{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:3DQMXVZBVRUELOHVC7L5A3OOJR","short_pith_number":"pith:3DQMXVZB","canonical_record":{"source":{"id":"1201.2555","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-01-12T13:08:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3995dcd632ed898acdf029fc018b1f91add57e0a3256fc06799d3032e3f870b1","abstract_canon_sha256":"4df9df80fcd1e3572d062c232825d4c5dcfac8fbe334fba9f0a81657a2701bf5"},"schema_version":"1.0"},"canonical_sha256":"d8e0cbd721ac6845b8f517d7d06dce4c776d51b7fbcdc74e222b7f68ed40d2f3","source":{"kind":"arxiv","id":"1201.2555","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1201.2555","created_at":"2026-05-18T03:46:16Z"},{"alias_kind":"arxiv_version","alias_value":"1201.2555v2","created_at":"2026-05-18T03:46:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1201.2555","created_at":"2026-05-18T03:46:16Z"},{"alias_kind":"pith_short_12","alias_value":"3DQMXVZBVRUE","created_at":"2026-05-18T12:26:50Z"},{"alias_kind":"pith_short_16","alias_value":"3DQMXVZBVRUELOHV","created_at":"2026-05-18T12:26:50Z"},{"alias_kind":"pith_short_8","alias_value":"3DQMXVZB","created_at":"2026-05-18T12:26:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:3DQMXVZBVRUELOHVC7L5A3OOJR","target":"record","payload":{"canonical_record":{"source":{"id":"1201.2555","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-01-12T13:08:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3995dcd632ed898acdf029fc018b1f91add57e0a3256fc06799d3032e3f870b1","abstract_canon_sha256":"4df9df80fcd1e3572d062c232825d4c5dcfac8fbe334fba9f0a81657a2701bf5"},"schema_version":"1.0"},"canonical_sha256":"d8e0cbd721ac6845b8f517d7d06dce4c776d51b7fbcdc74e222b7f68ed40d2f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:46:16.739128Z","signature_b64":"k5umZYA28B8R//O7pSl9dGTH5fRKb8Lv3EMK4RTd1cNQidODKj1YAENpp6eZK8e4y5q4DeTVNFB3HG9bK65cDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8e0cbd721ac6845b8f517d7d06dce4c776d51b7fbcdc74e222b7f68ed40d2f3","last_reissued_at":"2026-05-18T03:46:16.738467Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:46:16.738467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1201.2555","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":"2026-05-18T03:46:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PWZjtfvQS/xBr+verEvCxrXDvHR9EhAtSYs2G6pwno+47JcL+MH6OH45Lf13teyclV+DaLvBLrgtU3PJcnADAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T12:13:27.103192Z"},"content_sha256":"fc9a1b26b57379490bad255c690759a4fcfada9ae291de01af7f5aad662ae698","schema_version":"1.0","event_id":"sha256:fc9a1b26b57379490bad255c690759a4fcfada9ae291de01af7f5aad662ae698"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:3DQMXVZBVRUELOHVC7L5A3OOJR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sparse Reward Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christos Dimitrakakis","submitted_at":"2012-01-12T13:08:27Z","abstract_excerpt":"We introduce a class of learning problems where the agent is presented with a series of tasks. Intuitively, if there is relation among those tasks, then the information gained during execution of one task has value for the execution of another task. Consequently, the agent is intrinsically motivated to explore its environment beyond the degree necessary to solve the current task it has at hand. We develop a decision theoretic setting that generalises standard reinforcement learning tasks and captures this intuition. More precisely, we consider a multi-stage stochastic game between a learning a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1201.2555","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":""},"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":"2026-05-18T03:46:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AjQLNluxj262pbvVWjZR+VtP+ijpJ2h2YNQ60MFJfIL7+1yFo5h3hfaf7UxewB/NqPeDgDYRCn4WKGUDrnr5Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T12:13:27.103547Z"},"content_sha256":"4ffd033f006bb960cba0785f17832040942a0cc87263767d492a579e3e2096d1","schema_version":"1.0","event_id":"sha256:4ffd033f006bb960cba0785f17832040942a0cc87263767d492a579e3e2096d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3DQMXVZBVRUELOHVC7L5A3OOJR/bundle.json","