{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VCRXIVTJH5I5QJO336NROSTO4L","short_pith_number":"pith:VCRXIVTJ","canonical_record":{"source":{"id":"2307.02276","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-05T13:20:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"21281af5f42061f22bdd231b7739f6c0876dafcb277f63267b67e03a47499051","abstract_canon_sha256":"e9973991c7d90841d325d1eff054e47f8068064de13a558dfd16e193de80026e"},"schema_version":"1.0"},"canonical_sha256":"a8a37456693f51d825dbdf9b174a6ee2d3f6595b596b74d43bb812a85a3f4e73","source":{"kind":"arxiv","id":"2307.02276","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.02276","created_at":"2026-07-05T09:30:56Z"},{"alias_kind":"arxiv_version","alias_value":"2307.02276v2","created_at":"2026-07-05T09:30:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.02276","created_at":"2026-07-05T09:30:56Z"},{"alias_kind":"pith_short_12","alias_value":"VCRXIVTJH5I5","created_at":"2026-07-05T09:30:56Z"},{"alias_kind":"pith_short_16","alias_value":"VCRXIVTJH5I5QJO3","created_at":"2026-07-05T09:30:56Z"},{"alias_kind":"pith_short_8","alias_value":"VCRXIVTJ","created_at":"2026-07-05T09:30:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VCRXIVTJH5I5QJO336NROSTO4L","target":"record","payload":{"canonical_record":{"source":{"id":"2307.02276","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-05T13:20:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"21281af5f42061f22bdd231b7739f6c0876dafcb277f63267b67e03a47499051","abstract_canon_sha256":"e9973991c7d90841d325d1eff054e47f8068064de13a558dfd16e193de80026e"},"schema_version":"1.0"},"canonical_sha256":"a8a37456693f51d825dbdf9b174a6ee2d3f6595b596b74d43bb812a85a3f4e73","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:56.002903Z","signature_b64":"AoHln6ZujMnGOPofjoOG+PPu45KX4jSUbYvrAmVOKX0Ttmoqt+KpsBCsswaC8Kuo9XH5oVr2h89j1gs6J6UZAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8a37456693f51d825dbdf9b174a6ee2d3f6595b596b74d43bb812a85a3f4e73","last_reissued_at":"2026-07-05T09:30:56.002408Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:56.002408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.02276","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":"2026-07-05T09:30:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gTgHMBeBQIsfOD8xE30Px6OM/ZUynRfDLtqrXQuZgdlg4BDTAputGbM1MMSteS6kjUajNLdfBcqywqZJVDgECg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T18:05:37.918716Z"},"content_sha256":"360a381ccb550759a68b3b6904b92bceebb5ab8890af882764020588ed0e162a","schema_version":"1.0","event_id":"sha256:360a381ccb550759a68b3b6904b92bceebb5ab8890af882764020588ed0e162a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VCRXIVTJH5I5QJO336NROSTO4L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"First-Explore, then Exploit: Meta-Learning to Solve Hard Exploration-Exploitation Trade-Offs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ben Norman, Jeff Clune","submitted_at":"2023-07-05T13:20:21Z","abstract_excerpt":"Standard reinforcement learning (RL) agents never intelligently explore like a human (i.e. taking into account complex domain priors and adapting quickly based on previous exploration). Across episodes, RL agents struggle to perform even simple exploration strategies, for example systematic search that avoids exploring the same location multiple times. This poor exploration limits performance on challenging domains. Meta-RL is a potential solution, as unlike standard RL, meta-RL can learn to explore, and potentially learn highly complex strategies far beyond those of standard RL, strategies su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.02276","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/2307.02276/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":"2026-07-05T09:30:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HjflWLlEIx9X+Cp9yv1gFwjMttXOL9QTHw8E6c3YvJxRRk632ZrIn3RzPBZnd7JYyyfmh6A+h1LZ+qr2MPdFCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T18:05:37.919632Z"},"content_sha256":"0f24f6e24af8f5a5133c910b245a193df5718ed66ea6b4d69bd8afd7534056af","schema_version":"1.0","event_id":"sha256:0f24f6e24af8f5a5133c910b245a193df5718ed66ea6b4d69bd8afd7534056af"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VCRXIVTJH5I5QJO336NROSTO4L/bundle.json","state_url":"https://