{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:MBT77DSWYCDTFZUO343CUGL434","short_pith_number":"pith:MBT77DSW","canonical_record":{"source":{"id":"1709.01308","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-05T09:47:41Z","cross_cats_sorted":[],"title_canon_sha256":"56fd0ffe34d21bb594d900905b85918469d691d3c7228b37d81e00487bdca82f","abstract_canon_sha256":"af6d97aaf28b8cad92fbb5e7a1e7b2262d24d16bf77c62dd628180cbbc3df154"},"schema_version":"1.0"},"canonical_sha256":"6067ff8e56c08732e68edf362a197cdf2d5b2788630c6e05cd69ea355c48fc59","source":{"kind":"arxiv","id":"1709.01308","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.01308","created_at":"2026-05-18T00:23:53Z"},{"alias_kind":"arxiv_version","alias_value":"1709.01308v3","created_at":"2026-05-18T00:23:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.01308","created_at":"2026-05-18T00:23:53Z"},{"alias_kind":"pith_short_12","alias_value":"MBT77DSWYCDT","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"MBT77DSWYCDTFZUO","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"MBT77DSW","created_at":"2026-05-18T12:31:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:MBT77DSWYCDTFZUO343CUGL434","target":"record","payload":{"canonical_record":{"source":{"id":"1709.01308","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-05T09:47:41Z","cross_cats_sorted":[],"title_canon_sha256":"56fd0ffe34d21bb594d900905b85918469d691d3c7228b37d81e00487bdca82f","abstract_canon_sha256":"af6d97aaf28b8cad92fbb5e7a1e7b2262d24d16bf77c62dd628180cbbc3df154"},"schema_version":"1.0"},"canonical_sha256":"6067ff8e56c08732e68edf362a197cdf2d5b2788630c6e05cd69ea355c48fc59","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:53.082455Z","signature_b64":"bVTNDP3c+lheS+RNfcHQwFDxGmUtTfRqNxEmNR3dYwa9+lmcSExWJzar/H4Cv6bb+xl/rqYtV6JLyejZ0y32CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6067ff8e56c08732e68edf362a197cdf2d5b2788630c6e05cd69ea355c48fc59","last_reissued_at":"2026-05-18T00:23:53.081859Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:53.081859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.01308","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:23:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WMV0a9cQQjOV7VbaART5sTSMNRqYevA95K/h1uXLff0NTipDpQ1fshL7yDu2ONIvVCELp90yO5/EkoRIzWnMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T19:56:32.687856Z"},"content_sha256":"84d7fa04ea304df34b5d4003ba03f2cf65dba435733a674f52735a9ff9b24a13","schema_version":"1.0","event_id":"sha256:84d7fa04ea304df34b5d4003ba03f2cf65dba435733a674f52735a9ff9b24a13"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:MBT77DSWYCDTFZUO343CUGL434","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BOOK: Storing Algorithm-Invariant Episodes for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jaeseok Choi, Nojun Kwak, Simyung Chang, Youngjoon Yoo","submitted_at":"2017-09-05T09:47:41Z","abstract_excerpt":"We introduce a novel method to train agents of reinforcement learning (RL) by sharing knowledge in a way similar to the concept of using a book. The recorded information in the form of a book is the main means by which humans learn knowledge. Nevertheless, the conventional deep RL methods have mainly focused either on experiential learning where the agent learns through interactions with the environment from the start or on imitation learning that tries to mimic the teacher. Contrary to these, our proposed book learning shares key information among different agents in a book-like manner by del"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.01308","kind":"arxiv","version":3},"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":"2026-05-18T00:23:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"foEB5gVgJ5NFtijPz13g+NafyiljJs49hVbguus6XDumPOkncNmzuuMa3ZS60DVoG0W1+LyXg/BYkiSiadUDCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T19:56:32.688200Z"},"content_sha256":"7d8aa1e00c0576cb40e7b5903876bed9604b75facf27e28d91aca78037d7b5f3","schema_version":"1.0","event_id":"sha256:7d8aa1e00c0576cb40e7b5903876bed9604b75facf27e28d91aca78037d7b5f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MBT77DSWYCDTFZUO343CUGL434/bundle.json","state_url":"https://pith.science