{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:HSU745TQ7RWMSJTEFHPXRVWHLZ","short_pith_number":"pith:HSU745TQ","canonical_record":{"source":{"id":"1808.04355","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-13T17:58:01Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO","stat.ML"],"title_canon_sha256":"b2951204314b8d7cc6d25d4a882daed9d19443c66d74dc5805ba8cae38c1ade4","abstract_canon_sha256":"a9ada91f2d32c26cdf3cef39c5e8460d5b7e53273462cef7a6aee03d05dc5004"},"schema_version":"1.0"},"canonical_sha256":"3ca9fe7670fc6cc9266429df78d6c75e503bbad12c3a9e3daf1f884471ac0674","source":{"kind":"arxiv","id":"1808.04355","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.04355","created_at":"2026-05-18T00:08:16Z"},{"alias_kind":"arxiv_version","alias_value":"1808.04355v1","created_at":"2026-05-18T00:08:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.04355","created_at":"2026-05-18T00:08:16Z"},{"alias_kind":"pith_short_12","alias_value":"HSU745TQ7RWM","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HSU745TQ7RWMSJTE","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HSU745TQ","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:HSU745TQ7RWMSJTEFHPXRVWHLZ","target":"record","payload":{"canonical_record":{"source":{"id":"1808.04355","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-13T17:58:01Z","cross_cats_sorted":["cs.AI","cs.CV","cs.RO","stat.ML"],"title_canon_sha256":"b2951204314b8d7cc6d25d4a882daed9d19443c66d74dc5805ba8cae38c1ade4","abstract_canon_sha256":"a9ada91f2d32c26cdf3cef39c5e8460d5b7e53273462cef7a6aee03d05dc5004"},"schema_version":"1.0"},"canonical_sha256":"3ca9fe7670fc6cc9266429df78d6c75e503bbad12c3a9e3daf1f884471ac0674","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:16.588080Z","signature_b64":"0WqOe2Dzz+v1qsKZFUWXscIkcWFkKlTDCDWq0DJ/pW+GlTx2fi2B4ulFg9pKIDGXBDcmrrAxXfCw7Yg2oquuDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ca9fe7670fc6cc9266429df78d6c75e503bbad12c3a9e3daf1f884471ac0674","last_reissued_at":"2026-05-18T00:08:16.587650Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:16.587650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.04355","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":"2026-05-18T00:08:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XMm3SN04fG5I/8VhIZdbA2uvmReS9UEJdZwxO4mrehqcyJDvxqYr1DJpDXKzbyJK2/pz/2RgkScc2OuMoYMVDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T05:37:15.628548Z"},"content_sha256":"18da0479705d9a8a4e1da1287aedc27551e729d4b67eb91a4544cd0a1051cf5b","schema_version":"1.0","event_id":"sha256:18da0479705d9a8a4e1da1287aedc27551e729d4b67eb91a4544cd0a1051cf5b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:HSU745TQ7RWMSJTEFHPXRVWHLZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large-Scale Study of Curiosity-Driven Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.RO","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexei A. Efros, Amos Storkey, Deepak Pathak, Harri Edwards, Trevor Darrell, Yuri Burda","submitted_at":"2018-08-13T17:58:01Z","abstract_excerpt":"Reinforcement learning algorithms rely on carefully engineering environment rewards that are extrinsic to the agent. However, annotating each environment with hand-designed, dense rewards is not scalable, motivating the need for developing reward functions that are intrinsic to the agent. Curiosity is a type of intrinsic reward function which uses prediction error as reward signal. In this paper: (a) We perform the first large-scale study of purely curiosity-driven learning, i.e. without any extrinsic rewards, across 54 standard benchmark environments, including the Atari game suite. Our resul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.04355","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":"2026-05-18T00:08:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L8dYS5SowoyJ/09qkuGgWOyNokhOR6S6ruLfpOBBbXSohz8wqP856udQHLsFniAVhDD7Da+3EYys/n9Tnqn6CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T05:37:15.628904Z"},"content_sha256":"e05a058a57b87665d74ee535a74a41534ead323c0bb37199e63f470c30815b20","schema_version":"1.0","event_id":"sha256:e05a058a57b87665d74ee535a74a41534ead323c0bb37199e63f470c30815b20"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HSU745TQ7RWMSJTEFHPXRVWHLZ/bundle.json","state_url":"https://pith