{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:AEL2JIJI2ONUVEAORP5LVDMNIR","short_pith_number":"pith:AEL2JIJI","canonical_record":{"source":{"id":"2008.07737","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-18T04:34:21Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bf944b7081149db4925443489b7e5d31bb8b94ce16190d053fce3529bb9f2d7a","abstract_canon_sha256":"a833a2280e54d0c332b6b5ff0cb422bdfe378a48a01e30d4ebc962c853b7f614"},"schema_version":"1.0"},"canonical_sha256":"0117a4a128d39b4a900e8bfaba8d8d44453dec6253f27b383606c2a25562b149","source":{"kind":"arxiv","id":"2008.07737","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.07737","created_at":"2026-07-05T01:45:05Z"},{"alias_kind":"arxiv_version","alias_value":"2008.07737v2","created_at":"2026-07-05T01:45:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.07737","created_at":"2026-07-05T01:45:05Z"},{"alias_kind":"pith_short_12","alias_value":"AEL2JIJI2ONU","created_at":"2026-07-05T01:45:05Z"},{"alias_kind":"pith_short_16","alias_value":"AEL2JIJI2ONUVEAO","created_at":"2026-07-05T01:45:05Z"},{"alias_kind":"pith_short_8","alias_value":"AEL2JIJI","created_at":"2026-07-05T01:45:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:AEL2JIJI2ONUVEAORP5LVDMNIR","target":"record","payload":{"canonical_record":{"source":{"id":"2008.07737","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-18T04:34:21Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bf944b7081149db4925443489b7e5d31bb8b94ce16190d053fce3529bb9f2d7a","abstract_canon_sha256":"a833a2280e54d0c332b6b5ff0cb422bdfe378a48a01e30d4ebc962c853b7f614"},"schema_version":"1.0"},"canonical_sha256":"0117a4a128d39b4a900e8bfaba8d8d44453dec6253f27b383606c2a25562b149","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:05.785016Z","signature_b64":"2JOBklElKNIpNQSn7XJnAKOeOdeMPm365zLjJ0oBGOHRK4q7B9GDJA7nCaVHDOp3BwTQOMsE98VaoaGbj/OJCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0117a4a128d39b4a900e8bfaba8d8d44453dec6253f27b383606c2a25562b149","last_reissued_at":"2026-07-05T01:45:05.784541Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:05.784541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.07737","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":"2026-07-05T01:45:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"74K5JmPO4QT9pEboMRgikKp/elrt/GpUzgW22ClCUI3xTjn7zfZOBhnogWxgICdYWlfccgCoWcedcftr+rpgBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:15:04.172745Z"},"content_sha256":"a5bc636d7260ac531c8946cb6387507f63072d6f88b307d82ce8c8557dd3b45e","schema_version":"1.0","event_id":"sha256:a5bc636d7260ac531c8946cb6387507f63072d6f88b307d82ce8c8557dd3b45e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:AEL2JIJI2ONUVEAORP5LVDMNIR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Provably Efficient Reward-Agnostic Navigation with Linear Value Iteration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessandro Lazaric, Andrea Zanette, Emma Brunskill, Mykel J. Kochenderfer","submitted_at":"2020-08-18T04:34:21Z","abstract_excerpt":"There has been growing progress on theoretical analyses for provably efficient learning in MDPs with linear function approximation, but much of the existing work has made strong assumptions to enable exploration by conventional exploration frameworks. Typically these assumptions are stronger than what is needed to find good solutions in the batch setting. In this work, we show how under a more standard notion of low inherent Bellman error, typically employed in least-square value iteration-style algorithms, we can provide strong PAC guarantees on learning a near optimal value function provided"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.07737","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/2008.07737/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":"2026-07-05T01:45:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7Ap7IfkDAK8UrTxZE46NmH5SkwJbPNlWHFJcmLxEAifdOjdlYVEFgav78Dy5CVtzDPFYbX+w8g2LC9pvzbXkCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:15:04.173119Z"},"content_sha256":"4ed9150a939e8a149af99b085ee33d2d981f58c4bf168579bda0fb2950eaa67c","schema_version":"1.0","event_id":"sha256:4ed9150a939e8a149af99b085ee33d2d981f58c4bf168579bda0fb2950eaa67c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AEL2JIJI2ONUVEAORP5LVDMNIR/bundle.json","state_url":"https://pith