{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:EPXFRMCO4IQ3RJDGZODXKHJVCW","short_pith_number":"pith:EPXFRMCO","canonical_record":{"source":{"id":"1612.00882","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-02T22:38:37Z","cross_cats_sorted":[],"title_canon_sha256":"9ad0d45fcc796767f1829496b08db1c6f10cba2373f611d6cb61875d10b0cb88","abstract_canon_sha256":"44ad7c81d5c670c6fe09f949b2b1a13d335937dc0fe34e1af62389b3cc276aba"},"schema_version":"1.0"},"canonical_sha256":"23ee58b04ee221b8a466cb87751d3515844c21c3dd0a798f11d3f08fdae30db6","source":{"kind":"arxiv","id":"1612.00882","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.00882","created_at":"2026-05-18T00:55:53Z"},{"alias_kind":"arxiv_version","alias_value":"1612.00882v1","created_at":"2026-05-18T00:55:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.00882","created_at":"2026-05-18T00:55:53Z"},{"alias_kind":"pith_short_12","alias_value":"EPXFRMCO4IQ3","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"EPXFRMCO4IQ3RJDG","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"EPXFRMCO","created_at":"2026-05-18T12:30:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:EPXFRMCO4IQ3RJDGZODXKHJVCW","target":"record","payload":{"canonical_record":{"source":{"id":"1612.00882","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-02T22:38:37Z","cross_cats_sorted":[],"title_canon_sha256":"9ad0d45fcc796767f1829496b08db1c6f10cba2373f611d6cb61875d10b0cb88","abstract_canon_sha256":"44ad7c81d5c670c6fe09f949b2b1a13d335937dc0fe34e1af62389b3cc276aba"},"schema_version":"1.0"},"canonical_sha256":"23ee58b04ee221b8a466cb87751d3515844c21c3dd0a798f11d3f08fdae30db6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:55:53.914482Z","signature_b64":"+aPVGf3ToIyEpge40RV+qpDeQzIyCF3IdaSz61gzq1/bBI5wTFdLVEH2qaWEr3QM60otrsjIbpemFCEjn1X2BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23ee58b04ee221b8a466cb87751d3515844c21c3dd0a798f11d3f08fdae30db6","last_reissued_at":"2026-05-18T00:55:53.913976Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:55:53.913976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1612.00882","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":"2026-05-18T00:55:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iTooA9BQfealywDxxxi5pL0alH5P5ELNNVqq0e+z9Zf3q3klwxZ+mspUFbA5ZaY2S2EaxYgU4lDUvVso4N58Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T15:50:05.349005Z"},"content_sha256":"3943f924e2b3bc2944f14c8228f82bb404141f4d26b48f6764de6466489bb3a1","schema_version":"1.0","event_id":"sha256:3943f924e2b3bc2944f14c8228f82bb404141f4d26b48f6764de6466489bb3a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:EPXFRMCO4IQ3RJDGZODXKHJVCW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Success Probability of Exploration: a Concrete Analysis of Learning Efficiency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ke Tang, Liangpeng Zhang, Xin Yao","submitted_at":"2016-12-02T22:38:37Z","abstract_excerpt":"Exploration has been a crucial part of reinforcement learning, yet several important questions concerning exploration efficiency are still not answered satisfactorily by existing analytical frameworks. These questions include exploration parameter setting, situation analysis, and hardness of MDPs, all of which are unavoidable for practitioners. To bridge the gap between the theory and practice, we propose a new analytical framework called the success probability of exploration. We show that those important questions of exploration above can all be answered under our framework, and the answers "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.00882","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":"2026-05-18T00:55:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YlykJUp1NY10Va7zBOWGQjOTvW4mkmZhYoEI1DZyFRNHtRc/68HEC3GLA8FAQRNEDSJjP/82bBzxPyEAM3VYDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T15:50:05.349681Z"},"content_sha256":"92d295e5ab2c78d6393a71f7398a660fdcc423c7a4a6e472b295676bf08946a9","schema_version":"1.0","event_id":"sha256:92d295e5ab2c78d6393a71f7398a660fdcc423c7a4a6e472b295676bf08946a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EPXFRMCO4IQ3RJDGZODXKHJVCW/bundle.json","state_url":"https://pith.