{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:VQBP2Y3IUMDYNYK5EM6YO22KIP","short_pith_number":"pith:VQBP2Y3I","canonical_record":{"source":{"id":"2211.07419","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-14T14:48:39Z","cross_cats_sorted":[],"title_canon_sha256":"45c2515bade124160f7d39d7e2ea824330157186c071a2adde76a9ce847f28ac","abstract_canon_sha256":"7da580c6a68ad9bceeb169badb512ee99582d886b00c2892b62be106e0125fb2"},"schema_version":"1.0"},"canonical_sha256":"ac02fd6368a30786e15d233d876b4a43eb81718414aa9b51e4a5e2bf3106e4cd","source":{"kind":"arxiv","id":"2211.07419","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.07419","created_at":"2026-07-05T05:15:53Z"},{"alias_kind":"arxiv_version","alias_value":"2211.07419v1","created_at":"2026-07-05T05:15:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.07419","created_at":"2026-07-05T05:15:53Z"},{"alias_kind":"pith_short_12","alias_value":"VQBP2Y3IUMDY","created_at":"2026-07-05T05:15:53Z"},{"alias_kind":"pith_short_16","alias_value":"VQBP2Y3IUMDYNYK5","created_at":"2026-07-05T05:15:53Z"},{"alias_kind":"pith_short_8","alias_value":"VQBP2Y3I","created_at":"2026-07-05T05:15:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:VQBP2Y3IUMDYNYK5EM6YO22KIP","target":"record","payload":{"canonical_record":{"source":{"id":"2211.07419","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-14T14:48:39Z","cross_cats_sorted":[],"title_canon_sha256":"45c2515bade124160f7d39d7e2ea824330157186c071a2adde76a9ce847f28ac","abstract_canon_sha256":"7da580c6a68ad9bceeb169badb512ee99582d886b00c2892b62be106e0125fb2"},"schema_version":"1.0"},"canonical_sha256":"ac02fd6368a30786e15d233d876b4a43eb81718414aa9b51e4a5e2bf3106e4cd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:53.345537Z","signature_b64":"VW//wKL4zavQ8Lf/wNZB+ambiSn3wrEjxK70SXZW/6xtIBGgwUYJ223JpcVCuoyIs/vtSO6fre70/R+EBTYtAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac02fd6368a30786e15d233d876b4a43eb81718414aa9b51e4a5e2bf3106e4cd","last_reissued_at":"2026-07-05T05:15:53.344965Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:53.344965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.07419","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":"2026-07-05T05:15:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6mniTw2VV7SGOKfAhb+xa9vTzSl5KFu/jNCdgGhnwpdQVFRBF8JAdFSmzqmNoaSdaeYC/+u18HsFJNHt76dAAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:32:00.683078Z"},"content_sha256":"4e3059252b9445c21c9ef5ea837938eb7a979fa5b52c68410de20d04f0475a32","schema_version":"1.0","event_id":"sha256:4e3059252b9445c21c9ef5ea837938eb7a979fa5b52c68410de20d04f0475a32"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:VQBP2Y3IUMDYNYK5EM6YO22KIP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Linear Reinforcement Learning with Ball Structure Action Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dean P. Foster, Dhruv Madeka, Randy Jia, Zeyu Jia","submitted_at":"2022-11-14T14:48:39Z","abstract_excerpt":"We study the problem of Reinforcement Learning (RL) with linear function approximation, i.e. assuming the optimal action-value function is linear in a known $d$-dimensional feature mapping. Unfortunately, however, based on only this assumption, the worst case sample complexity has been shown to be exponential, even under a generative model. Instead of making further assumptions on the MDP or value functions, we assume that our action space is such that there always exist playable actions to explore any direction of the feature space. We formalize this assumption as a ``ball structure'' action "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.07419","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/2211.07419/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":"2026-07-05T05:15:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HGxHj5paM+I6je4ClT1NmoQvgPu9lBJWqUkXvY6JmFfffPS7zpiDvXqfpIHT2DXEUfCCrTbzGRiZqscOioCLCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:32:00.683490Z"},"content_sha256":"929c4122cd8b2ce1e0c5c204e121d50fa68184bfc30c92bf0b25095519dad7c5","schema_version":"1.0","event_id":"sha256:929c4122cd8b2ce1e0c5c204e121d50fa68184bfc30c92bf0b25095519dad7c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VQBP2Y3IUMDYNYK5EM6YO22KIP/bundle.json","state_url":"https://pith.