/pith/MBT77DSWYCDTFZUO343CUGL434/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MBT77DSWYCDTFZUO343CUGL434/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":"2026-06-27T19:56:32Z","links":{"resolver":"https://pith.science/pith/MBT77DSWYCDTFZUO343CUGL434","bundle":"https://pith.science/pith/MBT77DSWYCDTFZUO343CUGL434/bundle.json","state":"https://pith.science/pith/MBT77DSWYCDTFZUO343CUGL434/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MBT77DSWYCDTFZUO343CUGL434/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:MBT77DSWYCDTFZUO343CUGL434","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":"af6d97aaf28b8cad92fbb5e7a1e7b2262d24d16bf77c62dd628180cbbc3df154","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-05T09:47:41Z","title_canon_sha256":"56fd0ffe34d21bb594d900905b85918469d691d3c7228b37d81e00487bdca82f"},"schema_version":"1.0","source":{"id":"1709.01308","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.01308","created_at":"2026-05-18T00:23:53Z"},{"alias_kind":"arxiv_version","alias_value":"1709.01308v3","created_at":"2026-05-18T00:23:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.01308","created_at":"2026-05-18T00:23:53Z"},{"alias_kind":"pith_short_12","alias_value":"MBT77DSWYCDT","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"MBT77DSWYCDTFZUO","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"MBT77DSW","created_at":"2026-05-18T12:31:31Z"}],"graph_snapshots":[{"event_id":"sha256:7d8aa1e00c0576cb40e7b5903876bed9604b75facf27e28d91aca78037d7b5f3","target":"graph","created_at":"2026-05-18T00:23:53Z","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 novel method to train agents of reinforcement learning (RL) by sharing knowledge in a way similar to the concept of using a book. The recorded information in the form of a book is the main means by which humans learn knowledge. Nevertheless, the conventional deep RL methods have mainly focused either on experiential learning where the agent learns through interactions with the environment from the start or on imitation learning that tries to mimic the teacher. Contrary to these, our proposed book learning shares key information among different agents in a book-like manner by del","authors_text":"Jaeseok Choi, Nojun Kwak, Simyung Chang, Youngjoon Yoo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-05T09:47:41Z","title":"BOOK: Storing Algorithm-Invariant Episodes for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.01308","kind":"arxiv","version":3},"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":"sha256:84d7fa04ea304df34b5d4003ba03f2cf65dba435733a674f52735a9ff9b24a13","target":"record","created_at":"2026-05-18T00:23:53Z","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":"af6d97aaf28b8cad92fbb5e7a1e7b2262d24d16bf77c62dd628180cbbc3df154","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-05T09:47:41Z","title_canon_sha256":"56fd0ffe34d21bb594d900905b85918469d691d3c7228b37d81e00487bdca82f"},"schema_version":"1.0","source":{"id":"1709.01308","kind":"arxiv","version":3}},"canonical_sha256":"6067ff8e56c08732e68edf362a197cdf2d5b2788630c6e05cd69ea355c48fc59","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6067ff8e56c08732e68edf362a197cdf2d5b2788630c6e05cd69ea355c48fc59","first_computed_at":"2026-05-18T00:23:53.081859Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:23:53.081859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bVTNDP3c+lheS+RNfcHQwFDxGmUtTfRqNxEmNR3dYwa9+lmcSExWJzar/H4Cv6bb+xl/rqYtV6JLyejZ0y32CA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:23:53.082455Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.01308","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84d7fa04ea304df34b5d4003ba03f2cf65dba435733a674f52735a9ff9b24a13","sha256:7d8aa1e00c0576cb40e7b5903876bed9604b75facf27e28d91aca78037d7b5f3"],"state_sha256":"80788b845f3f4498709d28ba5337316e3e05d3c662908d9d890bc59bce7ea233"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7kvmaAH3PZBNIsoJdFFQZRbTX40VuxAxVlAI1QQIetb7IemfBCTsB/5Pfsy7nQPG+9Q4l3Jmn+xgQxsccWwzAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T19:56:32.690034Z","bundle_sha256":"ab86f7debefb1dfdc6bb09a0030f4508c298ab67cc50fb6e50eb5b09754180cb"}}