{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:X4U4FKX725TCLNAL4IONULQMRZ","short_pith_number":"pith:X4U4FKX7","schema_version":"1.0","canonical_sha256":"bf29c2aaffd76625b40be21cda2e0c8e77a9895bce3633125e3f573c0a5cc225","source":{"kind":"arxiv","id":"1912.04242","version":1},"attestation_state":"computed","paper":{"title":"Adversarial recovery of agent rewards from latent spaces of the limit order book","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-fin.TR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jacobo Roa-Vicens, Ricardo Silva, Virgile Mison, Yarin Gal, Yuanbo Wang","submitted_at":"2019-12-09T18:32:12Z","abstract_excerpt":"Inverse reinforcement learning has proved its ability to explain state-action trajectories of expert agents by recovering their underlying reward functions in increasingly challenging environments. Recent advances in adversarial learning have allowed extending inverse RL to applications with non-stationary environment dynamics unknown to the agents, arbitrary structures of reward functions and improved handling of the ambiguities inherent to the ill-posed nature of inverse RL. This is particularly relevant in real time applications on stochastic environments involving risk, like volatile finan"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1912.04242","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-09T18:32:12Z","cross_cats_sorted":["q-fin.TR","stat.ML"],"title_canon_sha256":"638121f43f8a1718fa89b00b8783c1e297c2b7092fc9ebc189f8d3c2ef5e5c73","abstract_canon_sha256":"5ba7c9f8a2108271764ad7caacd87fbe4da33a8986bec70b0b00b827b684f5a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:24:53.142883Z","signature_b64":"kr06MuKPHyxtep0Cjdd0uEs6AMmAwU++q9iAeXb6SfnnbmrFHow1UatWDfMf39Iq7H9uXZygK8lLY0+vXSqqBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf29c2aaffd76625b40be21cda2e0c8e77a9895bce3633125e3f573c0a5cc225","last_reissued_at":"2026-07-05T00:24:53.142473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:24:53.142473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial recovery of agent rewards from latent spaces of the limit order book","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-fin.TR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jacobo Roa-Vicens, Ricardo Silva, Virgile Mison, Yarin Gal, Yuanbo Wang","submitted_at":"2019-12-09T18:32:12Z","abstract_excerpt":"Inverse reinforcement learning has proved its ability to explain state-action trajectories of expert agents by recovering their underlying reward functions in increasingly challenging environments. Recent advances in adversarial learning have allowed extending inverse RL to applications with non-stationary environment dynamics unknown to the agents, arbitrary structures of reward functions and improved handling of the ambiguities inherent to the ill-posed nature of inverse RL. This is particularly relevant in real time applications on stochastic environments involving risk, like volatile finan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.04242","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/1912.04242/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1912.04242","created_at":"2026-07-05T00:24:53.142536+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.04242v1","created_at":"2026-07-05T00:24:53.142536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.04242","created_at":"2026-07-05T00:24:53.142536+00:00"},{"alias_kind":"pith_short_12","alias_value":"X4U4FKX725TC","created_at":"2026-07-05T00:24:53.142536+00:00"},{"alias_kind":"pith_short_16","alias_value":"X4U4FKX725TCLNAL","created_at":"2026-07-05T00:24:53.142536+00:00"},{"alias_kind":"pith_short_8","alias_value":"X4U4FKX7","created_at":"2026-07-05T00:24:53.142536+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X4U4FKX725TCLNAL4IONULQMRZ","json":"https://pith.science/pith/X4U4FKX725TCLNAL4IONULQMRZ.json","graph_json":"https://pith.science/api/pith-number/X4U4FKX725TCLNAL4IONULQMRZ/graph.json","events_json":"https://pith.science/api/pith-number/X4U4FKX725TCLNAL4IONULQMRZ/events.json","paper":"https://pith.science/paper/X4U4FKX7"},"agent_actions":{"view_html":"https://pith.science/pith/X4U4FKX725TCLNAL4IONULQMRZ","download_json":"https://pith.science/pith/X4U4FKX725TCLNAL4IONULQMRZ.json","view_paper":"https://pith.science/paper/X4U4FKX7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.04242&json=true","fetch_graph":"https://pith.science/api/pith-number/X4U4FKX725TCLNAL4IONULQMRZ/graph.json","fetch_events":"https://pith.science/api/pith-number/X4U4FKX725TCLNAL4IONULQMRZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X4U4FKX725TCLNAL4IONULQMRZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X4U4FKX725TCLNAL4IONULQMRZ/action/storage_attestation","attest_author":"https://pith.science/pith/X4U4FKX725TCLNAL4IONULQMRZ/action/author_attestation","sign_citation":"https://pith.science/pith/X4U4FKX725TCLNAL4IONULQMRZ/action/citation_signature","submit_replication":"https://pith.science/pith/X4U4FKX725TCLNAL4IONULQMRZ/action/replication_record"}},"created_at":"2026-07-05T00:24:53.142536+00:00","updated_at":"2026-07-05T00:24:53.142536+00:00"}