.science/pith/AEL2JIJI2ONUVEAORP5LVDMNIR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AEL2JIJI2ONUVEAORP5LVDMNIR/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":"2026-07-07T04:15:04Z","links":{"resolver":"https://pith.science/pith/AEL2JIJI2ONUVEAORP5LVDMNIR","bundle":"https://pith.science/pith/AEL2JIJI2ONUVEAORP5LVDMNIR/bundle.json","state":"https://pith.science/pith/AEL2JIJI2ONUVEAORP5LVDMNIR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AEL2JIJI2ONUVEAORP5LVDMNIR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:AEL2JIJI2ONUVEAORP5LVDMNIR","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":"a833a2280e54d0c332b6b5ff0cb422bdfe378a48a01e30d4ebc962c853b7f614","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-18T04:34:21Z","title_canon_sha256":"bf944b7081149db4925443489b7e5d31bb8b94ce16190d053fce3529bb9f2d7a"},"schema_version":"1.0","source":{"id":"2008.07737","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.07737","created_at":"2026-07-05T01:45:05Z"},{"alias_kind":"arxiv_version","alias_value":"2008.07737v2","created_at":"2026-07-05T01:45:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.07737","created_at":"2026-07-05T01:45:05Z"},{"alias_kind":"pith_short_12","alias_value":"AEL2JIJI2ONU","created_at":"2026-07-05T01:45:05Z"},{"alias_kind":"pith_short_16","alias_value":"AEL2JIJI2ONUVEAO","created_at":"2026-07-05T01:45:05Z"},{"alias_kind":"pith_short_8","alias_value":"AEL2JIJI","created_at":"2026-07-05T01:45:05Z"}],"graph_snapshots":[{"event_id":"sha256:4ed9150a939e8a149af99b085ee33d2d981f58c4bf168579bda0fb2950eaa67c","target":"graph","created_at":"2026-07-05T01:45:05Z","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/2008.07737/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There has been growing progress on theoretical analyses for provably efficient learning in MDPs with linear function approximation, but much of the existing work has made strong assumptions to enable exploration by conventional exploration frameworks. Typically these assumptions are stronger than what is needed to find good solutions in the batch setting. In this work, we show how under a more standard notion of low inherent Bellman error, typically employed in least-square value iteration-style algorithms, we can provide strong PAC guarantees on learning a near optimal value function provided","authors_text":"Alessandro Lazaric, Andrea Zanette, Emma Brunskill, Mykel J. Kochenderfer","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-18T04:34:21Z","title":"Provably Efficient Reward-Agnostic Navigation with Linear Value Iteration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.07737","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:a5bc636d7260ac531c8946cb6387507f63072d6f88b307d82ce8c8557dd3b45e","target":"record","created_at":"2026-07-05T01:45:05Z","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":"a833a2280e54d0c332b6b5ff0cb422bdfe378a48a01e30d4ebc962c853b7f614","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-18T04:34:21Z","title_canon_sha256":"bf944b7081149db4925443489b7e5d31bb8b94ce16190d053fce3529bb9f2d7a"},"schema_version":"1.0","source":{"id":"2008.07737","kind":"arxiv","version":2}},"canonical_sha256":"0117a4a128d39b4a900e8bfaba8d8d44453dec6253f27b383606c2a25562b149","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0117a4a128d39b4a900e8bfaba8d8d44453dec6253f27b383606c2a25562b149","first_computed_at":"2026-07-05T01:45:05.784541Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:45:05.784541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2JOBklElKNIpNQSn7XJnAKOeOdeMPm365zLjJ0oBGOHRK4q7B9GDJA7nCaVHDOp3BwTQOMsE98VaoaGbj/OJCw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:45:05.785016Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.07737","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5bc636d7260ac531c8946cb6387507f63072d6f88b307d82ce8c8557dd3b45e","sha256:4ed9150a939e8a149af99b085ee33d2d981f58c4bf168579bda0fb2950eaa67c"],"state_sha256":"06d5741f5c5b071636e5b29fe07737f3c5b4149fb9d8a6235a9df5b6c4f3524c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uwu9JvSfya6eJfaBvnQoFwGH2Y4WrNbJIZDnm1uSuABq2JXqB1s0/jBeoWrxHYmUDkB3DSHg3Y2nY9FQkg+VCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:15:04.178593Z","bundle_sha256":"08b287fb72854ae5186120f4717c53750ddde6a9a233aa19f70157340270cddc"}}