{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XU67BFNR7IPJPS3QJRXRLQBM6V","short_pith_number":"pith:XU67BFNR","canonical_record":{"source":{"id":"2310.17538","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-26T16:28:29Z","cross_cats_sorted":[],"title_canon_sha256":"e18c014db637a319a3ad76dc71ee95654c423dbca68b05e9cbfad8623d25ec52","abstract_canon_sha256":"798f617f813110c8b6f86bab72fa9eac6910c8dbb6978f9afd5c725c669de22b"},"schema_version":"1.0"},"canonical_sha256":"bd3df095b1fa1e97cb704c6f15c02cf57caac9ed8d2236dc1103b400a5652541","source":{"kind":"arxiv","id":"2310.17538","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.17538","created_at":"2026-07-05T07:05:35Z"},{"alias_kind":"arxiv_version","alias_value":"2310.17538v1","created_at":"2026-07-05T07:05:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17538","created_at":"2026-07-05T07:05:35Z"},{"alias_kind":"pith_short_12","alias_value":"XU67BFNR7IPJ","created_at":"2026-07-05T07:05:35Z"},{"alias_kind":"pith_short_16","alias_value":"XU67BFNR7IPJPS3Q","created_at":"2026-07-05T07:05:35Z"},{"alias_kind":"pith_short_8","alias_value":"XU67BFNR","created_at":"2026-07-05T07:05:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XU67BFNR7IPJPS3QJRXRLQBM6V","target":"record","payload":{"canonical_record":{"source":{"id":"2310.17538","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-26T16:28:29Z","cross_cats_sorted":[],"title_canon_sha256":"e18c014db637a319a3ad76dc71ee95654c423dbca68b05e9cbfad8623d25ec52","abstract_canon_sha256":"798f617f813110c8b6f86bab72fa9eac6910c8dbb6978f9afd5c725c669de22b"},"schema_version":"1.0"},"canonical_sha256":"bd3df095b1fa1e97cb704c6f15c02cf57caac9ed8d2236dc1103b400a5652541","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:35.819118Z","signature_b64":"4HegojmvSh2G8g9n5z0Fh4/MjO579e1x5Ukb9TB4apmGc2ybKBaU5TM+MIFUZOSO16oTDqnyUlZfKY7JTHtuBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd3df095b1fa1e97cb704c6f15c02cf57caac9ed8d2236dc1103b400a5652541","last_reissued_at":"2026-07-05T07:05:35.818689Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:35.818689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.17538","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":"2026-07-05T07:05:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k45pc22Xsj9CIh/L2AAsw6G6X+yNGNJRHv1MsD2SQ+S8ZIn0uZZaPCU7FywYtpyiSVY1rgHmWJ5lHgXwRaHQBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T09:04:20.454741Z"},"content_sha256":"8fcf39e851ac1f579dda9a5e795f1118a2fb3c236d121da0a2c261ed7045133e","schema_version":"1.0","event_id":"sha256:8fcf39e851ac1f579dda9a5e795f1118a2fb3c236d121da0a2c261ed7045133e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XU67BFNR7IPJPS3QJRXRLQBM6V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Little Exploration is All You Need","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Henry H.H. Chen, Jiaming Lu","submitted_at":"2023-10-26T16:28:29Z","abstract_excerpt":"The prevailing principle of \"Optimism in the Face of Uncertainty\" advocates for the incorporation of an exploration bonus, generally assumed to be proportional to the inverse square root of the visit count ($1/\\sqrt{n}$), where $n$ is the number of visits to a particular state-action pair. This approach, however, exclusively focuses on \"uncertainty,\" neglecting the inherent \"difficulty\" of different options. To address this gap, we introduce a novel modification of standard UCB algorithm in the multi-armed bandit problem, proposing an adjusted bonus term of $1/n^\\tau$, where $\\tau > 1/2$, that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17538","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/2310.17538/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":"2026-07-05T07:05:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Au1Scc1xE0m85Pm7PtFPL529jg/gFdUcMwOkvzF+3bE/j0NRwn68IOWeZO74IMDUAzmYAbUGTOHROZDK55fZDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T09:04:20.455065Z"},"content_sha256":"d7581e94fc98e0c099be80894f90969282ce798db3c8af35c852f91debbaf8ce","schema_version":"1.0","event_id":"sha256:d7581e94fc98e0c099be80894f90969282ce798db3c8af35c852f91debbaf8ce"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XU67BFNR7IPJPS3QJRXRLQBM6V/bundle.json","state_url":"https://pith