{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:J4ZSD4PJCG2BHBKRD26UD74ITP","short_pith_number":"pith:J4ZSD4PJ","canonical_record":{"source":{"id":"1205.2606","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-05-09T18:40:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"440f3d5ad119ca97b7a9151792575d92001ac8c6f9492cb6ae2d6466cef93ab2","abstract_canon_sha256":"f9820c200ae371ccb52b53e73e9ad5236a3888cd979d4eb6aece0a44758ce525"},"schema_version":"1.0"},"canonical_sha256":"4f3321f1e911b41385511ebd41ff889bc0781b8f7a78613a5d15ba2d6ef6986c","source":{"kind":"arxiv","id":"1205.2606","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1205.2606","created_at":"2026-05-18T03:55:47Z"},{"alias_kind":"arxiv_version","alias_value":"1205.2606v1","created_at":"2026-05-18T03:55:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1205.2606","created_at":"2026-05-18T03:55:47Z"},{"alias_kind":"pith_short_12","alias_value":"J4ZSD4PJCG2B","created_at":"2026-05-18T12:27:09Z"},{"alias_kind":"pith_short_16","alias_value":"J4ZSD4PJCG2BHBKR","created_at":"2026-05-18T12:27:09Z"},{"alias_kind":"pith_short_8","alias_value":"J4ZSD4PJ","created_at":"2026-05-18T12:27:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:J4ZSD4PJCG2BHBKRD26UD74ITP","target":"record","payload":{"canonical_record":{"source":{"id":"1205.2606","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-05-09T18:40:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"440f3d5ad119ca97b7a9151792575d92001ac8c6f9492cb6ae2d6466cef93ab2","abstract_canon_sha256":"f9820c200ae371ccb52b53e73e9ad5236a3888cd979d4eb6aece0a44758ce525"},"schema_version":"1.0"},"canonical_sha256":"4f3321f1e911b41385511ebd41ff889bc0781b8f7a78613a5d15ba2d6ef6986c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:55:47.949371Z","signature_b64":"YYtBMs4pIlgFTLEb6PO3AX6sRi8UcjJNw5UHEugFsRNyyZaGSAvtEJRqB+y4JbevU6h6zR71GOt1NTx0OZokAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f3321f1e911b41385511ebd41ff889bc0781b8f7a78613a5d15ba2d6ef6986c","last_reissued_at":"2026-05-18T03:55:47.948836Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:55:47.948836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1205.2606","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":"2026-05-18T03:55:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gUasM5vyeamAzlvyWAtwLfPP/yk1G5o02J2yJE9mIwEjuL+ur/pAyTUsAznx8y5hXaYlSrb6Ld0phaxSaIcCCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T20:48:52.213850Z"},"content_sha256":"1e0a27c7a4c13ba33366f01714a55d48284e1014b4a7995c9bba9ede3e9111b5","schema_version":"1.0","event_id":"sha256:1e0a27c7a4c13ba33366f01714a55d48284e1014b4a7995c9bba9ede3e9111b5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:J4ZSD4PJCG2BHBKRD26UD74ITP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring compact reinforcement-learning representations with linear regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Carlos Diuk, Istvan Szita, Michael L. Littman, Thomas J. Walsh","submitted_at":"2012-05-09T18:40:40Z","abstract_excerpt":"This paper presents a new algorithm for online linear regression whose efficiency guarantees satisfy the requirements of the KWIK (Knows What It Knows) framework. The algorithm improves on the complexity bounds of the current state-of-the-art procedure in this setting. We explore several applications of this algorithm for learning compact reinforcement-learning representations. We show that KWIK linear regression can be used to learn the reward function of a factored MDP and the probabilities of action outcomes in Stochastic STRIPS and Object Oriented MDPs, none of which have been proven to be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1205.2606","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":"2026-05-18T03:55:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2YVt5EBXfI0jC8+dtSRli7qMyfwfiyoRtfgUpeymXFjS2QEIHnGok1XtDQCwniwfLcbARnLzIzBVqoyDmLqAAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T20:48:52.214596Z"},"content_sha256":"41dd99c3a79076645193ebf0929a0def008a51067c1f65e705b4f6e73fea2b30","schema_version":"1.0","event_id":"sha256:41dd99c3a79076645193ebf0929a0def008a51067c1f65e705b4f6e73fea2b30"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J4ZSD4PJCG2BHBKRD26UD74ITP/bundle.json","state_url":"https://pith.science/pith