{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:YOMK2UOGSNL3SNK2UADPFIDV4T","short_pith_number":"pith:YOMK2UOG","canonical_record":{"source":{"id":"1910.03743","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-10-09T01:42:27Z","cross_cats_sorted":[],"title_canon_sha256":"345b27323bd56a7623f767705bfa4b2699075addc4814aa0c10a31fcef600be1","abstract_canon_sha256":"0689a40603b6fd6172e94fe1e4ef15e4987e590f3aa454144740acf370f61fe1"},"schema_version":"1.0"},"canonical_sha256":"c398ad51c69357b9355aa006f2a075e4d5d2e4ed26d01ab9d3f75fbf310e8447","source":{"kind":"arxiv","id":"1910.03743","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.03743","created_at":"2026-07-05T00:10:57Z"},{"alias_kind":"arxiv_version","alias_value":"1910.03743v1","created_at":"2026-07-05T00:10:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.03743","created_at":"2026-07-05T00:10:57Z"},{"alias_kind":"pith_short_12","alias_value":"YOMK2UOGSNL3","created_at":"2026-07-05T00:10:57Z"},{"alias_kind":"pith_short_16","alias_value":"YOMK2UOGSNL3SNK2","created_at":"2026-07-05T00:10:57Z"},{"alias_kind":"pith_short_8","alias_value":"YOMK2UOG","created_at":"2026-07-05T00:10:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:YOMK2UOGSNL3SNK2UADPFIDV4T","target":"record","payload":{"canonical_record":{"source":{"id":"1910.03743","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-10-09T01:42:27Z","cross_cats_sorted":[],"title_canon_sha256":"345b27323bd56a7623f767705bfa4b2699075addc4814aa0c10a31fcef600be1","abstract_canon_sha256":"0689a40603b6fd6172e94fe1e4ef15e4987e590f3aa454144740acf370f61fe1"},"schema_version":"1.0"},"canonical_sha256":"c398ad51c69357b9355aa006f2a075e4d5d2e4ed26d01ab9d3f75fbf310e8447","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:10:57.515756Z","signature_b64":"xS/2SrDeCszYDD97YfS2ABCS5CDySGJvjSgabPtzptQutrB5NUkwc2Lq+I3E/dHx7GCVjCzKdxQ+sunZCtwHCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c398ad51c69357b9355aa006f2a075e4d5d2e4ed26d01ab9d3f75fbf310e8447","last_reissued_at":"2026-07-05T00:10:57.515249Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:10:57.515249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.03743","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":"2026-07-05T00:10:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KoXeQhS82aMLr+RiC+Uf5CLVSJDFAkQoA3O32uK1OlTXr8BdRuZinV8jNnpoZxte8h1N4gdP5dpBGYLhbokoBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T21:50:39.458957Z"},"content_sha256":"f027212b2379b6479bd60dbb752338332c6ff08d4908c083afe71ee5226ad00e","schema_version":"1.0","event_id":"sha256:f027212b2379b6479bd60dbb752338332c6ff08d4908c083afe71ee5226ad00e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:YOMK2UOGSNL3SNK2UADPFIDV4T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model-based Reinforcement Learning for Predictions and Control for Limit Order Books","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Haoran Wei, Keith Decker, Lidia Mangu, Yuanbo Wang","submitted_at":"2019-10-09T01:42:27Z","abstract_excerpt":"We build a profitable electronic trading agent with Reinforcement Learning that places buy and sell orders in the stock market. An environment model is built only with historical observational data, and the RL agent learns the trading policy by interacting with the environment model instead of with the real-market to minimize the risk and potential monetary loss. Trained in unsupervised and self-supervised fashion, our environment model learned a temporal and causal representation of the market in latent space through deep neural networks. We demonstrate that the trading policy trained entirel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.03743","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1910.03743/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":"2026-07-05T00:10:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ym39jexAskfb+c7T8/qh28S6ackHESDfFPO0LPsp+GFfiqkH/rYvc9HwUfo8fJ5IZBiIa4A95ZTo3YMUBqdmAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T21:50:39.460096Z"},"content_sha256":"37c5d0afe2da627b0f5f72683e68779f3ae806f4809971c9b2bc53549a2543cc","schema_version":"1.0","event_id":"sha256:37c5d0afe2da627b0f5f72683e68779f3ae806f4809971c9b2bc53549a2543cc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YOMK2UOGSNL3SNK2UADPFIDV4T/bundle.json","state_url":"https://