.science/pith/XU67BFNR7IPJPS3QJRXRLQBM6V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XU67BFNR7IPJPS3QJRXRLQBM6V/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":"2026-08-01T09:04:20Z","links":{"resolver":"https://pith.science/pith/XU67BFNR7IPJPS3QJRXRLQBM6V","bundle":"https://pith.science/pith/XU67BFNR7IPJPS3QJRXRLQBM6V/bundle.json","state":"https://pith.science/pith/XU67BFNR7IPJPS3QJRXRLQBM6V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XU67BFNR7IPJPS3QJRXRLQBM6V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XU67BFNR7IPJPS3QJRXRLQBM6V","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":"798f617f813110c8b6f86bab72fa9eac6910c8dbb6978f9afd5c725c669de22b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-26T16:28:29Z","title_canon_sha256":"e18c014db637a319a3ad76dc71ee95654c423dbca68b05e9cbfad8623d25ec52"},"schema_version":"1.0","source":{"id":"2310.17538","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.17538","created_at":"2026-07-05T07:05:35Z"},{"alias_kind":"arxiv_version","alias_value":"2310.17538v1","created_at":"2026-07-05T07:05:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17538","created_at":"2026-07-05T07:05:35Z"},{"alias_kind":"pith_short_12","alias_value":"XU67BFNR7IPJ","created_at":"2026-07-05T07:05:35Z"},{"alias_kind":"pith_short_16","alias_value":"XU67BFNR7IPJPS3Q","created_at":"2026-07-05T07:05:35Z"},{"alias_kind":"pith_short_8","alias_value":"XU67BFNR","created_at":"2026-07-05T07:05:35Z"}],"graph_snapshots":[{"event_id":"sha256:d7581e94fc98e0c099be80894f90969282ce798db3c8af35c852f91debbaf8ce","target":"graph","created_at":"2026-07-05T07:05:35Z","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/2310.17538/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The prevailing principle of \"Optimism in the Face of Uncertainty\" advocates for the incorporation of an exploration bonus, generally assumed to be proportional to the inverse square root of the visit count ($1/\\sqrt{n}$), where $n$ is the number of visits to a particular state-action pair. This approach, however, exclusively focuses on \"uncertainty,\" neglecting the inherent \"difficulty\" of different options. To address this gap, we introduce a novel modification of standard UCB algorithm in the multi-armed bandit problem, proposing an adjusted bonus term of $1/n^\\tau$, where $\\tau > 1/2$, that","authors_text":"Henry H.H. Chen, Jiaming Lu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-26T16:28:29Z","title":"Little Exploration is All You Need"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17538","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":"sha256:8fcf39e851ac1f579dda9a5e795f1118a2fb3c236d121da0a2c261ed7045133e","target":"record","created_at":"2026-07-05T07:05:35Z","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":"798f617f813110c8b6f86bab72fa9eac6910c8dbb6978f9afd5c725c669de22b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-26T16:28:29Z","title_canon_sha256":"e18c014db637a319a3ad76dc71ee95654c423dbca68b05e9cbfad8623d25ec52"},"schema_version":"1.0","source":{"id":"2310.17538","kind":"arxiv","version":1}},"canonical_sha256":"bd3df095b1fa1e97cb704c6f15c02cf57caac9ed8d2236dc1103b400a5652541","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd3df095b1fa1e97cb704c6f15c02cf57caac9ed8d2236dc1103b400a5652541","first_computed_at":"2026-07-05T07:05:35.818689Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:35.818689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4HegojmvSh2G8g9n5z0Fh4/MjO579e1x5Ukb9TB4apmGc2ybKBaU5TM+MIFUZOSO16oTDqnyUlZfKY7JTHtuBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:35.819118Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.17538","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8fcf39e851ac1f579dda9a5e795f1118a2fb3c236d121da0a2c261ed7045133e","sha256:d7581e94fc98e0c099be80894f90969282ce798db3c8af35c852f91debbaf8ce"],"state_sha256":"5cc849e9200e6058c3d41d21689fc37dbef2e187ae1d98b52e4dce87752c570c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y+5GnC5Qot+VB84n3VQxSrYALrCQftWwCJrKBhvPqr1UDqSNpHLQtkXIq0hczmbpVyUialIUlNK/11dsYl/0AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T09:04:20.458397Z","bundle_sha256":"b4bb716284dae28ac63be7e07a5bc44235315162f10fff74abf830d8cdf043fd"}}