e910b7260868b7527f3f9","target":"record","created_at":"2026-05-26T01:03:01Z","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":"31d67085d3cec2e5bf0553559dd5f7d9ab886474b31a4fcb91c88bcfd0b737ab","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T02:41:07Z","title_canon_sha256":"5fffcfa5e1a3c34d06a123424309c9578e7ccebc9441ec8827862cb7555c132a"},"schema_version":"1.0","source":{"id":"2605.24357","kind":"arxiv","version":1}},"canonical_sha256":"cd6f063c37a28061c4686e1f2ccc680e736c8cb86fc1fa45af0a6aceffd6cf98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd6f063c37a28061c4686e1f2ccc680e736c8cb86fc1fa45af0a6aceffd6cf98","first_computed_at":"2026-05-26T01:03:01.668505Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:01.668505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jP4jA4hOLDhybAdemVqaHQ2SLVs44+JcoFWd7aqf8J3AbhuxFsg6jOdONeNjSWOhq1T9/5B1P2qIn+mh194DCg==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:01.669101Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24357","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6470005dd1d1f4d9bf0aa77d2aa1fd775710ebd877e910b7260868b7527f3f9","sha256:e238b9f5e827f3a2ec68ff01cdda8c161dc135442f8c8a29fb1836c824469307"],"state_sha256":"21a9b966055c76e60c4083c9d17741936a56dbca47adc6908f2c8842cd7b2130"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G5A7nzJ+N4QQm51AQKPpRvk/KB5Murg8936vQFe0o0aMLrp/cbsx3byXB6Y5ZinFyahsmdZsP7SR8RfykkjzBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T19:15:44.220168Z","bundle_sha256":"0bf20d89d5c5faee8712d6075eb73dd03ac74233b6847789544bd00dfbde3f05"}}