state_url":"https://pith.science/pith/3DQMXVZBVRUELOHVC7L5A3OOJR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3DQMXVZBVRUELOHVC7L5A3OOJR/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":"2026-06-11T12:13:27Z","links":{"resolver":"https://pith.science/pith/3DQMXVZBVRUELOHVC7L5A3OOJR","bundle":"https://pith.science/pith/3DQMXVZBVRUELOHVC7L5A3OOJR/bundle.json","state":"https://pith.science/pith/3DQMXVZBVRUELOHVC7L5A3OOJR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3DQMXVZBVRUELOHVC7L5A3OOJR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:3DQMXVZBVRUELOHVC7L5A3OOJR","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":"4df9df80fcd1e3572d062c232825d4c5dcfac8fbe334fba9f0a81657a2701bf5","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-01-12T13:08:27Z","title_canon_sha256":"3995dcd632ed898acdf029fc018b1f91add57e0a3256fc06799d3032e3f870b1"},"schema_version":"1.0","source":{"id":"1201.2555","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1201.2555","created_at":"2026-05-18T03:46:16Z"},{"alias_kind":"arxiv_version","alias_value":"1201.2555v2","created_at":"2026-05-18T03:46:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1201.2555","created_at":"2026-05-18T03:46:16Z"},{"alias_kind":"pith_short_12","alias_value":"3DQMXVZBVRUE","created_at":"2026-05-18T12:26:50Z"},{"alias_kind":"pith_short_16","alias_value":"3DQMXVZBVRUELOHV","created_at":"2026-05-18T12:26:50Z"},{"alias_kind":"pith_short_8","alias_value":"3DQMXVZB","created_at":"2026-05-18T12:26:50Z"}],"graph_snapshots":[{"event_id":"sha256:4ffd033f006bb960cba0785f17832040942a0cc87263767d492a579e3e2096d1","target":"graph","created_at":"2026-05-18T03:46:16Z","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":"We introduce a class of learning problems where the agent is presented with a series of tasks. Intuitively, if there is relation among those tasks, then the information gained during execution of one task has value for the execution of another task. Consequently, the agent is intrinsically motivated to explore its environment beyond the degree necessary to solve the current task it has at hand. We develop a decision theoretic setting that generalises standard reinforcement learning tasks and captures this intuition. More precisely, we consider a multi-stage stochastic game between a learning a","authors_text":"Christos Dimitrakakis","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-01-12T13:08:27Z","title":"Sparse Reward Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1201.2555","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:fc9a1b26b57379490bad255c690759a4fcfada9ae291de01af7f5aad662ae698","target":"record","created_at":"2026-05-18T03:46:16Z","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":"4df9df80fcd1e3572d062c232825d4c5dcfac8fbe334fba9f0a81657a2701bf5","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-01-12T13:08:27Z","title_canon_sha256":"3995dcd632ed898acdf029fc018b1f91add57e0a3256fc06799d3032e3f870b1"},"schema_version":"1.0","source":{"id":"1201.2555","kind":"arxiv","version":2}},"canonical_sha256":"d8e0cbd721ac6845b8f517d7d06dce4c776d51b7fbcdc74e222b7f68ed40d2f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8e0cbd721ac6845b8f517d7d06dce4c776d51b7fbcdc74e222b7f68ed40d2f3","first_computed_at":"2026-05-18T03:46:16.738467Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:46:16.738467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k5umZYA28B8R//O7pSl9dGTH5fRKb8Lv3EMK4RTd1cNQidODKj1YAENpp6eZK8e4y5q4DeTVNFB3HG9bK65cDg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:46:16.739128Z","signed_message":"canonical_sha256_bytes"},"source_id":"1201.2555","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fc9a1b26b57379490bad255c690759a4fcfada9ae291de01af7f5aad662ae698","sha256:4ffd033f006bb960cba0785f17832040942a0cc87263767d492a579e3e2096d1"],"state_sha256":"3535709169160e10980f09fac3a1a13b00d6e3cfdb1f01995b2207ea2ceb75e6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CRLV1Rt9GI+yIU+Lu4U4OErmgpC74IpzA0yCa37Ow3jGJJlHE4TziObCWviCWaVeC7LlraMwHiI3/HfA+hRABA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T12:13:27.105481Z","bundle_sha256":"312db4a56042922cc989cb448cb3a659a78a2223c10425f6165210af3ab4c4ae"}}