{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4Q3BY6NFF4HEBGU47OY622C54P","short_pith_number":"pith:4Q3BY6NF","schema_version":"1.0","canonical_sha256":"e4361c79a52f0e409a9cfbb1ed685de3df852b836821d824b0983097d1b8fb8c","source":{"kind":"arxiv","id":"2202.08137","version":2},"attestation_state":"computed","paper":{"title":"A data-driven approach for learning to control computers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adam Santoro, Alex Goldin, Alistair Muldal, David Raposo, Gregory Thornton, Josh Abramson, Peter C Humphreys, Petko Georgiev, Rachita Chhaparia, Timothy Lillicrap, Toby Pohlen","submitted_at":"2022-02-16T15:23:46Z","abstract_excerpt":"It would be useful for machines to use computers as humans do so that they can aid us in everyday tasks. This is a setting in which there is also the potential to leverage large-scale expert demonstrations and human judgements of interactive behaviour, which are two ingredients that have driven much recent success in AI. Here we investigate the setting of computer control using keyboard and mouse, with goals specified via natural language. Instead of focusing on hand-designed curricula and specialized action spaces, we focus on developing a scalable method centered on reinforcement learning co"},"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":"2202.08137","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-16T15:23:46Z","cross_cats_sorted":[],"title_canon_sha256":"ec8ccbda41789e5911a95d9c4107dbf8ce458842ab8f4dfe30c74ade2c06a545","abstract_canon_sha256":"095347bd2d238ea8ee9690a8e3577bb7fd3321f4de9f271cd456f266d2554227"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:09.719171Z","signature_b64":"/SnG5pjAzEsKRClpq1yALuXLS/phgdU1VYGLXNxrC/9/jJPcz9MKPacHCyRv78dyTOGEjMYRkbipvcitWmdLDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4361c79a52f0e409a9cfbb1ed685de3df852b836821d824b0983097d1b8fb8c","last_reissued_at":"2026-07-05T05:15:09.718728Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:09.718728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A data-driven approach for learning to control computers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adam Santoro, Alex Goldin, Alistair Muldal, David Raposo, Gregory Thornton, Josh Abramson, Peter C Humphreys, Petko Georgiev, Rachita Chhaparia, Timothy Lillicrap, Toby Pohlen","submitted_at":"2022-02-16T15:23:46Z","abstract_excerpt":"It would be useful for machines to use computers as humans do so that they can aid us in everyday tasks. This is a setting in which there is also the potential to leverage large-scale expert demonstrations and human judgements of interactive behaviour, which are two ingredients that have driven much recent success in AI. Here we investigate the setting of computer control using keyboard and mouse, with goals specified via natural language. Instead of focusing on hand-designed curricula and specialized action spaces, we focus on developing a scalable method centered on reinforcement learning co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.08137","kind":"arxiv","version":2},"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/2202.08137/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":"2202.08137","created_at":"2026-07-05T05:15:09.718801+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.08137v2","created_at":"2026-07-05T05:15:09.718801+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.08137","created_at":"2026-07-05T05:15:09.718801+00:00"},{"alias_kind":"pith_short_12","alias_value":"4Q3BY6NFF4HE","created_at":"2026-07-05T05:15:09.718801+00:00"},{"alias_kind":"pith_short_16","alias_value":"4Q3BY6NFF4HEBGU4","created_at":"2026-07-05T05:15:09.718801+00:00"},{"alias_kind":"pith_short_8","alias_value":"4Q3BY6NF","created_at":"2026-07-05T05:15:09.718801+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.00724","citing_title":"Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27955","citing_title":"GUI Agents with Reinforcement Learning: Toward Digital Inhabitants","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2204.01691","citing_title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4Q3BY6NFF4HEBGU47OY622C54P","json":"https://pith.science/pith/4Q3BY6NFF4HEBGU47OY622C54P.json","graph_json":"https://pith.science/api/pith-number/4Q3BY6NFF4HEBGU47OY622C54P/graph.json","events_json":"https://pith.science/api/pith-number/4Q3BY6NFF4HEBGU47OY622C54P/events.json","paper":"https://pith.science/paper/4Q3BY6NF"},"agent_actions":{"view_html":"https://pith.science/pith/4Q3BY6NFF4HEBGU47OY622C54P","download_json":"https://pith.science/pith/4Q3BY6NFF4HEBGU47OY622C54P.json","view_paper":"https://pith.science/paper/4Q3BY6NF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.08137&json=true","fetch_graph":"https://pith.science/api/pith-number/4Q3BY6NFF4HEBGU47OY622C54P/graph.json","fetch_events":"https://pith.science/api/pith-number/4Q3BY6NFF4HEBGU47OY622C54P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4Q3BY6NFF4HEBGU47OY622C54P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4Q3BY6NFF4HEBGU47OY622C54P/action/storage_attestation","attest_author":"https://pith.science/pith/4Q3BY6NFF4HEBGU47OY622C54P/action/author_attestation","sign_citation":"https://pith.science/pith/4Q3BY6NFF4HEBGU47OY622C54P/action/citation_signature","submit_replication":"https://pith.science/pith/4Q3BY6NFF4HEBGU47OY622C54P/action/replication_record"}},"created_at":"2026-07-05T05:15:09.718801+00:00","updated_at":"2026-07-05T05:15:09.718801+00:00"}