{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:5LNO774Y3RO4I6L6MVXSPYERIS","short_pith_number":"pith:5LNO774Y","canonical_record":{"source":{"id":"1712.00222","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-12-01T07:54:53Z","cross_cats_sorted":[],"title_canon_sha256":"5885033a089370da3dcbb9af80abcb06fdf10873e6272e4f367c04fe79ddfba9","abstract_canon_sha256":"7439bc554f36015f7f16f42d276cd3b3fc106998854836875fe50da9b154f458"},"schema_version":"1.0"},"canonical_sha256":"eadaefff98dc5dc4797e656f27e09144b596e27fbca6d76d7abcf4a9aae8d1aa","source":{"kind":"arxiv","id":"1712.00222","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.00222","created_at":"2026-05-18T00:29:06Z"},{"alias_kind":"arxiv_version","alias_value":"1712.00222v1","created_at":"2026-05-18T00:29:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.00222","created_at":"2026-05-18T00:29:06Z"},{"alias_kind":"pith_short_12","alias_value":"5LNO774Y3RO4","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"5LNO774Y3RO4I6L6","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"5LNO774Y","created_at":"2026-05-18T12:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:5LNO774Y3RO4I6L6MVXSPYERIS","target":"record","payload":{"canonical_record":{"source":{"id":"1712.00222","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-12-01T07:54:53Z","cross_cats_sorted":[],"title_canon_sha256":"5885033a089370da3dcbb9af80abcb06fdf10873e6272e4f367c04fe79ddfba9","abstract_canon_sha256":"7439bc554f36015f7f16f42d276cd3b3fc106998854836875fe50da9b154f458"},"schema_version":"1.0"},"canonical_sha256":"eadaefff98dc5dc4797e656f27e09144b596e27fbca6d76d7abcf4a9aae8d1aa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:06.911517Z","signature_b64":"FjPuxyySe8SyfN6slu7INDhM+xvHJyOa5PrjQh6Wcr54Zn1YEP42x3IzTSsxyMQsW1676lW+37j8ZStCpEN1Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eadaefff98dc5dc4797e656f27e09144b596e27fbca6d76d7abcf4a9aae8d1aa","last_reissued_at":"2026-05-18T00:29:06.911019Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:06.911019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.00222","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":"2026-05-18T00:29:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r0jEJHoGMAYG/BDQKO4xSNM7NlMPYSYGGmvAYR/lIH42DHDnwJscCVhfIAruGHHCMexZK7knVMXrt4gmpQu6DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T22:54:23.601674Z"},"content_sha256":"fcf1d9779711c7d72acd80df841063589d4efa45ddc73386ff85162b9218bd71","schema_version":"1.0","event_id":"sha256:fcf1d9779711c7d72acd80df841063589d4efa45ddc73386ff85162b9218bd71"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:5LNO774Y3RO4I6L6MVXSPYERIS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A double competitive strategy based learning automata algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chong Di","submitted_at":"2017-12-01T07:54:53Z","abstract_excerpt":"Learning Automata (LA) are considered as one of the most powerful tools in the field of reinforcement learning. The family of estimator algorithms is proposed to improve the convergence rate of LA and has made great achievements. However, the estimators perform poorly on estimating the reward probabilities of actions in the initial stage of the learning process of LA. In this situation, a lot of rewards would be added to the probabilities of non-optimal actions. Thus, a large number of extra iterations are needed to compensate for these wrong rewards. In order to improve the speed of convergen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.00222","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":""},"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":"2026-05-18T00:29:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5HcWmUi2uUFrPRUT5YTWO0Bs/YM3Sit0FUtP+3Jq4UIoW5Is5iEYhKjImD7i0Pmj0hwZtjDAuEfwAiv8/Y1JCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T22:54:23.602028Z"},"content_sha256":"64b14a369ca23a262cc9131b5f834a24de0e8df85418ad442eec1a32e04965ed","schema_version":"1.0","event_id":"sha256:64b14a369ca23a262cc9131b5f834a24de0e8df85418ad442eec1a32e04965ed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5LNO774Y3RO4I6L6MVXSPYERIS/bundle.json","state_url