{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AAGY6JAZHLKYXLYQUIJYVQHQGP","short_pith_number":"pith:AAGY6JAZ","canonical_record":{"source":{"id":"2512.06244","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-06T02:04:50Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"62a901f0fd011aec2e67c96c59c2cc325772df509dc73af228d165f9b9195cb0","abstract_canon_sha256":"263d93f6556599e81b408819bca0c44054c37ab9620eb6dce6b30e86c5cce8c9"},"schema_version":"1.0"},"canonical_sha256":"000d8f24193ad58baf10a2138ac0f033f12bfec26d56c8084e5fc417c0911d49","source":{"kind":"arxiv","id":"2512.06244","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.06244","created_at":"2026-06-25T01:18:36Z"},{"alias_kind":"arxiv_version","alias_value":"2512.06244v2","created_at":"2026-06-25T01:18:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.06244","created_at":"2026-06-25T01:18:36Z"},{"alias_kind":"pith_short_12","alias_value":"AAGY6JAZHLKY","created_at":"2026-06-25T01:18:36Z"},{"alias_kind":"pith_short_16","alias_value":"AAGY6JAZHLKYXLYQ","created_at":"2026-06-25T01:18:36Z"},{"alias_kind":"pith_short_8","alias_value":"AAGY6JAZ","created_at":"2026-06-25T01:18:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AAGY6JAZHLKYXLYQUIJYVQHQGP","target":"record","payload":{"canonical_record":{"source":{"id":"2512.06244","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-06T02:04:50Z","cross_cats_sorted":["cs.AI","math.OC"],"title_canon_sha256":"62a901f0fd011aec2e67c96c59c2cc325772df509dc73af228d165f9b9195cb0","abstract_canon_sha256":"263d93f6556599e81b408819bca0c44054c37ab9620eb6dce6b30e86c5cce8c9"},"schema_version":"1.0"},"canonical_sha256":"000d8f24193ad58baf10a2138ac0f033f12bfec26d56c8084e5fc417c0911d49","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:18:36.166340Z","signature_b64":"45PLO/92t5xTkbBTmDR6eYURXpF0vtzWXUjxCjOsplsyYe+wyLy8l8HlwcXP3pjvv1Dk6PV844YDAjXfnbbsBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"000d8f24193ad58baf10a2138ac0f033f12bfec26d56c8084e5fc417c0911d49","last_reissued_at":"2026-06-25T01:18:36.165879Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:18:36.165879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2512.06244","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":"2026-06-25T01:18:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zrKfcOUo/SuCiOwLMiP9ZVPX7nT++h7w/NwvDsadwmMyphz31QRVooGHike4SoCcmIQiCwgovFS5vziaMPyDCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T03:24:36.781638Z"},"content_sha256":"c8fa0eb0129ef4dd6816048d09ff548247537008871674737e3a1a4d14a3f8c1","schema_version":"1.0","event_id":"sha256:c8fa0eb0129ef4dd6816048d09ff548247537008871674737e3a1a4d14a3f8c1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AAGY6JAZHLKYXLYQUIJYVQHQGP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Auto-exploration for online reinforcement learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","math.OC"],"primary_cat":"cs.LG","authors_text":"Caleb Ju, Guanghui Lan","submitted_at":"2025-12-06T02:04:50Z","abstract_excerpt":"The exploration-exploitation dilemma in reinforcement learning (RL) is a fundamental challenge to efficient RL algorithms. Existing algorithms for finite state and action discounted RL problems address this by assuming sufficient exploration over both state and action spaces. However, this yields non-implementable algorithms and sub-optimal performance. To resolve these limitations, we introduce a new class of methods with auto-exploration, or methods that automatically explore both state and action spaces. Auto-exploration can be applied in both the tabular and linear function approximation s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.06244","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2512.06244/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":"2026-06-25T01:18:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C2ALpEaw9AxJWdwxBkesB2lcq27hLNb/DrckjguSE7qT4xj2/xiG7eyMarilVo06nUYty9DOQ8YkjJ4mchHUCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T03:24:36.782128Z"},"content_sha256":"42efb9fe566bda092a594805065c0b438b3e721ddaad47ac7f400f68a7128741","schema_version":"1.0","event_id":"sha256:42efb9fe566bda092a594805065c0b438b3e721ddaad47ac7f400f68a7128741"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AAGY6JAZHLKYXLYQUIJYVQHQGP/bundle.json","state_url":"https://