{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Q5NALOSHAL4JUZ7IABFWY4NKJD","short_pith_number":"pith:Q5NALOSH","canonical_record":{"source":{"id":"2403.01805","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-03-04T07:53:15Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"929116881adfe2f8e2a647d3c4892b90803475de3c1a29849b9820f494fd70ee","abstract_canon_sha256":"ebd163f0d95cdb4c573c47e71564ddb50e6a13cfe903d576533b029081582e75"},"schema_version":"1.0"},"canonical_sha256":"875a05ba4702f89a67e8004b6c71aa48eb10c7d4f143b282dc3476bf84127097","source":{"kind":"arxiv","id":"2403.01805","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.01805","created_at":"2026-07-05T07:51:52Z"},{"alias_kind":"arxiv_version","alias_value":"2403.01805v1","created_at":"2026-07-05T07:51:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01805","created_at":"2026-07-05T07:51:52Z"},{"alias_kind":"pith_short_12","alias_value":"Q5NALOSHAL4J","created_at":"2026-07-05T07:51:52Z"},{"alias_kind":"pith_short_16","alias_value":"Q5NALOSHAL4JUZ7I","created_at":"2026-07-05T07:51:52Z"},{"alias_kind":"pith_short_8","alias_value":"Q5NALOSH","created_at":"2026-07-05T07:51:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Q5NALOSHAL4JUZ7IABFWY4NKJD","target":"record","payload":{"canonical_record":{"source":{"id":"2403.01805","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-03-04T07:53:15Z","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"929116881adfe2f8e2a647d3c4892b90803475de3c1a29849b9820f494fd70ee","abstract_canon_sha256":"ebd163f0d95cdb4c573c47e71564ddb50e6a13cfe903d576533b029081582e75"},"schema_version":"1.0"},"canonical_sha256":"875a05ba4702f89a67e8004b6c71aa48eb10c7d4f143b282dc3476bf84127097","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:52.109920Z","signature_b64":"txudM/HpWirm21rczHi3PP9TfiASYwDk34OSTXaT9FKKFVT8cN415TrCJDFsrC2yIn5MEKd1eByMRT9r6bDkBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"875a05ba4702f89a67e8004b6c71aa48eb10c7d4f143b282dc3476bf84127097","last_reissued_at":"2026-07-05T07:51:52.109491Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:52.109491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.01805","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":"2026-07-05T07:51:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s1v0mAoXEpXbv/0dECYH8fB4lXnkbz65/8cdIQW4f1lkY/zBZ7adz4FsdAsEqgs0pKNh9NIDDQsRprI3bFEqDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T06:56:33.165097Z"},"content_sha256":"6055110c2f1590aaa525c4669df8d1519eb6379a13631e50e784445e4820c1ee","schema_version":"1.0","event_id":"sha256:6055110c2f1590aaa525c4669df8d1519eb6379a13631e50e784445e4820c1ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Q5NALOSHAL4JUZ7IABFWY4NKJD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tsallis Entropy Regularization for Linearly Solvable MDP and Linear Quadratic Regulator","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SY","eess.SY"],"primary_cat":"math.OC","authors_text":"Kenji Kashima, Koshi Oishi, Yota Hashizume","submitted_at":"2024-03-04T07:53:15Z","abstract_excerpt":"Shannon entropy regularization is widely adopted in optimal control due to its ability to promote exploration and enhance robustness, e.g., maximum entropy reinforcement learning known as Soft Actor-Critic. In this paper, Tsallis entropy, which is a one-parameter extension of Shannon entropy, is used for the regularization of linearly solvable MDP and linear quadratic regulators. We derive the solution for these problems and demonstrate its usefulness in balancing between exploration and sparsity of the obtained control law."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01805","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/2403.01805/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":"2026-07-05T07:51:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GrByA342nEIpn3oxJ25vftlqcKJSKLlcfiD6e14dWLk4+9ksPlRcBkqzZwOWDwSVEFIjSeyCIw695JNN0ik5AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T06:56:33.166045Z"},"content_sha256":"a635590a7376873c61a5e94f12ead70a31309109928f99229279829f248b0b5f","schema_version":"1.0","event_id":"sha256:a635590a7376873c61a5e94f12ead70a31309109928f99229279829f248b0b5f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q5NALOSHAL4JUZ7IABFWY4NKJD/bundle.json","state_url":"https://pith