{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QCXBEDITASNQZYAYHTG6VE7KSF","short_pith_number":"pith:QCXBEDIT","canonical_record":{"source":{"id":"2501.17827","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-29T18:18:00Z","cross_cats_sorted":[],"title_canon_sha256":"00bbafdffd8d4c9fcb54f9c879020144f9d2dd5b716ee9ba6d723ac665ce1afd","abstract_canon_sha256":"cfa34d4134f30f36d13f2a5282584c70215c3c725f29adff5e060d958c574b41"},"schema_version":"1.0"},"canonical_sha256":"80ae120d13049b0ce0183ccdea93ea915e93eaa098e075969d2ff6e109d3ea87","source":{"kind":"arxiv","id":"2501.17827","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.17827","created_at":"2026-07-05T10:06:58Z"},{"alias_kind":"arxiv_version","alias_value":"2501.17827v1","created_at":"2026-07-05T10:06:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.17827","created_at":"2026-07-05T10:06:58Z"},{"alias_kind":"pith_short_12","alias_value":"QCXBEDITASNQ","created_at":"2026-07-05T10:06:58Z"},{"alias_kind":"pith_short_16","alias_value":"QCXBEDITASNQZYAY","created_at":"2026-07-05T10:06:58Z"},{"alias_kind":"pith_short_8","alias_value":"QCXBEDIT","created_at":"2026-07-05T10:06:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QCXBEDITASNQZYAYHTG6VE7KSF","target":"record","payload":{"canonical_record":{"source":{"id":"2501.17827","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-29T18:18:00Z","cross_cats_sorted":[],"title_canon_sha256":"00bbafdffd8d4c9fcb54f9c879020144f9d2dd5b716ee9ba6d723ac665ce1afd","abstract_canon_sha256":"cfa34d4134f30f36d13f2a5282584c70215c3c725f29adff5e060d958c574b41"},"schema_version":"1.0"},"canonical_sha256":"80ae120d13049b0ce0183ccdea93ea915e93eaa098e075969d2ff6e109d3ea87","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:58.700117Z","signature_b64":"xRm9niYlf70O5yD4CoRrwuNLrqAJYmj0kp7HdYYZV+LZVFMGRW0IhGT8UA8J7WeFMlVo058PgamgwAhZ8NXBAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80ae120d13049b0ce0183ccdea93ea915e93eaa098e075969d2ff6e109d3ea87","last_reissued_at":"2026-07-05T10:06:58.699704Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:58.699704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.17827","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":"2026-07-05T10:06:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i3T81n8TLTk6DRuljqAFTdLCWYZD0/hRpQALL7BA5kwRL6P3y3S89T4KCOYzJiG2SyTksNIslO0a7FuQDcZ+Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:35:26.732530Z"},"content_sha256":"0fc7c1fe945d69e3a6a962a6d1fb7819337783d0b5bbd13f4fe9ade9b4f17d82","schema_version":"1.0","event_id":"sha256:0fc7c1fe945d69e3a6a962a6d1fb7819337783d0b5bbd13f4fe9ade9b4f17d82"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QCXBEDITASNQZYAYHTG6VE7KSF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Doina Precup, Guangyuan Wang, Haque Ishfaq, Sami Nur Islam","submitted_at":"2025-01-29T18:18:00Z","abstract_excerpt":"Existing actor-critic algorithms, which are popular for continuous control reinforcement learning (RL) tasks, suffer from poor sample efficiency due to lack of principled exploration mechanism within them. Motivated by the success of Thompson sampling for efficient exploration in RL, we propose a novel model-free RL algorithm, Langevin Soft Actor Critic (LSAC), which prioritizes enhancing critic learning through uncertainty estimation over policy optimization. LSAC employs three key innovations: approximate Thompson sampling through distributional Langevin Monte Carlo (LMC) based $Q$ updates, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.17827","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/2501.17827/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":"2026-07-05T10:06:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W6/xTb0tR5oEOjfi/oYR14xrYnsete3zm2rLAAA2YhDTHhnGA9zN9VG4Fqqe7eUWQ2+iCYH70nUdF8AoZ3IYCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T03:35:26.732907Z"},"content_sha256":"81a6d401c63c60096f4826118d1cc759d9aa024bf2687083a828eb7e1a35f47d","schema_version":"1.0","event_id":"sha256:81a6d401c63c60096f4826118d1cc759d9aa024bf2687083a828eb7e1a35f47d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QCXBEDITASNQZYAYHTG6VE7KSF/bundle.json","state_url":"https://pith.science/pith/QCXBEDITASNQZYAYHTG