.science/pith/HSU745TQ7RWMSJTEFHPXRVWHLZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HSU745TQ7RWMSJTEFHPXRVWHLZ/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":"2026-06-03T05:37:15Z","links":{"resolver":"https://pith.science/pith/HSU745TQ7RWMSJTEFHPXRVWHLZ","bundle":"https://pith.science/pith/HSU745TQ7RWMSJTEFHPXRVWHLZ/bundle.json","state":"https://pith.science/pith/HSU745TQ7RWMSJTEFHPXRVWHLZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HSU745TQ7RWMSJTEFHPXRVWHLZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:HSU745TQ7RWMSJTEFHPXRVWHLZ","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":"a9ada91f2d32c26cdf3cef39c5e8460d5b7e53273462cef7a6aee03d05dc5004","cross_cats_sorted":["cs.AI","cs.CV","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-13T17:58:01Z","title_canon_sha256":"b2951204314b8d7cc6d25d4a882daed9d19443c66d74dc5805ba8cae38c1ade4"},"schema_version":"1.0","source":{"id":"1808.04355","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.04355","created_at":"2026-05-18T00:08:16Z"},{"alias_kind":"arxiv_version","alias_value":"1808.04355v1","created_at":"2026-05-18T00:08:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.04355","created_at":"2026-05-18T00:08:16Z"},{"alias_kind":"pith_short_12","alias_value":"HSU745TQ7RWM","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HSU745TQ7RWMSJTE","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HSU745TQ","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:e05a058a57b87665d74ee535a74a41534ead323c0bb37199e63f470c30815b20","target":"graph","created_at":"2026-05-18T00:08:16Z","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":"Reinforcement learning algorithms rely on carefully engineering environment rewards that are extrinsic to the agent. However, annotating each environment with hand-designed, dense rewards is not scalable, motivating the need for developing reward functions that are intrinsic to the agent. Curiosity is a type of intrinsic reward function which uses prediction error as reward signal. In this paper: (a) We perform the first large-scale study of purely curiosity-driven learning, i.e. without any extrinsic rewards, across 54 standard benchmark environments, including the Atari game suite. Our resul","authors_text":"Alexei A. Efros, Amos Storkey, Deepak Pathak, Harri Edwards, Trevor Darrell, Yuri Burda","cross_cats":["cs.AI","cs.CV","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-13T17:58:01Z","title":"Large-Scale Study of Curiosity-Driven Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.04355","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":"sha256:18da0479705d9a8a4e1da1287aedc27551e729d4b67eb91a4544cd0a1051cf5b","target":"record","created_at":"2026-05-18T00:08:16Z","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":"a9ada91f2d32c26cdf3cef39c5e8460d5b7e53273462cef7a6aee03d05dc5004","cross_cats_sorted":["cs.AI","cs.CV","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-13T17:58:01Z","title_canon_sha256":"b2951204314b8d7cc6d25d4a882daed9d19443c66d74dc5805ba8cae38c1ade4"},"schema_version":"1.0","source":{"id":"1808.04355","kind":"arxiv","version":1}},"canonical_sha256":"3ca9fe7670fc6cc9266429df78d6c75e503bbad12c3a9e3daf1f884471ac0674","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ca9fe7670fc6cc9266429df78d6c75e503bbad12c3a9e3daf1f884471ac0674","first_computed_at":"2026-05-18T00:08:16.587650Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:08:16.587650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0WqOe2Dzz+v1qsKZFUWXscIkcWFkKlTDCDWq0DJ/pW+GlTx2fi2B4ulFg9pKIDGXBDcmrrAxXfCw7Yg2oquuDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:08:16.588080Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.04355","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:18da0479705d9a8a4e1da1287aedc27551e729d4b67eb91a4544cd0a1051cf5b","sha256:e05a058a57b87665d74ee535a74a41534ead323c0bb37199e63f470c30815b20"],"state_sha256":"5acc8a10031c12518a3da1df11021de188889916433c7e7a148483293a7efec1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4GYG5Rv3NJhF91Gi557fvL1+QQ6jD36qOsH5GkT0OvKDAMEkdAj/0lrWxhfbwQWaJY5NYC6YiA9MES7QCCbeDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T05:37:15.630893Z","bundle_sha256":"ea4d8c639a2daef3c1819d4d4523bc04eea31d0e4e0c6539996a6701fa053039"}}