science/pith/VQBP2Y3IUMDYNYK5EM6YO22KIP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VQBP2Y3IUMDYNYK5EM6YO22KIP/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":"2026-07-06T08:32:00Z","links":{"resolver":"https://pith.science/pith/VQBP2Y3IUMDYNYK5EM6YO22KIP","bundle":"https://pith.science/pith/VQBP2Y3IUMDYNYK5EM6YO22KIP/bundle.json","state":"https://pith.science/pith/VQBP2Y3IUMDYNYK5EM6YO22KIP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VQBP2Y3IUMDYNYK5EM6YO22KIP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VQBP2Y3IUMDYNYK5EM6YO22KIP","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":"7da580c6a68ad9bceeb169badb512ee99582d886b00c2892b62be106e0125fb2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-14T14:48:39Z","title_canon_sha256":"45c2515bade124160f7d39d7e2ea824330157186c071a2adde76a9ce847f28ac"},"schema_version":"1.0","source":{"id":"2211.07419","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.07419","created_at":"2026-07-05T05:15:53Z"},{"alias_kind":"arxiv_version","alias_value":"2211.07419v1","created_at":"2026-07-05T05:15:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.07419","created_at":"2026-07-05T05:15:53Z"},{"alias_kind":"pith_short_12","alias_value":"VQBP2Y3IUMDY","created_at":"2026-07-05T05:15:53Z"},{"alias_kind":"pith_short_16","alias_value":"VQBP2Y3IUMDYNYK5","created_at":"2026-07-05T05:15:53Z"},{"alias_kind":"pith_short_8","alias_value":"VQBP2Y3I","created_at":"2026-07-05T05:15:53Z"}],"graph_snapshots":[{"event_id":"sha256:929c4122cd8b2ce1e0c5c204e121d50fa68184bfc30c92bf0b25095519dad7c5","target":"graph","created_at":"2026-07-05T05:15:53Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2211.07419/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the problem of Reinforcement Learning (RL) with linear function approximation, i.e. assuming the optimal action-value function is linear in a known $d$-dimensional feature mapping. Unfortunately, however, based on only this assumption, the worst case sample complexity has been shown to be exponential, even under a generative model. Instead of making further assumptions on the MDP or value functions, we assume that our action space is such that there always exist playable actions to explore any direction of the feature space. We formalize this assumption as a ``ball structure'' action ","authors_text":"Dean P. Foster, Dhruv Madeka, Randy Jia, Zeyu Jia","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-14T14:48:39Z","title":"Linear Reinforcement Learning with Ball Structure Action Space"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.07419","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":"sha256:4e3059252b9445c21c9ef5ea837938eb7a979fa5b52c68410de20d04f0475a32","target":"record","created_at":"2026-07-05T05:15:53Z","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":"7da580c6a68ad9bceeb169badb512ee99582d886b00c2892b62be106e0125fb2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-14T14:48:39Z","title_canon_sha256":"45c2515bade124160f7d39d7e2ea824330157186c071a2adde76a9ce847f28ac"},"schema_version":"1.0","source":{"id":"2211.07419","kind":"arxiv","version":1}},"canonical_sha256":"ac02fd6368a30786e15d233d876b4a43eb81718414aa9b51e4a5e2bf3106e4cd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac02fd6368a30786e15d233d876b4a43eb81718414aa9b51e4a5e2bf3106e4cd","first_computed_at":"2026-07-05T05:15:53.344965Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:15:53.344965Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VW//wKL4zavQ8Lf/wNZB+ambiSn3wrEjxK70SXZW/6xtIBGgwUYJ223JpcVCuoyIs/vtSO6fre70/R+EBTYtAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:15:53.345537Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.07419","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e3059252b9445c21c9ef5ea837938eb7a979fa5b52c68410de20d04f0475a32","sha256:929c4122cd8b2ce1e0c5c204e121d50fa68184bfc30c92bf0b25095519dad7c5"],"state_sha256":"a189a480bad05fb28397d44eba97d16a237431944738f51625e177b6f0fec9fe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qVEEca6B7/kA3rVhmaCgVptWBrffK1gmBPutgm9yccu2e7tzD72XZ8mjYesmp1dLQD6jqDwJktyY3/7Lx2B/Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T08:32:00.685649Z","bundle_sha256":"250c048624788e50c725a0db2f76e80b048f2eb686d587f003c80be860063518"}}