6VE7KSF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QCXBEDITASNQZYAYHTG6VE7KSF/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":"2026-07-09T03:35:26Z","links":{"resolver":"https://pith.science/pith/QCXBEDITASNQZYAYHTG6VE7KSF","bundle":"https://pith.science/pith/QCXBEDITASNQZYAYHTG6VE7KSF/bundle.json","state":"https://pith.science/pith/QCXBEDITASNQZYAYHTG6VE7KSF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QCXBEDITASNQZYAYHTG6VE7KSF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QCXBEDITASNQZYAYHTG6VE7KSF","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":"cfa34d4134f30f36d13f2a5282584c70215c3c725f29adff5e060d958c574b41","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-29T18:18:00Z","title_canon_sha256":"00bbafdffd8d4c9fcb54f9c879020144f9d2dd5b716ee9ba6d723ac665ce1afd"},"schema_version":"1.0","source":{"id":"2501.17827","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.17827","created_at":"2026-07-05T10:06:58Z"},{"alias_kind":"arxiv_version","alias_value":"2501.17827v1","created_at":"2026-07-05T10:06:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.17827","created_at":"2026-07-05T10:06:58Z"},{"alias_kind":"pith_short_12","alias_value":"QCXBEDITASNQ","created_at":"2026-07-05T10:06:58Z"},{"alias_kind":"pith_short_16","alias_value":"QCXBEDITASNQZYAY","created_at":"2026-07-05T10:06:58Z"},{"alias_kind":"pith_short_8","alias_value":"QCXBEDIT","created_at":"2026-07-05T10:06:58Z"}],"graph_snapshots":[{"event_id":"sha256:81a6d401c63c60096f4826118d1cc759d9aa024bf2687083a828eb7e1a35f47d","target":"graph","created_at":"2026-07-05T10:06:58Z","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/2501.17827/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing actor-critic algorithms, which are popular for continuous control reinforcement learning (RL) tasks, suffer from poor sample efficiency due to lack of principled exploration mechanism within them. Motivated by the success of Thompson sampling for efficient exploration in RL, we propose a novel model-free RL algorithm, Langevin Soft Actor Critic (LSAC), which prioritizes enhancing critic learning through uncertainty estimation over policy optimization. LSAC employs three key innovations: approximate Thompson sampling through distributional Langevin Monte Carlo (LMC) based $Q$ updates, ","authors_text":"Doina Precup, Guangyuan Wang, Haque Ishfaq, Sami Nur Islam","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-29T18:18:00Z","title":"Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.17827","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":"sha256:0fc7c1fe945d69e3a6a962a6d1fb7819337783d0b5bbd13f4fe9ade9b4f17d82","target":"record","created_at":"2026-07-05T10:06:58Z","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":"cfa34d4134f30f36d13f2a5282584c70215c3c725f29adff5e060d958c574b41","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-29T18:18:00Z","title_canon_sha256":"00bbafdffd8d4c9fcb54f9c879020144f9d2dd5b716ee9ba6d723ac665ce1afd"},"schema_version":"1.0","source":{"id":"2501.17827","kind":"arxiv","version":1}},"canonical_sha256":"80ae120d13049b0ce0183ccdea93ea915e93eaa098e075969d2ff6e109d3ea87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80ae120d13049b0ce0183ccdea93ea915e93eaa098e075969d2ff6e109d3ea87","first_computed_at":"2026-07-05T10:06:58.699704Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:06:58.699704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xRm9niYlf70O5yD4CoRrwuNLrqAJYmj0kp7HdYYZV+LZVFMGRW0IhGT8UA8J7WeFMlVo058PgamgwAhZ8NXBAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:06:58.700117Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.17827","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0fc7c1fe945d69e3a6a962a6d1fb7819337783d0b5bbd13f4fe9ade9b4f17d82","sha256:81a6d401c63c60096f4826118d1cc759d9aa024bf2687083a828eb7e1a35f47d"],"state_sha256":"6e2b0cf66acbc30df5f05ae44eeb7364d827acf015bb37395b40dd4a70e04b71"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hU2Ab1ejwszRgL0MavX5I5g9Imeqmcjk1nXi8DXcT6p474xZ92PXzUMEEsZFueh8AIPNFknlGF8/3sAsg7mXDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T03:35:26.735308Z","bundle_sha256":"393356fa02c9c3237f6ed1320f851f1badb3927bcddf66a6817832dc65e62208"}}