{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:DUP6OSESZKLAQTK7BTM2Y7DLXU","short_pith_number":"pith:DUP6OSES","canonical_record":{"source":{"id":"1804.04012","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-11T14:21:53Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"332286d8c4f413c9a9664f97fa64cb07773abb24e43759e65e238f040f74ed9f","abstract_canon_sha256":"e67372c2c6e15aa2eda5485f7c3730c8c13ef7e5494cf850b2bca49562cf52cb"},"schema_version":"1.0"},"canonical_sha256":"1d1fe74892ca96084d5f0cd9ac7c6bbd22da114e9247aedb32f9e5f958eadacd","source":{"kind":"arxiv","id":"1804.04012","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.04012","created_at":"2026-05-18T00:18:42Z"},{"alias_kind":"arxiv_version","alias_value":"1804.04012v1","created_at":"2026-05-18T00:18:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.04012","created_at":"2026-05-18T00:18:42Z"},{"alias_kind":"pith_short_12","alias_value":"DUP6OSESZKLA","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DUP6OSESZKLAQTK7","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DUP6OSES","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:DUP6OSESZKLAQTK7BTM2Y7DLXU","target":"record","payload":{"canonical_record":{"source":{"id":"1804.04012","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-11T14:21:53Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"332286d8c4f413c9a9664f97fa64cb07773abb24e43759e65e238f040f74ed9f","abstract_canon_sha256":"e67372c2c6e15aa2eda5485f7c3730c8c13ef7e5494cf850b2bca49562cf52cb"},"schema_version":"1.0"},"canonical_sha256":"1d1fe74892ca96084d5f0cd9ac7c6bbd22da114e9247aedb32f9e5f958eadacd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:42.381300Z","signature_b64":"z/vdupk8KId3h1poho0+KH8Dlv3VM9SPRYJovvtOMrkdLVgQgdgJ/sUMemKYeqUCrMpZqPnutC6DAPUjBpB6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d1fe74892ca96084d5f0cd9ac7c6bbd22da114e9247aedb32f9e5f958eadacd","last_reissued_at":"2026-05-18T00:18:42.380617Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:42.380617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.04012","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":"2026-05-18T00:18:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Prq8duUqhpDGjd3rFvXws2TF1niTPNxgs6dK3GAFzXArUJ511xfXRTCPiaqK5exIbQCRxK5QxVNs6G1L+qwuBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:04:35.528633Z"},"content_sha256":"6a046f0297bfae533d8c7e8ed25144b7c30b4c28c475893879734f4433ce5377","schema_version":"1.0","event_id":"sha256:6a046f0297bfae533d8c7e8ed25144b7c30b4c28c475893879734f4433ce5377"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:DUP6OSESZKLAQTK7BTM2Y7DLXU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DORA The Explorer: Directed Outreaching Reinforcement Action-Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Leshem Choshen, Lior Fox, Yonatan Loewenstein","submitted_at":"2018-04-11T14:21:53Z","abstract_excerpt":"Exploration is a fundamental aspect of Reinforcement Learning, typically implemented using stochastic action-selection. Exploration, however, can be more efficient if directed toward gaining new world knowledge. Visit-counters have been proven useful both in practice and in theory for directed exploration. However, a major limitation of counters is their locality. While there are a few model-based solutions to this shortcoming, a model-free approach is still missing. We propose $E$-values, a generalization of counters that can be used to evaluate the propagating exploratory value over state-ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.04012","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":"2026-05-18T00:18:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2bfy7k2JlJfMuEFiqCz3uR05uBVn9c8LLRh43k86pxgvRX1YVC7tqciVMRUdN7TkybD4Tk50PomL4eIjZV93Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T16:04:35.529370Z"},"content_sha256":"dd53187d3db8ef4287480f1df54406cb664eb7ecdf515cb86090fd66454263c6","schema_version":"1.0","event_id":"sha256:dd53187d3db8ef4287480f1df54406cb664eb7ecdf515cb86090fd66454263c6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DUP6OSESZKLAQTK7BTM2Y7DLXU/bundle.json","state_url":"https://pith.science/