pith.science/pith/YOMK2UOGSNL3SNK2UADPFIDV4T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YOMK2UOGSNL3SNK2UADPFIDV4T/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":"2026-08-11T21:50:39Z","links":{"resolver":"https://pith.science/pith/YOMK2UOGSNL3SNK2UADPFIDV4T","bundle":"https://pith.science/pith/YOMK2UOGSNL3SNK2UADPFIDV4T/bundle.json","state":"https://pith.science/pith/YOMK2UOGSNL3SNK2UADPFIDV4T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YOMK2UOGSNL3SNK2UADPFIDV4T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:YOMK2UOGSNL3SNK2UADPFIDV4T","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":"0689a40603b6fd6172e94fe1e4ef15e4987e590f3aa454144740acf370f61fe1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-10-09T01:42:27Z","title_canon_sha256":"345b27323bd56a7623f767705bfa4b2699075addc4814aa0c10a31fcef600be1"},"schema_version":"1.0","source":{"id":"1910.03743","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.03743","created_at":"2026-07-05T00:10:57Z"},{"alias_kind":"arxiv_version","alias_value":"1910.03743v1","created_at":"2026-07-05T00:10:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.03743","created_at":"2026-07-05T00:10:57Z"},{"alias_kind":"pith_short_12","alias_value":"YOMK2UOGSNL3","created_at":"2026-07-05T00:10:57Z"},{"alias_kind":"pith_short_16","alias_value":"YOMK2UOGSNL3SNK2","created_at":"2026-07-05T00:10:57Z"},{"alias_kind":"pith_short_8","alias_value":"YOMK2UOG","created_at":"2026-07-05T00:10:57Z"}],"graph_snapshots":[{"event_id":"sha256:37c5d0afe2da627b0f5f72683e68779f3ae806f4809971c9b2bc53549a2543cc","target":"graph","created_at":"2026-07-05T00:10:57Z","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/1910.03743/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We build a profitable electronic trading agent with Reinforcement Learning that places buy and sell orders in the stock market. An environment model is built only with historical observational data, and the RL agent learns the trading policy by interacting with the environment model instead of with the real-market to minimize the risk and potential monetary loss. Trained in unsupervised and self-supervised fashion, our environment model learned a temporal and causal representation of the market in latent space through deep neural networks. We demonstrate that the trading policy trained entirel","authors_text":"Haoran Wei, Keith Decker, Lidia Mangu, Yuanbo Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-10-09T01:42:27Z","title":"Model-based Reinforcement Learning for Predictions and Control for Limit Order Books"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.03743","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:f027212b2379b6479bd60dbb752338332c6ff08d4908c083afe71ee5226ad00e","target":"record","created_at":"2026-07-05T00:10:57Z","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":"0689a40603b6fd6172e94fe1e4ef15e4987e590f3aa454144740acf370f61fe1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-10-09T01:42:27Z","title_canon_sha256":"345b27323bd56a7623f767705bfa4b2699075addc4814aa0c10a31fcef600be1"},"schema_version":"1.0","source":{"id":"1910.03743","kind":"arxiv","version":1}},"canonical_sha256":"c398ad51c69357b9355aa006f2a075e4d5d2e4ed26d01ab9d3f75fbf310e8447","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c398ad51c69357b9355aa006f2a075e4d5d2e4ed26d01ab9d3f75fbf310e8447","first_computed_at":"2026-07-05T00:10:57.515249Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:10:57.515249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xS/2SrDeCszYDD97YfS2ABCS5CDySGJvjSgabPtzptQutrB5NUkwc2Lq+I3E/dHx7GCVjCzKdxQ+sunZCtwHCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:10:57.515756Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.03743","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f027212b2379b6479bd60dbb752338332c6ff08d4908c083afe71ee5226ad00e","sha256:37c5d0afe2da627b0f5f72683e68779f3ae806f4809971c9b2bc53549a2543cc"],"state_sha256":"b94731f780d0ed609143fea1ea7786f6cb2a08815bcad4c81ddcb89fabf6e221"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n3MfFqAqBaX6v2+Ofuo+OqRImQbKbtuI9NI0fvmVMRnikZ2SNUPNX2m50V6LbBDaucSg9hymSKxUiNsc9ezECg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T21:50:39.466546Z","bundle_sha256":"50d757a7d1208703941926cd88b2a110e6eaf4a85a7fe5677793388ae3aca246"}}