{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:DV2HO3SV45RG5JRM3UDHABBRNK","short_pith_number":"pith:DV2HO3SV","canonical_record":{"source":{"id":"1903.05926","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-14T11:54:13Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"372fd73c6924e4f42461e6a14006749e53b8911ca54085f5893e4fa874ba6b54","abstract_canon_sha256":"43d1ec092bf038d46f7d9e14061c11ef9080ee9ca9867be9b417fadca5dcce46"},"schema_version":"1.0"},"canonical_sha256":"1d74776e55e7626ea62cdd067004316a9d14ffc255932ac5e8ac015f8cb3cee5","source":{"kind":"arxiv","id":"1903.05926","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.05926","created_at":"2026-07-05T00:02:57Z"},{"alias_kind":"arxiv_version","alias_value":"1903.05926v4","created_at":"2026-07-05T00:02:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.05926","created_at":"2026-07-05T00:02:57Z"},{"alias_kind":"pith_short_12","alias_value":"DV2HO3SV45RG","created_at":"2026-07-05T00:02:57Z"},{"alias_kind":"pith_short_16","alias_value":"DV2HO3SV45RG5JRM","created_at":"2026-07-05T00:02:57Z"},{"alias_kind":"pith_short_8","alias_value":"DV2HO3SV","created_at":"2026-07-05T00:02:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:DV2HO3SV45RG5JRM3UDHABBRNK","target":"record","payload":{"canonical_record":{"source":{"id":"1903.05926","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-14T11:54:13Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"372fd73c6924e4f42461e6a14006749e53b8911ca54085f5893e4fa874ba6b54","abstract_canon_sha256":"43d1ec092bf038d46f7d9e14061c11ef9080ee9ca9867be9b417fadca5dcce46"},"schema_version":"1.0"},"canonical_sha256":"1d74776e55e7626ea62cdd067004316a9d14ffc255932ac5e8ac015f8cb3cee5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:02:57.480072Z","signature_b64":"6jjKXHkMT4CFuRhHWHgoTJhzkBIupdRxabqdYbP9o9JYWFPtCVWVkVrCTLqy7+kEXeQP3fA72a+Ek247wcVIAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d74776e55e7626ea62cdd067004316a9d14ffc255932ac5e8ac015f8cb3cee5","last_reissued_at":"2026-07-05T00:02:57.479470Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:02:57.479470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.05926","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:02:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tnDz3TlDXXLY+CshnhdTqji8VaMyGT5V0m4NV/qostm0Zsf3klMQwDweHkmv2vEeeL/ZP1yB6GEQjAKzBUD4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:37:32.517057Z"},"content_sha256":"9958b24e8c530d38809c76b1d50ab5e0a26f6b92f5a69f9714deb20180acc924","schema_version":"1.0","event_id":"sha256:9958b24e8c530d38809c76b1d50ab5e0a26f6b92f5a69f9714deb20180acc924"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:DV2HO3SV45RG5JRM3UDHABBRNK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning with Dynamic Boltzmann Softmax Updates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ling Pan, Longbo Huang, Qi Meng, Qingpeng Cai, Tie-Yan Liu, Wei Chen","submitted_at":"2019-03-14T11:54:13Z","abstract_excerpt":"Value function estimation is an important task in reinforcement learning, i.e., prediction. The Boltzmann softmax operator is a natural value estimator and can provide several benefits. However, it does not satisfy the non-expansion property, and its direct use may fail to converge even in value iteration. In this paper, we propose to update the value function with dynamic Boltzmann softmax (DBS) operator, which has good convergence property in the setting of planning and learning. Experimental results on GridWorld show that the DBS operator enables better estimation of the value function, whi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.05926","kind":"arxiv","version":4},"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/1903.05926/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":"2026-07-05T00:02:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4ZeyeW6Zsab6EDw+Vqm9LnMs0cm2MQkcxbhXjaF/5ajL/VcpI8oCY+27/Cjl+MbJSaAhNRqS3Tlqt4PrFrCFDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:37:32.517559Z"},"content_sha256":"4e793e56bb1132fd3363adeee685a58cbc7b38beb56dd78a79bb36b203c3bcf1","schema_version":"1.0","event_id":"sha256:4e793e56bb1132fd3363adeee685a58cbc7b38beb56dd78a79bb36b203c3bcf1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DV2HO3SV45RG5JRM3UDHABBRNK/bundle.json","state_url":"https://pith.science/pith/DV2HO3SV45RG5JRM3UDHABBRNK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DV2HO3SV45RG5JRM3UDHABBRNK/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":"2026-08-07T22:37:32Z","links":{"resolver":"https://pith.science/pith/DV2HO3SV45RG5JRM3UDHABBRNK","bundle":"https://pith.science/pith/DV2HO3SV45RG5JRM3UDHABBRNK/bundle.json","state":"https://pith.science/pith/DV2HO3SV45RG5JRM3UDHABBRNK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DV2HO3SV45RG5JRM3UDHABBRNK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:DV2HO3SV45RG5JRM3UDHABBRNK","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":"43d1ec092bf038d46f7d9e14061c11ef9080ee9ca9867be9b417fadca5dcce46","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-14T11:54:13Z","title_canon_sha256":"372fd73c6924e4f42461e6a14006749e53b8911ca54085f5893e4fa874ba6b54"},"schema_version":"1.0","source":{"id":"1903.05926","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.05926","created_at":"2026-07-05T00:02:57Z"},{"alias_kind":"arxiv_version","alias_value":"1903.05926v4","created_at":"2026-07-05T00:02:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.05926","created_at":"2026-07-05T00:02:57Z"},{"alias_kind":"pith_short_12","alias_value":"DV2HO3SV45RG","created_at":"2026-07-05T00:02:57Z"},{"alias_kind":"pith_short_16","alias_value":"DV2HO3SV45RG5JRM","created_at":"2026-07-05T00:02:57Z"},{"alias_kind":"pith_short_8","alias_value":"DV2HO3SV","created_at":"2026-07-05T00:02:57Z"}],"graph_snapshots":[{"event_id":"sha256:4e793e56bb1132fd3363adeee685a58cbc7b38beb56dd78a79bb36b203c3bcf1","target":"graph","created_at":"2026-07-05T00:02:57Z","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/1903.05926/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Value function estimation is an important task in reinforcement learning, i.e., prediction. The Boltzmann softmax operator is a natural value estimator and can provide several benefits. However, it does not satisfy the non-expansion property, and its direct use may fail to converge even in value iteration. In this paper, we propose to update the value function with dynamic Boltzmann softmax (DBS) operator, which has good convergence property in the setting of planning and learning. Experimental results on GridWorld show that the DBS operator enables better estimation of the value function, whi","authors_text":"Ling Pan, Longbo Huang, Qi Meng, Qingpeng Cai, Tie-Yan Liu, Wei Chen","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-14T11:54:13Z","title":"Reinforcement Learning with Dynamic Boltzmann Softmax Updates"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.05926","kind":"arxiv","version":4},"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":"sha256:9958b24e8c530d38809c76b1d50ab5e0a26f6b92f5a69f9714deb20180acc924","target":"record","created_at":"2026-07-05T00:02:57Z","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":"43d1ec092bf038d46f7d9e14061c11ef9080ee9ca9867be9b417fadca5dcce46","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-14T11:54:13Z","title_canon_sha256":"372fd73c6924e4f42461e6a14006749e53b8911ca54085f5893e4fa874ba6b54"},"schema_version":"1.0","source":{"id":"1903.05926","kind":"arxiv","version":4}},"canonical_sha256":"1d74776e55e7626ea62cdd067004316a9d14ffc255932ac5e8ac015f8cb3cee5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d74776e55e7626ea62cdd067004316a9d14ffc255932ac5e8ac015f8cb3cee5","first_computed_at":"2026-07-05T00:02:57.479470Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:02:57.479470Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6jjKXHkMT4CFuRhHWHgoTJhzkBIupdRxabqdYbP9o9JYWFPtCVWVkVrCTLqy7+kEXeQP3fA72a+Ek247wcVIAg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:02:57.480072Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.05926","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9958b24e8c530d38809c76b1d50ab5e0a26f6b92f5a69f9714deb20180acc924","sha256:4e793e56bb1132fd3363adeee685a58cbc7b38beb56dd78a79bb36b203c3bcf1"],"state_sha256":"fd5998f50214a2de8597e91666b98439935a56c3325e39926bc4636bc0c1dea5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pBd4TcRX8qEjWuEmm3NXOPmXeqHeNj0gwz7PSFpjjSqo1BMpxyhsuAf27XtnL3ZFez1mYR5+jp6oXn/4D3qBAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T22:37:32.521841Z","bundle_sha256":"bf43328566a3c7077163766ee40450d670d823244ef8290e833e3a65a7d532da"}}