{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:GDCBZB2RKCAQHRQJ3LBIZNES32","short_pith_number":"pith:GDCBZB2R","canonical_record":{"source":{"id":"1907.08040","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-18T13:16:39Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"294961d589c74818710a5da238e0ab345e05e5498a1c07fd9b7633423ff24309","abstract_canon_sha256":"f33a3f19aadc8329a70b30f4c25373bc8d7a1fadfed143da78e725d306a09364"},"schema_version":"1.0"},"canonical_sha256":"30c41c8751508103c609dac28cb492de9c2fd743a490242d90cabf7883355f33","source":{"kind":"arxiv","id":"1907.08040","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.08040","created_at":"2026-05-17T23:40:15Z"},{"alias_kind":"arxiv_version","alias_value":"1907.08040v1","created_at":"2026-05-17T23:40:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.08040","created_at":"2026-05-17T23:40:15Z"},{"alias_kind":"pith_short_12","alias_value":"GDCBZB2RKCAQ","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"GDCBZB2RKCAQHRQJ","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"GDCBZB2R","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:GDCBZB2RKCAQHRQJ3LBIZNES32","target":"record","payload":{"canonical_record":{"source":{"id":"1907.08040","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-18T13:16:39Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"294961d589c74818710a5da238e0ab345e05e5498a1c07fd9b7633423ff24309","abstract_canon_sha256":"f33a3f19aadc8329a70b30f4c25373bc8d7a1fadfed143da78e725d306a09364"},"schema_version":"1.0"},"canonical_sha256":"30c41c8751508103c609dac28cb492de9c2fd743a490242d90cabf7883355f33","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:15.333962Z","signature_b64":"oR9sLs2zhKaI/XaNq5SEYuG2OcGLQROjLJafyuoDGZbWbL1oyD0KWoMIbVehB5gn8t20REv8fauL7rP0u5o+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30c41c8751508103c609dac28cb492de9c2fd743a490242d90cabf7883355f33","last_reissued_at":"2026-05-17T23:40:15.333176Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:15.333176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.08040","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":"2026-05-17T23:40:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QeWIGd6GgpAQNpryr5MHQqf7MwDU62TLgFwPHrXt0VKHeB5HtNpV+GO+2yzeqw5xS470eBlgpRMLKV4qdJPDDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T15:05:16.528820Z"},"content_sha256":"16a75a62cf1f6d441af7a23352f58de29920e80f776bf42d0df93a2a8fbbf045","schema_version":"1.0","event_id":"sha256:16a75a62cf1f6d441af7a23352f58de29920e80f776bf42d0df93a2a8fbbf045"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:GDCBZB2RKCAQHRQJ3LBIZNES32","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Convolutional Reservoir Computing for World Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hanten Chang, Katsuya Futagami","submitted_at":"2019-07-18T13:16:39Z","abstract_excerpt":"Recently, reinforcement learning models have achieved great success, completing complex tasks such as mastering Go and other games with higher scores than human players. Many of these models collect considerable data on the tasks and improve accuracy by extracting visual and time-series features using convolutional neural networks (CNNs) and recurrent neural networks, respectively. However, these networks have very high computational costs because they need to be trained by repeatedly using a large volume of past playing data. In this study, we propose a novel practical approach called reinfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.08040","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":"2026-05-17T23:40:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sWAIwKENNa3ojmLTF8gfzjUwYd/IF1YufVzxmgP8nWI5nw1XlhTRIw861L2Cfex1HZM29eSr3Movv1c00P2CAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T15:05:16.529472Z"},"content_sha256":"3d58058a198b4983f4bae16ee03873153578f4721d732077b0199ccc035becaa","schema_version":"1.0","event_id":"sha256:3d58058a198b4983f4bae16ee03873153578f4721d732077b0199ccc035becaa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GDCBZB2RKCAQHRQJ3LBIZNES32/bundle.json","state_url":"https://pith.science/pith/GDCBZB2RKCAQHRQJ3LBIZNES32/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GDCBZB2RKCAQHRQJ3LBIZNES32/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":"2026-05-25T15:05:16Z","links":{"resolver":"https://pith.science/pith/GDCBZB2RKCAQHRQJ3LBIZNES32","bundle":"https://pith.science/pith/GDCBZB2RKCAQHRQJ3LBIZNES32/bundle.json","state":"https://pith.science/pith/GDCBZB2RKCAQHRQJ3LBIZNES32/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GDCBZB2RKCAQHRQJ3LBIZNES32/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:GDCBZB2RKCAQHRQJ3LBIZNES32","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":"f33a3f19aadc8329a70b30f4c25373bc8d7a1fadfed143da78e725d306a09364","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-18T13:16:39Z","title_canon_sha256":"294961d589c74818710a5da238e0ab345e05e5498a1c07fd9b7633423ff24309"},"schema_version":"1.0","source":{"id":"1907.08040","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.08040","created_at":"2026-05-17T23:40:15Z"},{"alias_kind":"arxiv_version","alias_value":"1907.08040v1","created_at":"2026-05-17T23:40:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.08040","created_at":"2026-05-17T23:40:15Z"},{"alias_kind":"pith_short_12","alias_value":"GDCBZB2RKCAQ","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"GDCBZB2RKCAQHRQJ","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"GDCBZB2R","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:3d58058a198b4983f4bae16ee03873153578f4721d732077b0199ccc035becaa","target":"graph","created_at":"2026-05-17T23:40:15Z","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":"Recently, reinforcement learning models have achieved great success, completing complex tasks such as mastering Go and other games with higher scores than human players. Many of these models collect considerable data on the tasks and improve accuracy by extracting visual and time-series features using convolutional neural networks (CNNs) and recurrent neural networks, respectively. However, these networks have very high computational costs because they need to be trained by repeatedly using a large volume of past playing data. In this study, we propose a novel practical approach called reinfor","authors_text":"Hanten Chang, Katsuya Futagami","cross_cats":["cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-18T13:16:39Z","title":"Convolutional Reservoir Computing for World Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.08040","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":"sha256:16a75a62cf1f6d441af7a23352f58de29920e80f776bf42d0df93a2a8fbbf045","target":"record","created_at":"2026-05-17T23:40:15Z","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":"f33a3f19aadc8329a70b30f4c25373bc8d7a1fadfed143da78e725d306a09364","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-18T13:16:39Z","title_canon_sha256":"294961d589c74818710a5da238e0ab345e05e5498a1c07fd9b7633423ff24309"},"schema_version":"1.0","source":{"id":"1907.08040","kind":"arxiv","version":1}},"canonical_sha256":"30c41c8751508103c609dac28cb492de9c2fd743a490242d90cabf7883355f33","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30c41c8751508103c609dac28cb492de9c2fd743a490242d90cabf7883355f33","first_computed_at":"2026-05-17T23:40:15.333176Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:40:15.333176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oR9sLs2zhKaI/XaNq5SEYuG2OcGLQROjLJafyuoDGZbWbL1oyD0KWoMIbVehB5gn8t20REv8fauL7rP0u5o+AQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:40:15.333962Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.08040","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16a75a62cf1f6d441af7a23352f58de29920e80f776bf42d0df93a2a8fbbf045","sha256:3d58058a198b4983f4bae16ee03873153578f4721d732077b0199ccc035becaa"],"state_sha256":"fd2b778ff31cfb3650bb9f5807e3deb717a921985601f867c06723219daa77db"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CEmvggAypSpyMzitSz0p3jaGuJPKwIvv7q3CTE9yUrtVc3RsDUWV5jq+4xmw/warxHOG9MBN86M1JylNzV3NCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T15:05:16.532887Z","bundle_sha256":"f325c931eb6b21cbdbf45bbd6432724f2181f00aae46663ef02de6d61bfb0d5a"}}