.science/pith/Q5NALOSHAL4JUZ7IABFWY4NKJD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q5NALOSHAL4JUZ7IABFWY4NKJD/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":"2026-08-17T06:56:33Z","links":{"resolver":"https://pith.science/pith/Q5NALOSHAL4JUZ7IABFWY4NKJD","bundle":"https://pith.science/pith/Q5NALOSHAL4JUZ7IABFWY4NKJD/bundle.json","state":"https://pith.science/pith/Q5NALOSHAL4JUZ7IABFWY4NKJD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q5NALOSHAL4JUZ7IABFWY4NKJD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q5NALOSHAL4JUZ7IABFWY4NKJD","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":"ebd163f0d95cdb4c573c47e71564ddb50e6a13cfe903d576533b029081582e75","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-03-04T07:53:15Z","title_canon_sha256":"929116881adfe2f8e2a647d3c4892b90803475de3c1a29849b9820f494fd70ee"},"schema_version":"1.0","source":{"id":"2403.01805","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.01805","created_at":"2026-07-05T07:51:52Z"},{"alias_kind":"arxiv_version","alias_value":"2403.01805v1","created_at":"2026-07-05T07:51:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01805","created_at":"2026-07-05T07:51:52Z"},{"alias_kind":"pith_short_12","alias_value":"Q5NALOSHAL4J","created_at":"2026-07-05T07:51:52Z"},{"alias_kind":"pith_short_16","alias_value":"Q5NALOSHAL4JUZ7I","created_at":"2026-07-05T07:51:52Z"},{"alias_kind":"pith_short_8","alias_value":"Q5NALOSH","created_at":"2026-07-05T07:51:52Z"}],"graph_snapshots":[{"event_id":"sha256:a635590a7376873c61a5e94f12ead70a31309109928f99229279829f248b0b5f","target":"graph","created_at":"2026-07-05T07:51:52Z","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/2403.01805/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Shannon entropy regularization is widely adopted in optimal control due to its ability to promote exploration and enhance robustness, e.g., maximum entropy reinforcement learning known as Soft Actor-Critic. In this paper, Tsallis entropy, which is a one-parameter extension of Shannon entropy, is used for the regularization of linearly solvable MDP and linear quadratic regulators. We derive the solution for these problems and demonstrate its usefulness in balancing between exploration and sparsity of the obtained control law.","authors_text":"Kenji Kashima, Koshi Oishi, Yota Hashizume","cross_cats":["cs.LG","cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-03-04T07:53:15Z","title":"Tsallis Entropy Regularization for Linearly Solvable MDP and Linear Quadratic Regulator"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01805","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":"sha256:6055110c2f1590aaa525c4669df8d1519eb6379a13631e50e784445e4820c1ee","target":"record","created_at":"2026-07-05T07:51:52Z","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":"ebd163f0d95cdb4c573c47e71564ddb50e6a13cfe903d576533b029081582e75","cross_cats_sorted":["cs.LG","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-03-04T07:53:15Z","title_canon_sha256":"929116881adfe2f8e2a647d3c4892b90803475de3c1a29849b9820f494fd70ee"},"schema_version":"1.0","source":{"id":"2403.01805","kind":"arxiv","version":1}},"canonical_sha256":"875a05ba4702f89a67e8004b6c71aa48eb10c7d4f143b282dc3476bf84127097","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"875a05ba4702f89a67e8004b6c71aa48eb10c7d4f143b282dc3476bf84127097","first_computed_at":"2026-07-05T07:51:52.109491Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:51:52.109491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"txudM/HpWirm21rczHi3PP9TfiASYwDk34OSTXaT9FKKFVT8cN415TrCJDFsrC2yIn5MEKd1eByMRT9r6bDkBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:51:52.109920Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.01805","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6055110c2f1590aaa525c4669df8d1519eb6379a13631e50e784445e4820c1ee","sha256:a635590a7376873c61a5e94f12ead70a31309109928f99229279829f248b0b5f"],"state_sha256":"c38c31db5b985f476131c9e4a88a5e965b458121a9cd344f362c9827b624d0a4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fT3cejDok+pqmIe3d+iwFSTseol6smseqPWMGdJchyP9jbuJtdWao9HVrOyD6NEq9dbrsqn9lHPzY23cHZCpBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T06:56:33.172160Z","bundle_sha256":"bd4886500d5710798aba47ddc2405b60f2714ab768bc9458c4b23c9a70a1c7b9"}}