{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:TUZHS7GV3A3FYLNWGBZGMRFDDR","short_pith_number":"pith:TUZHS7GV","canonical_record":{"source":{"id":"1803.03916","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-11T06:56:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"43e0c0860170bc226a69ae1aceca6a1e30ec26455c81053e619da02abe11e6b7","abstract_canon_sha256":"6674033cc11bf5a2e364a435181d14764762050771b3717f1731283b56ba2821"},"schema_version":"1.0"},"canonical_sha256":"9d32797cd5d8365c2db630726644a31c7e27569dee42b6cc619ea5b829e1504c","source":{"kind":"arxiv","id":"1803.03916","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.03916","created_at":"2026-05-18T00:21:33Z"},{"alias_kind":"arxiv_version","alias_value":"1803.03916v1","created_at":"2026-05-18T00:21:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.03916","created_at":"2026-05-18T00:21:33Z"},{"alias_kind":"pith_short_12","alias_value":"TUZHS7GV3A3F","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"TUZHS7GV3A3FYLNW","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"TUZHS7GV","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:TUZHS7GV3A3FYLNWGBZGMRFDDR","target":"record","payload":{"canonical_record":{"source":{"id":"1803.03916","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-11T06:56:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"43e0c0860170bc226a69ae1aceca6a1e30ec26455c81053e619da02abe11e6b7","abstract_canon_sha256":"6674033cc11bf5a2e364a435181d14764762050771b3717f1731283b56ba2821"},"schema_version":"1.0"},"canonical_sha256":"9d32797cd5d8365c2db630726644a31c7e27569dee42b6cc619ea5b829e1504c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:21:33.474517Z","signature_b64":"5gtqZkbfqrFYJLketb68hSEieKkwVjAPMMXRd6OOxawUDIQETrVqvmhLOZ+QIMM3saJDLfOhutqBsWygkqBdAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d32797cd5d8365c2db630726644a31c7e27569dee42b6cc619ea5b829e1504c","last_reissued_at":"2026-05-18T00:21:33.473586Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:21:33.473586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.03916","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":"2026-05-18T00:21:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yiUUXOzYyOlN+LxsXxXPb9QhKk3SPDHDj/U42trRmH2pWF15uzNxZiJsl0B6xvGBazuGDrNyc1SDB2zrHTVPDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T08:40:41.505992Z"},"content_sha256":"8c35863384767c7751deb42db2f4fedeeff575e7b1dc7e9c47acec7c0ac91df0","schema_version":"1.0","event_id":"sha256:8c35863384767c7751deb42db2f4fedeeff575e7b1dc7e9c47acec7c0ac91df0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:TUZHS7GV3A3FYLNWGBZGMRFDDR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep reinforcement learning for time series: playing idealized trading games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Xiang Gao","submitted_at":"2018-03-11T06:56:29Z","abstract_excerpt":"Deep Q-learning is investigated as an end-to-end solution to estimate the optimal strategies for acting on time series input. Experiments are conducted on two idealized trading games. 1) Univariate: the only input is a wave-like price time series, and 2) Bivariate: the input includes a random stepwise price time series and a noisy signal time series, which is positively correlated with future price changes. The Univariate game tests whether the agent can capture the underlying dynamics, and the Bivariate game tests whether the agent can utilize the hidden relation among the inputs. Stacked Gat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.03916","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":"2026-05-18T00:21:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qx+3HxSidgVTlHEccmE8aQpxdBSdg9U+zFk3ZGA3if4G1XPMp+0tEW0SEfh2yeXqvQ3qi19J9HZfDe/0aDFaCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T08:40:41.506345Z"},"content_sha256":"bc7059eeaca4541d80a4e6ba195414c55e3c6f7488e71e679bb491e06bc4b1c5","schema_version":"1.0","event_id":"sha256:bc7059eeaca4541d80a4e6ba195414c55e3c6f7488e71e679bb491e06bc4b1c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TUZHS7GV3A3FYLNWGBZGMRFDDR/bundle.json","state_url":"https://pith.science