":"https://pith.science/pith/5LNO774Y3RO4I6L6MVXSPYERIS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5LNO774Y3RO4I6L6MVXSPYERIS/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":"2026-06-03T22:54:23Z","links":{"resolver":"https://pith.science/pith/5LNO774Y3RO4I6L6MVXSPYERIS","bundle":"https://pith.science/pith/5LNO774Y3RO4I6L6MVXSPYERIS/bundle.json","state":"https://pith.science/pith/5LNO774Y3RO4I6L6MVXSPYERIS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5LNO774Y3RO4I6L6MVXSPYERIS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:5LNO774Y3RO4I6L6MVXSPYERIS","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":"7439bc554f36015f7f16f42d276cd3b3fc106998854836875fe50da9b154f458","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-12-01T07:54:53Z","title_canon_sha256":"5885033a089370da3dcbb9af80abcb06fdf10873e6272e4f367c04fe79ddfba9"},"schema_version":"1.0","source":{"id":"1712.00222","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.00222","created_at":"2026-05-18T00:29:06Z"},{"alias_kind":"arxiv_version","alias_value":"1712.00222v1","created_at":"2026-05-18T00:29:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.00222","created_at":"2026-05-18T00:29:06Z"},{"alias_kind":"pith_short_12","alias_value":"5LNO774Y3RO4","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"5LNO774Y3RO4I6L6","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"5LNO774Y","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:64b14a369ca23a262cc9131b5f834a24de0e8df85418ad442eec1a32e04965ed","target":"graph","created_at":"2026-05-18T00:29:06Z","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"},"paper":{"abstract_excerpt":"Learning Automata (LA) are considered as one of the most powerful tools in the field of reinforcement learning. The family of estimator algorithms is proposed to improve the convergence rate of LA and has made great achievements. However, the estimators perform poorly on estimating the reward probabilities of actions in the initial stage of the learning process of LA. In this situation, a lot of rewards would be added to the probabilities of non-optimal actions. Thus, a large number of extra iterations are needed to compensate for these wrong rewards. In order to improve the speed of convergen","authors_text":"Chong Di","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-12-01T07:54:53Z","title":"A double competitive strategy based learning automata algorithm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.00222","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:fcf1d9779711c7d72acd80df841063589d4efa45ddc73386ff85162b9218bd71","target":"record","created_at":"2026-05-18T00:29:06Z","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":"7439bc554f36015f7f16f42d276cd3b3fc106998854836875fe50da9b154f458","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-12-01T07:54:53Z","title_canon_sha256":"5885033a089370da3dcbb9af80abcb06fdf10873e6272e4f367c04fe79ddfba9"},"schema_version":"1.0","source":{"id":"1712.00222","kind":"arxiv","version":1}},"canonical_sha256":"eadaefff98dc5dc4797e656f27e09144b596e27fbca6d76d7abcf4a9aae8d1aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eadaefff98dc5dc4797e656f27e09144b596e27fbca6d76d7abcf4a9aae8d1aa","first_computed_at":"2026-05-18T00:29:06.911019Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:29:06.911019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FjPuxyySe8SyfN6slu7INDhM+xvHJyOa5PrjQh6Wcr54Zn1YEP42x3IzTSsxyMQsW1676lW+37j8ZStCpEN1Bg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:29:06.911517Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.00222","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fcf1d9779711c7d72acd80df841063589d4efa45ddc73386ff85162b9218bd71","sha256:64b14a369ca23a262cc9131b5f834a24de0e8df85418ad442eec1a32e04965ed"],"state_sha256":"fc4e260084c39a98de2da2ac390e53c293c9b1c67b4b42e8a54933e2346cd800"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kuvWQN0NgKMd38hUAyqR53AxCe4Zofr1JeoveApjtNx4zyGTrH/3OsZEXrviQhwHlgL1u3dYpSbDu9i37P3DCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T22:54:23.604104Z","bundle_sha256":"435b748ff92e3688d07e9fc41f7d2b185cd78392ee1fb31389c58580e1831845"}}