pith.science/pith/AAGY6JAZHLKYXLYQUIJYVQHQGP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AAGY6JAZHLKYXLYQUIJYVQHQGP/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":"2026-08-17T03:24:36Z","links":{"resolver":"https://pith.science/pith/AAGY6JAZHLKYXLYQUIJYVQHQGP","bundle":"https://pith.science/pith/AAGY6JAZHLKYXLYQUIJYVQHQGP/bundle.json","state":"https://pith.science/pith/AAGY6JAZHLKYXLYQUIJYVQHQGP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AAGY6JAZHLKYXLYQUIJYVQHQGP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AAGY6JAZHLKYXLYQUIJYVQHQGP","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":"263d93f6556599e81b408819bca0c44054c37ab9620eb6dce6b30e86c5cce8c9","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-06T02:04:50Z","title_canon_sha256":"62a901f0fd011aec2e67c96c59c2cc325772df509dc73af228d165f9b9195cb0"},"schema_version":"1.0","source":{"id":"2512.06244","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.06244","created_at":"2026-06-25T01:18:36Z"},{"alias_kind":"arxiv_version","alias_value":"2512.06244v2","created_at":"2026-06-25T01:18:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.06244","created_at":"2026-06-25T01:18:36Z"},{"alias_kind":"pith_short_12","alias_value":"AAGY6JAZHLKY","created_at":"2026-06-25T01:18:36Z"},{"alias_kind":"pith_short_16","alias_value":"AAGY6JAZHLKYXLYQ","created_at":"2026-06-25T01:18:36Z"},{"alias_kind":"pith_short_8","alias_value":"AAGY6JAZ","created_at":"2026-06-25T01:18:36Z"}],"graph_snapshots":[{"event_id":"sha256:42efb9fe566bda092a594805065c0b438b3e721ddaad47ac7f400f68a7128741","target":"graph","created_at":"2026-06-25T01:18:36Z","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/2512.06244/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The exploration-exploitation dilemma in reinforcement learning (RL) is a fundamental challenge to efficient RL algorithms. Existing algorithms for finite state and action discounted RL problems address this by assuming sufficient exploration over both state and action spaces. However, this yields non-implementable algorithms and sub-optimal performance. To resolve these limitations, we introduce a new class of methods with auto-exploration, or methods that automatically explore both state and action spaces. Auto-exploration can be applied in both the tabular and linear function approximation s","authors_text":"Caleb Ju, Guanghui Lan","cross_cats":["cs.AI","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-06T02:04:50Z","title":"Auto-exploration for online reinforcement learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.06244","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:c8fa0eb0129ef4dd6816048d09ff548247537008871674737e3a1a4d14a3f8c1","target":"record","created_at":"2026-06-25T01:18:36Z","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":"263d93f6556599e81b408819bca0c44054c37ab9620eb6dce6b30e86c5cce8c9","cross_cats_sorted":["cs.AI","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-12-06T02:04:50Z","title_canon_sha256":"62a901f0fd011aec2e67c96c59c2cc325772df509dc73af228d165f9b9195cb0"},"schema_version":"1.0","source":{"id":"2512.06244","kind":"arxiv","version":2}},"canonical_sha256":"000d8f24193ad58baf10a2138ac0f033f12bfec26d56c8084e5fc417c0911d49","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"000d8f24193ad58baf10a2138ac0f033f12bfec26d56c8084e5fc417c0911d49","first_computed_at":"2026-06-25T01:18:36.165879Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T01:18:36.165879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"45PLO/92t5xTkbBTmDR6eYURXpF0vtzWXUjxCjOsplsyYe+wyLy8l8HlwcXP3pjvv1Dk6PV844YDAjXfnbbsBQ==","signature_status":"signed_v1","signed_at":"2026-06-25T01:18:36.166340Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.06244","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8fa0eb0129ef4dd6816048d09ff548247537008871674737e3a1a4d14a3f8c1","sha256:42efb9fe566bda092a594805065c0b438b3e721ddaad47ac7f400f68a7128741"],"state_sha256":"1f491fb6a8d848615d30f1938f548713e0baf24482e261ffda4836294372b13f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a74hZP2D+VDt6pBwIk0cJtJUno2Z7IPns76PqpvO2Po6Lb4nIc2SI9bMjCTzj3xKub//G/H/i4QPJ4r/NcWOBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T03:24:36.786720Z","bundle_sha256":"b5e25f952f9afa9cc02a21228893cbd8d5830d256f009f09c2e8132edc00f99e"}}