{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:HKRJFKPTI3VCJ5Y3HLGNTHKWJT","short_pith_number":"pith:HKRJFKPT","canonical_record":{"source":{"id":"1705.10257","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-29T15:33:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8e64e0f2e31e60a2a218f40eee485c39c99e16d2335e64e3fc4f11d8318aae01","abstract_canon_sha256":"4423cc2fc7cac1361dd02afd566d13da28bc1f560b245e2b2ca3dc8dbd533037"},"schema_version":"1.0"},"canonical_sha256":"3aa292a9f346ea24f71b3accd99d564cc6993edf889ffae97c79654fe328ab2c","source":{"kind":"arxiv","id":"1705.10257","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.10257","created_at":"2026-05-18T00:31:12Z"},{"alias_kind":"arxiv_version","alias_value":"1705.10257v2","created_at":"2026-05-18T00:31:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.10257","created_at":"2026-05-18T00:31:12Z"},{"alias_kind":"pith_short_12","alias_value":"HKRJFKPTI3VC","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"HKRJFKPTI3VCJ5Y3","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"HKRJFKPT","created_at":"2026-05-18T12:31:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:HKRJFKPTI3VCJ5Y3HLGNTHKWJT","target":"record","payload":{"canonical_record":{"source":{"id":"1705.10257","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-29T15:33:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8e64e0f2e31e60a2a218f40eee485c39c99e16d2335e64e3fc4f11d8318aae01","abstract_canon_sha256":"4423cc2fc7cac1361dd02afd566d13da28bc1f560b245e2b2ca3dc8dbd533037"},"schema_version":"1.0"},"canonical_sha256":"3aa292a9f346ea24f71b3accd99d564cc6993edf889ffae97c79654fe328ab2c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:12.657976Z","signature_b64":"1TdVbftDrfLRjc7DERmQUxO36aYk/l+Fmy6tjSwUD4nr7tO3yZc1lO2pEefZF+Ah05wMP6IF5Av8L6MNRzCXDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3aa292a9f346ea24f71b3accd99d564cc6993edf889ffae97c79654fe328ab2c","last_reissued_at":"2026-05-18T00:31:12.657284Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:12.657284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.10257","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:31:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pc4RoCkKxz/ilga5C4Kj8rrLeY/k9EqDum9zxmTTsNtEpxbJnMwvtH+BPMsJzC5OOL3KGPO+a0OIzVsPjHjnAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T17:03:19.898494Z"},"content_sha256":"64bff21522fd0f1c610ddb331fd7f9d117ef9b7d940959d9f8370c9f4f70f5d5","schema_version":"1.0","event_id":"sha256:64bff21522fd0f1c610ddb331fd7f9d117ef9b7d940959d9f8370c9f4f70f5d5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:HKRJFKPTI3VCJ5Y3HLGNTHKWJT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Boltzmann Exploration Done Right","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Claudio Gentile, G\\'abor Lugosi, Gergely Neu, Nicol\\`o Cesa-Bianchi","submitted_at":"2017-05-29T15:33:29Z","abstract_excerpt":"Boltzmann exploration is a classic strategy for sequential decision-making under uncertainty, and is one of the most standard tools in Reinforcement Learning (RL). Despite its widespread use, there is virtually no theoretical understanding about the limitations or the actual benefits of this exploration scheme. Does it drive exploration in a meaningful way? Is it prone to misidentifying the optimal actions or spending too much time exploring the suboptimal ones? What is the right tuning for the learning rate? In this paper, we address several of these questions in the classic setup of stochast"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.10257","kind":"arxiv","version":2},"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":"2026-05-18T00:31:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3JNxS6TcvASbp7aksRJcbK9KXiFl58hwcx2uniTuNsX51cvYQKdTJEFMEhRjwu0g900TXuUYimjnj66wNOA0Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T17:03:19.899256Z"},"content_sha256":"0fd8cc0571e34f18e547c43ac176a0a9b113624945d713eb2c3ff0c3b4f69909","schema_version":"1.0","event_id":"sha256:0fd8cc0571e34f18e547c43ac176a0a9b113624945d713eb2c3ff0c3b4f69909"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HKRJFKPTI3VCJ5Y3HLGNTHKWJT/bundle.json","state_url":"https://pith.science/pith