pith/DUP6OSESZKLAQTK7BTM2Y7DLXU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DUP6OSESZKLAQTK7BTM2Y7DLXU/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":"2026-05-25T16:04:35Z","links":{"resolver":"https://pith.science/pith/DUP6OSESZKLAQTK7BTM2Y7DLXU","bundle":"https://pith.science/pith/DUP6OSESZKLAQTK7BTM2Y7DLXU/bundle.json","state":"https://pith.science/pith/DUP6OSESZKLAQTK7BTM2Y7DLXU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DUP6OSESZKLAQTK7BTM2Y7DLXU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DUP6OSESZKLAQTK7BTM2Y7DLXU","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":"e67372c2c6e15aa2eda5485f7c3730c8c13ef7e5494cf850b2bca49562cf52cb","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-11T14:21:53Z","title_canon_sha256":"332286d8c4f413c9a9664f97fa64cb07773abb24e43759e65e238f040f74ed9f"},"schema_version":"1.0","source":{"id":"1804.04012","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.04012","created_at":"2026-05-18T00:18:42Z"},{"alias_kind":"arxiv_version","alias_value":"1804.04012v1","created_at":"2026-05-18T00:18:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.04012","created_at":"2026-05-18T00:18:42Z"},{"alias_kind":"pith_short_12","alias_value":"DUP6OSESZKLA","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DUP6OSESZKLAQTK7","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DUP6OSES","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:dd53187d3db8ef4287480f1df54406cb664eb7ecdf515cb86090fd66454263c6","target":"graph","created_at":"2026-05-18T00:18:42Z","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":"Exploration is a fundamental aspect of Reinforcement Learning, typically implemented using stochastic action-selection. Exploration, however, can be more efficient if directed toward gaining new world knowledge. Visit-counters have been proven useful both in practice and in theory for directed exploration. However, a major limitation of counters is their locality. While there are a few model-based solutions to this shortcoming, a model-free approach is still missing. We propose $E$-values, a generalization of counters that can be used to evaluate the propagating exploratory value over state-ac","authors_text":"Leshem Choshen, Lior Fox, Yonatan Loewenstein","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-11T14:21:53Z","title":"DORA The Explorer: Directed Outreaching Reinforcement Action-Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.04012","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":"sha256:6a046f0297bfae533d8c7e8ed25144b7c30b4c28c475893879734f4433ce5377","target":"record","created_at":"2026-05-18T00:18:42Z","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":"e67372c2c6e15aa2eda5485f7c3730c8c13ef7e5494cf850b2bca49562cf52cb","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-11T14:21:53Z","title_canon_sha256":"332286d8c4f413c9a9664f97fa64cb07773abb24e43759e65e238f040f74ed9f"},"schema_version":"1.0","source":{"id":"1804.04012","kind":"arxiv","version":1}},"canonical_sha256":"1d1fe74892ca96084d5f0cd9ac7c6bbd22da114e9247aedb32f9e5f958eadacd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d1fe74892ca96084d5f0cd9ac7c6bbd22da114e9247aedb32f9e5f958eadacd","first_computed_at":"2026-05-18T00:18:42.380617Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:18:42.380617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z/vdupk8KId3h1poho0+KH8Dlv3VM9SPRYJovvtOMrkdLVgQgdgJ/sUMemKYeqUCrMpZqPnutC6DAPUjBpB6DA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:18:42.381300Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.04012","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a046f0297bfae533d8c7e8ed25144b7c30b4c28c475893879734f4433ce5377","sha256:dd53187d3db8ef4287480f1df54406cb664eb7ecdf515cb86090fd66454263c6"],"state_sha256":"b091c58090c528ce573930e547b98419dff9844fa3fd157f62b76a86d85c06cf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6CR2PlJGYCCjkbej3I50+grePLIOB1yRUnwho96DuGE62L2Jl0jqlUQeWj58oAVaqVt7UpHTl56QZHBUxx3SAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T16:04:35.533295Z","bundle_sha256":"1af6c0ec071a89340a76d12c02b58fef5e944dd9eef073be945c5b5a4cc2c57e"}}