pith.science/pith/VCRXIVTJH5I5QJO336NROSTO4L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VCRXIVTJH5I5QJO336NROSTO4L/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":"2026-08-15T18:05:37Z","links":{"resolver":"https://pith.science/pith/VCRXIVTJH5I5QJO336NROSTO4L","bundle":"https://pith.science/pith/VCRXIVTJH5I5QJO336NROSTO4L/bundle.json","state":"https://pith.science/pith/VCRXIVTJH5I5QJO336NROSTO4L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VCRXIVTJH5I5QJO336NROSTO4L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VCRXIVTJH5I5QJO336NROSTO4L","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":"e9973991c7d90841d325d1eff054e47f8068064de13a558dfd16e193de80026e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-05T13:20:21Z","title_canon_sha256":"21281af5f42061f22bdd231b7739f6c0876dafcb277f63267b67e03a47499051"},"schema_version":"1.0","source":{"id":"2307.02276","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.02276","created_at":"2026-07-05T09:30:56Z"},{"alias_kind":"arxiv_version","alias_value":"2307.02276v2","created_at":"2026-07-05T09:30:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.02276","created_at":"2026-07-05T09:30:56Z"},{"alias_kind":"pith_short_12","alias_value":"VCRXIVTJH5I5","created_at":"2026-07-05T09:30:56Z"},{"alias_kind":"pith_short_16","alias_value":"VCRXIVTJH5I5QJO3","created_at":"2026-07-05T09:30:56Z"},{"alias_kind":"pith_short_8","alias_value":"VCRXIVTJ","created_at":"2026-07-05T09:30:56Z"}],"graph_snapshots":[{"event_id":"sha256:0f24f6e24af8f5a5133c910b245a193df5718ed66ea6b4d69bd8afd7534056af","target":"graph","created_at":"2026-07-05T09:30:56Z","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/2307.02276/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Standard reinforcement learning (RL) agents never intelligently explore like a human (i.e. taking into account complex domain priors and adapting quickly based on previous exploration). Across episodes, RL agents struggle to perform even simple exploration strategies, for example systematic search that avoids exploring the same location multiple times. This poor exploration limits performance on challenging domains. Meta-RL is a potential solution, as unlike standard RL, meta-RL can learn to explore, and potentially learn highly complex strategies far beyond those of standard RL, strategies su","authors_text":"Ben Norman, Jeff Clune","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-05T13:20:21Z","title":"First-Explore, then Exploit: Meta-Learning to Solve Hard Exploration-Exploitation Trade-Offs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.02276","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":"sha256:360a381ccb550759a68b3b6904b92bceebb5ab8890af882764020588ed0e162a","target":"record","created_at":"2026-07-05T09:30:56Z","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":"e9973991c7d90841d325d1eff054e47f8068064de13a558dfd16e193de80026e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-05T13:20:21Z","title_canon_sha256":"21281af5f42061f22bdd231b7739f6c0876dafcb277f63267b67e03a47499051"},"schema_version":"1.0","source":{"id":"2307.02276","kind":"arxiv","version":2}},"canonical_sha256":"a8a37456693f51d825dbdf9b174a6ee2d3f6595b596b74d43bb812a85a3f4e73","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8a37456693f51d825dbdf9b174a6ee2d3f6595b596b74d43bb812a85a3f4e73","first_computed_at":"2026-07-05T09:30:56.002408Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:56.002408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AoHln6ZujMnGOPofjoOG+PPu45KX4jSUbYvrAmVOKX0Ttmoqt+KpsBCsswaC8Kuo9XH5oVr2h89j1gs6J6UZAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:56.002903Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.02276","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:360a381ccb550759a68b3b6904b92bceebb5ab8890af882764020588ed0e162a","sha256:0f24f6e24af8f5a5133c910b245a193df5718ed66ea6b4d69bd8afd7534056af"],"state_sha256":"2cc337f93817dc1cea13159708fe78b40c67e9c6185cbc5f02629ccf643a5bc8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QzVZoVlOh2YWr2Th8lkEwO5DS1tLPmTLfpyjm1+xlb3/iR86SzlwVq0othTO1W0z2xU6s36RRF7bqwkRGcy+Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T18:05:37.926432Z","bundle_sha256":"5da52d2be371660de07743bb9a5cced9816be6fc4a0e0e032e16426c3fff03ea"}}