/J4ZSD4PJCG2BHBKRD26UD74ITP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J4ZSD4PJCG2BHBKRD26UD74ITP/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":"2026-05-31T20:48:52Z","links":{"resolver":"https://pith.science/pith/J4ZSD4PJCG2BHBKRD26UD74ITP","bundle":"https://pith.science/pith/J4ZSD4PJCG2BHBKRD26UD74ITP/bundle.json","state":"https://pith.science/pith/J4ZSD4PJCG2BHBKRD26UD74ITP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J4ZSD4PJCG2BHBKRD26UD74ITP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:J4ZSD4PJCG2BHBKRD26UD74ITP","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":"f9820c200ae371ccb52b53e73e9ad5236a3888cd979d4eb6aece0a44758ce525","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-05-09T18:40:40Z","title_canon_sha256":"440f3d5ad119ca97b7a9151792575d92001ac8c6f9492cb6ae2d6466cef93ab2"},"schema_version":"1.0","source":{"id":"1205.2606","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1205.2606","created_at":"2026-05-18T03:55:47Z"},{"alias_kind":"arxiv_version","alias_value":"1205.2606v1","created_at":"2026-05-18T03:55:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1205.2606","created_at":"2026-05-18T03:55:47Z"},{"alias_kind":"pith_short_12","alias_value":"J4ZSD4PJCG2B","created_at":"2026-05-18T12:27:09Z"},{"alias_kind":"pith_short_16","alias_value":"J4ZSD4PJCG2BHBKR","created_at":"2026-05-18T12:27:09Z"},{"alias_kind":"pith_short_8","alias_value":"J4ZSD4PJ","created_at":"2026-05-18T12:27:09Z"}],"graph_snapshots":[{"event_id":"sha256:41dd99c3a79076645193ebf0929a0def008a51067c1f65e705b4f6e73fea2b30","target":"graph","created_at":"2026-05-18T03:55:47Z","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":"This paper presents a new algorithm for online linear regression whose efficiency guarantees satisfy the requirements of the KWIK (Knows What It Knows) framework. The algorithm improves on the complexity bounds of the current state-of-the-art procedure in this setting. We explore several applications of this algorithm for learning compact reinforcement-learning representations. We show that KWIK linear regression can be used to learn the reward function of a factored MDP and the probabilities of action outcomes in Stochastic STRIPS and Object Oriented MDPs, none of which have been proven to be","authors_text":"Carlos Diuk, Istvan Szita, Michael L. Littman, Thomas J. Walsh","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-05-09T18:40:40Z","title":"Exploring compact reinforcement-learning representations with linear regression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1205.2606","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":"sha256:1e0a27c7a4c13ba33366f01714a55d48284e1014b4a7995c9bba9ede3e9111b5","target":"record","created_at":"2026-05-18T03:55:47Z","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":"f9820c200ae371ccb52b53e73e9ad5236a3888cd979d4eb6aece0a44758ce525","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-05-09T18:40:40Z","title_canon_sha256":"440f3d5ad119ca97b7a9151792575d92001ac8c6f9492cb6ae2d6466cef93ab2"},"schema_version":"1.0","source":{"id":"1205.2606","kind":"arxiv","version":1}},"canonical_sha256":"4f3321f1e911b41385511ebd41ff889bc0781b8f7a78613a5d15ba2d6ef6986c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f3321f1e911b41385511ebd41ff889bc0781b8f7a78613a5d15ba2d6ef6986c","first_computed_at":"2026-05-18T03:55:47.948836Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:55:47.948836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YYtBMs4pIlgFTLEb6PO3AX6sRi8UcjJNw5UHEugFsRNyyZaGSAvtEJRqB+y4JbevU6h6zR71GOt1NTx0OZokAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:55:47.949371Z","signed_message":"canonical_sha256_bytes"},"source_id":"1205.2606","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e0a27c7a4c13ba33366f01714a55d48284e1014b4a7995c9bba9ede3e9111b5","sha256:41dd99c3a79076645193ebf0929a0def008a51067c1f65e705b4f6e73fea2b30"],"state_sha256":"10957a47a2986e3bc4c231aae1f08f1f4054e3e3b3cf77263e5bec95f1f4131a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VbcIO2JB/L60TRcy2zuX5+25otvL2ywhAygZHieIaBJSMQuPCJrXwvUDgNMZxpFKCBiF5XGeTCm2T7mp0ChNBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T20:48:52.218243Z","bundle_sha256":"38533020e463a1c81e3d48808298213e53447a1a885f63e4dff474f38672e07a"}}