science/pith/EPXFRMCO4IQ3RJDGZODXKHJVCW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EPXFRMCO4IQ3RJDGZODXKHJVCW/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":"2026-05-27T15:50:05Z","links":{"resolver":"https://pith.science/pith/EPXFRMCO4IQ3RJDGZODXKHJVCW","bundle":"https://pith.science/pith/EPXFRMCO4IQ3RJDGZODXKHJVCW/bundle.json","state":"https://pith.science/pith/EPXFRMCO4IQ3RJDGZODXKHJVCW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EPXFRMCO4IQ3RJDGZODXKHJVCW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:EPXFRMCO4IQ3RJDGZODXKHJVCW","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":"44ad7c81d5c670c6fe09f949b2b1a13d335937dc0fe34e1af62389b3cc276aba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-02T22:38:37Z","title_canon_sha256":"9ad0d45fcc796767f1829496b08db1c6f10cba2373f611d6cb61875d10b0cb88"},"schema_version":"1.0","source":{"id":"1612.00882","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.00882","created_at":"2026-05-18T00:55:53Z"},{"alias_kind":"arxiv_version","alias_value":"1612.00882v1","created_at":"2026-05-18T00:55:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.00882","created_at":"2026-05-18T00:55:53Z"},{"alias_kind":"pith_short_12","alias_value":"EPXFRMCO4IQ3","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"EPXFRMCO4IQ3RJDG","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"EPXFRMCO","created_at":"2026-05-18T12:30:12Z"}],"graph_snapshots":[{"event_id":"sha256:92d295e5ab2c78d6393a71f7398a660fdcc423c7a4a6e472b295676bf08946a9","target":"graph","created_at":"2026-05-18T00:55:53Z","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":"Exploration has been a crucial part of reinforcement learning, yet several important questions concerning exploration efficiency are still not answered satisfactorily by existing analytical frameworks. These questions include exploration parameter setting, situation analysis, and hardness of MDPs, all of which are unavoidable for practitioners. To bridge the gap between the theory and practice, we propose a new analytical framework called the success probability of exploration. We show that those important questions of exploration above can all be answered under our framework, and the answers ","authors_text":"Ke Tang, Liangpeng Zhang, Xin Yao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-02T22:38:37Z","title":"Success Probability of Exploration: a Concrete Analysis of Learning Efficiency"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.00882","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":"sha256:3943f924e2b3bc2944f14c8228f82bb404141f4d26b48f6764de6466489bb3a1","target":"record","created_at":"2026-05-18T00:55:53Z","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":"44ad7c81d5c670c6fe09f949b2b1a13d335937dc0fe34e1af62389b3cc276aba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-02T22:38:37Z","title_canon_sha256":"9ad0d45fcc796767f1829496b08db1c6f10cba2373f611d6cb61875d10b0cb88"},"schema_version":"1.0","source":{"id":"1612.00882","kind":"arxiv","version":1}},"canonical_sha256":"23ee58b04ee221b8a466cb87751d3515844c21c3dd0a798f11d3f08fdae30db6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23ee58b04ee221b8a466cb87751d3515844c21c3dd0a798f11d3f08fdae30db6","first_computed_at":"2026-05-18T00:55:53.913976Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:55:53.913976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+aPVGf3ToIyEpge40RV+qpDeQzIyCF3IdaSz61gzq1/bBI5wTFdLVEH2qaWEr3QM60otrsjIbpemFCEjn1X2BA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:55:53.914482Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.00882","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3943f924e2b3bc2944f14c8228f82bb404141f4d26b48f6764de6466489bb3a1","sha256:92d295e5ab2c78d6393a71f7398a660fdcc423c7a4a6e472b295676bf08946a9"],"state_sha256":"df18678e283da31abef4366d842c6636cb915a120a6d67ca1fb54ecd0fa7d0a3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3EyCgV3aeARkI/eUrrgTzhnhMmrRiAR6le+43Llwpx2j+okI9UjXnuOBktrK7tXy/hNLG7VvpDSNk0WojRkcAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T15:50:05.353451Z","bundle_sha256":"db00906d1b7f108959183a5dd13664bbd6de7ac28c89821049c0d5fcef4fb79d"}}