{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:HILLI4F2LEQVXXLLBZFJW53I3Q","short_pith_number":"pith:HILLI4F2","schema_version":"1.0","canonical_sha256":"3a16b470ba59215bdd6b0e4a9b7768dc2b2f12db3e3a2a9f9c52b0672a646ffa","source":{"kind":"arxiv","id":"1811.00260","version":5},"attestation_state":"computed","paper":{"title":"Horizon: Facebook's Open Source Applied Reinforcement Learning Platform","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Edoardo Conti, Jason Gauci, Kittipat Virochsiri, Scott Fujimoto, Vivek Narayanan, Xiaohui Ye, Yitao Liang, Yuchen He, Zachary Kaden, Zhengxing Chen","submitted_at":"2018-11-01T07:02:45Z","abstract_excerpt":"In this paper we present Horizon, Facebook's open source applied reinforcement learning (RL) platform. Horizon is an end-to-end platform designed to solve industry applied RL problems where datasets are large (millions to billions of observations), the feedback loop is slow (vs. a simulator), and experiments must be done with care because they don't run in a simulator. Unlike other RL platforms, which are often designed for fast prototyping and experimentation, Horizon is designed with production use cases as top of mind. The platform contains workflows to train popular deep RL algorithms and "},"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":"1811.00260","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-01T07:02:45Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"baae4da2ea278d0e218d738c68733467fdf01ccffe4d23b73531723fc4f1afa2","abstract_canon_sha256":"af0bae43d939214d9cdc83f2d1327ce45258a43056b04921632eaa9aff83c70e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:02:24.227180Z","signature_b64":"5NChze1Ne3VzBaAZcehf/4WXCWbvC57Vl22qvz6ZeIS5fUD9wRQ7wgZflEBHZPmsyf3Z63JDsBbsp3HyWDxqDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a16b470ba59215bdd6b0e4a9b7768dc2b2f12db3e3a2a9f9c52b0672a646ffa","last_reissued_at":"2026-07-05T00:02:24.226725Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:02:24.226725Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Horizon: Facebook's Open Source Applied Reinforcement Learning Platform","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Edoardo Conti, Jason Gauci, Kittipat Virochsiri, Scott Fujimoto, Vivek Narayanan, Xiaohui Ye, Yitao Liang, Yuchen He, Zachary Kaden, Zhengxing Chen","submitted_at":"2018-11-01T07:02:45Z","abstract_excerpt":"In this paper we present Horizon, Facebook's open source applied reinforcement learning (RL) platform. Horizon is an end-to-end platform designed to solve industry applied RL problems where datasets are large (millions to billions of observations), the feedback loop is slow (vs. a simulator), and experiments must be done with care because they don't run in a simulator. Unlike other RL platforms, which are often designed for fast prototyping and experimentation, Horizon is designed with production use cases as top of mind. The platform contains workflows to train popular deep RL algorithms and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00260","kind":"arxiv","version":5},"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/1811.00260/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":"1811.00260","created_at":"2026-07-05T00:02:24.226777+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.00260v5","created_at":"2026-07-05T00:02:24.226777+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00260","created_at":"2026-07-05T00:02:24.226777+00:00"},{"alias_kind":"pith_short_12","alias_value":"HILLI4F2LEQV","created_at":"2026-07-05T00:02:24.226777+00:00"},{"alias_kind":"pith_short_16","alias_value":"HILLI4F2LEQVXXLL","created_at":"2026-07-05T00:02:24.226777+00:00"},{"alias_kind":"pith_short_8","alias_value":"HILLI4F2","created_at":"2026-07-05T00:02:24.226777+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1910.01708","citing_title":"Benchmarking Batch Deep Reinforcement Learning Algorithms","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HILLI4F2LEQVXXLLBZFJW53I3Q","json":"https://pith.science/pith/HILLI4F2LEQVXXLLBZFJW53I3Q.json","graph_json":"https://pith.science/api/pith-number/HILLI4F2LEQVXXLLBZFJW53I3Q/graph.json","events_json":"https://pith.science/api/pith-number/HILLI4F2LEQVXXLLBZFJW53I3Q/events.json","paper":"https://pith.science/paper/HILLI4F2"},"agent_actions":{"view_html":"https://pith.science/pith/HILLI4F2LEQVXXLLBZFJW53I3Q","download_json":"https://pith.science/pith/HILLI4F2LEQVXXLLBZFJW53I3Q.json","view_paper":"https://pith.science/paper/HILLI4F2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.00260&json=true","fetch_graph":"https://pith.science/api/pith-number/HILLI4F2LEQVXXLLBZFJW53I3Q/graph.json","fetch_events":"https://pith.science/api/pith-number/HILLI4F2LEQVXXLLBZFJW53I3Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HILLI4F2LEQVXXLLBZFJW53I3Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HILLI4F2LEQVXXLLBZFJW53I3Q/action/storage_attestation","attest_author":"https://pith.science/pith/HILLI4F2LEQVXXLLBZFJW53I3Q/action/author_attestation","sign_citation":"https://pith.science/pith/HILLI4F2LEQVXXLLBZFJW53I3Q/action/citation_signature","submit_replication":"https://pith.science/pith/HILLI4F2LEQVXXLLBZFJW53I3Q/action/replication_record"}},"created_at":"2026-07-05T00:02:24.226777+00:00","updated_at":"2026-07-05T00:02:24.226777+00:00"}