/HKRJFKPTI3VCJ5Y3HLGNTHKWJT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HKRJFKPTI3VCJ5Y3HLGNTHKWJT/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":"2026-05-31T17:03:19Z","links":{"resolver":"https://pith.science/pith/HKRJFKPTI3VCJ5Y3HLGNTHKWJT","bundle":"https://pith.science/pith/HKRJFKPTI3VCJ5Y3HLGNTHKWJT/bundle.json","state":"https://pith.science/pith/HKRJFKPTI3VCJ5Y3HLGNTHKWJT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HKRJFKPTI3VCJ5Y3HLGNTHKWJT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:HKRJFKPTI3VCJ5Y3HLGNTHKWJT","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":"4423cc2fc7cac1361dd02afd566d13da28bc1f560b245e2b2ca3dc8dbd533037","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-29T15:33:29Z","title_canon_sha256":"8e64e0f2e31e60a2a218f40eee485c39c99e16d2335e64e3fc4f11d8318aae01"},"schema_version":"1.0","source":{"id":"1705.10257","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.10257","created_at":"2026-05-18T00:31:12Z"},{"alias_kind":"arxiv_version","alias_value":"1705.10257v2","created_at":"2026-05-18T00:31:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.10257","created_at":"2026-05-18T00:31:12Z"},{"alias_kind":"pith_short_12","alias_value":"HKRJFKPTI3VC","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"HKRJFKPTI3VCJ5Y3","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"HKRJFKPT","created_at":"2026-05-18T12:31:18Z"}],"graph_snapshots":[{"event_id":"sha256:0fd8cc0571e34f18e547c43ac176a0a9b113624945d713eb2c3ff0c3b4f69909","target":"graph","created_at":"2026-05-18T00:31:12Z","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":"Boltzmann exploration is a classic strategy for sequential decision-making under uncertainty, and is one of the most standard tools in Reinforcement Learning (RL). Despite its widespread use, there is virtually no theoretical understanding about the limitations or the actual benefits of this exploration scheme. Does it drive exploration in a meaningful way? Is it prone to misidentifying the optimal actions or spending too much time exploring the suboptimal ones? What is the right tuning for the learning rate? In this paper, we address several of these questions in the classic setup of stochast","authors_text":"Claudio Gentile, G\\'abor Lugosi, Gergely Neu, Nicol\\`o Cesa-Bianchi","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-29T15:33:29Z","title":"Boltzmann Exploration Done Right"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.10257","kind":"arxiv","version":2},"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":"sha256:64bff21522fd0f1c610ddb331fd7f9d117ef9b7d940959d9f8370c9f4f70f5d5","target":"record","created_at":"2026-05-18T00:31:12Z","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":"4423cc2fc7cac1361dd02afd566d13da28bc1f560b245e2b2ca3dc8dbd533037","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-29T15:33:29Z","title_canon_sha256":"8e64e0f2e31e60a2a218f40eee485c39c99e16d2335e64e3fc4f11d8318aae01"},"schema_version":"1.0","source":{"id":"1705.10257","kind":"arxiv","version":2}},"canonical_sha256":"3aa292a9f346ea24f71b3accd99d564cc6993edf889ffae97c79654fe328ab2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3aa292a9f346ea24f71b3accd99d564cc6993edf889ffae97c79654fe328ab2c","first_computed_at":"2026-05-18T00:31:12.657284Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:31:12.657284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1TdVbftDrfLRjc7DERmQUxO36aYk/l+Fmy6tjSwUD4nr7tO3yZc1lO2pEefZF+Ah05wMP6IF5Av8L6MNRzCXDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:31:12.657976Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.10257","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64bff21522fd0f1c610ddb331fd7f9d117ef9b7d940959d9f8370c9f4f70f5d5","sha256:0fd8cc0571e34f18e547c43ac176a0a9b113624945d713eb2c3ff0c3b4f69909"],"state_sha256":"cce916a62a38d2be6a515543f9ad0a85edfe6ee3dce0abba9d96bd9ca8983809"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QAXu4WczWWZayJdlyN92t8amYtzs5rjQ2GjfxWyvlqFjY27O1QTZGPQYHb+WTIHbxyWhmnqHClMfsMWdjRtbAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T17:03:19.903012Z","bundle_sha256":"8fceb70ec5522006f4bbe891a04da43ac6449e8aa0509000a13f07489d7242f9"}}