/pith/TUZHS7GV3A3FYLNWGBZGMRFDDR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TUZHS7GV3A3FYLNWGBZGMRFDDR/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":"2026-06-01T08:40:41Z","links":{"resolver":"https://pith.science/pith/TUZHS7GV3A3FYLNWGBZGMRFDDR","bundle":"https://pith.science/pith/TUZHS7GV3A3FYLNWGBZGMRFDDR/bundle.json","state":"https://pith.science/pith/TUZHS7GV3A3FYLNWGBZGMRFDDR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TUZHS7GV3A3FYLNWGBZGMRFDDR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:TUZHS7GV3A3FYLNWGBZGMRFDDR","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":"6674033cc11bf5a2e364a435181d14764762050771b3717f1731283b56ba2821","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-11T06:56:29Z","title_canon_sha256":"43e0c0860170bc226a69ae1aceca6a1e30ec26455c81053e619da02abe11e6b7"},"schema_version":"1.0","source":{"id":"1803.03916","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.03916","created_at":"2026-05-18T00:21:33Z"},{"alias_kind":"arxiv_version","alias_value":"1803.03916v1","created_at":"2026-05-18T00:21:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.03916","created_at":"2026-05-18T00:21:33Z"},{"alias_kind":"pith_short_12","alias_value":"TUZHS7GV3A3F","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"TUZHS7GV3A3FYLNW","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"TUZHS7GV","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:bc7059eeaca4541d80a4e6ba195414c55e3c6f7488e71e679bb491e06bc4b1c5","target":"graph","created_at":"2026-05-18T00:21:33Z","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":"Deep Q-learning is investigated as an end-to-end solution to estimate the optimal strategies for acting on time series input. Experiments are conducted on two idealized trading games. 1) Univariate: the only input is a wave-like price time series, and 2) Bivariate: the input includes a random stepwise price time series and a noisy signal time series, which is positively correlated with future price changes. The Univariate game tests whether the agent can capture the underlying dynamics, and the Bivariate game tests whether the agent can utilize the hidden relation among the inputs. Stacked Gat","authors_text":"Xiang Gao","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-11T06:56:29Z","title":"Deep reinforcement learning for time series: playing idealized trading games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.03916","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":"sha256:8c35863384767c7751deb42db2f4fedeeff575e7b1dc7e9c47acec7c0ac91df0","target":"record","created_at":"2026-05-18T00:21:33Z","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":"6674033cc11bf5a2e364a435181d14764762050771b3717f1731283b56ba2821","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-11T06:56:29Z","title_canon_sha256":"43e0c0860170bc226a69ae1aceca6a1e30ec26455c81053e619da02abe11e6b7"},"schema_version":"1.0","source":{"id":"1803.03916","kind":"arxiv","version":1}},"canonical_sha256":"9d32797cd5d8365c2db630726644a31c7e27569dee42b6cc619ea5b829e1504c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d32797cd5d8365c2db630726644a31c7e27569dee42b6cc619ea5b829e1504c","first_computed_at":"2026-05-18T00:21:33.473586Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:21:33.473586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5gtqZkbfqrFYJLketb68hSEieKkwVjAPMMXRd6OOxawUDIQETrVqvmhLOZ+QIMM3saJDLfOhutqBsWygkqBdAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:21:33.474517Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.03916","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c35863384767c7751deb42db2f4fedeeff575e7b1dc7e9c47acec7c0ac91df0","sha256:bc7059eeaca4541d80a4e6ba195414c55e3c6f7488e71e679bb491e06bc4b1c5"],"state_sha256":"78b1d124698c9abf567bdd5b741a0d8d640a4284948564be0b92662efb157346"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MM2W/3FiJyPtNJ7t8FmhJWUJEuRmyGOmt5VQSiZjXEeLH0m4RfKmRoYuJQDNLtdvgck88N74s3vqKdsGDpVTBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T08:40:41.508257Z","bundle_sha256":"dc3b078d4a6faafb4abb547231ff93bab184ed60f794592ea540ff009865f1e6"}}