{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:MFNPCOFE3GWS4N4WRTUKA63GKB","short_pith_number":"pith:MFNPCOFE","schema_version":"1.0","canonical_sha256":"615af138a4d9ad2e37968ce8a07b665046e36d966d51d238e8b1f8ea585470f8","source":{"kind":"arxiv","id":"2012.01736","version":1},"attestation_state":"computed","paper":{"title":"Designing a Prospective COVID-19 Therapeutic with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Alexandre Laterre, Amine Kerkeni, Joe Phillips, Karim Beguir, Marcin J. Skwark, Nicol\\'as L\\'opez Carranza, Slim Said, Thomas Pierrot, U\\u{g}ur \\c{S}ahin","submitted_at":"2020-12-03T07:35:38Z","abstract_excerpt":"The SARS-CoV-2 pandemic has created a global race for a cure. One approach focuses on designing a novel variant of the human angiotensin-converting enzyme 2 (ACE2) that binds more tightly to the SARS-CoV-2 spike protein and diverts it from human cells. Here we formulate a novel protein design framework as a reinforcement learning problem. We generate new designs efficiently through the combination of a fast, biologically-grounded reward function and sequential action-space formulation. The use of Policy Gradients reduces the compute budget needed to reach consistent, high-quality designs by at"},"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":"2012.01736","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.BM","submitted_at":"2020-12-03T07:35:38Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"14f4f2827e5dddbac618fc8213b8ed1520fc3d7a82e91d251dea4c977320c1c9","abstract_canon_sha256":"049516809268d68dbf4b1fa25d6e2434dd8a6139d24594e1765898b6f3b7112e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:56:49.501247Z","signature_b64":"So1Bh3x0bGf5hNPU03TuaV46iVgUMErDo5fkXvFkiMu00aBFC/r8+bYF9K+xOWuS74NL8lT/diFJFyt5UarcDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"615af138a4d9ad2e37968ce8a07b665046e36d966d51d238e8b1f8ea585470f8","last_reissued_at":"2026-07-05T01:56:49.500785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:56:49.500785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Designing a Prospective COVID-19 Therapeutic with Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Alexandre Laterre, Amine Kerkeni, Joe Phillips, Karim Beguir, Marcin J. Skwark, Nicol\\'as L\\'opez Carranza, Slim Said, Thomas Pierrot, U\\u{g}ur \\c{S}ahin","submitted_at":"2020-12-03T07:35:38Z","abstract_excerpt":"The SARS-CoV-2 pandemic has created a global race for a cure. One approach focuses on designing a novel variant of the human angiotensin-converting enzyme 2 (ACE2) that binds more tightly to the SARS-CoV-2 spike protein and diverts it from human cells. Here we formulate a novel protein design framework as a reinforcement learning problem. We generate new designs efficiently through the combination of a fast, biologically-grounded reward function and sequential action-space formulation. The use of Policy Gradients reduces the compute budget needed to reach consistent, high-quality designs by at"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.01736","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/2012.01736/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":"2012.01736","created_at":"2026-07-05T01:56:49.500839+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.01736v1","created_at":"2026-07-05T01:56:49.500839+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.01736","created_at":"2026-07-05T01:56:49.500839+00:00"},{"alias_kind":"pith_short_12","alias_value":"MFNPCOFE3GWS","created_at":"2026-07-05T01:56:49.500839+00:00"},{"alias_kind":"pith_short_16","alias_value":"MFNPCOFE3GWS4N4W","created_at":"2026-07-05T01:56:49.500839+00:00"},{"alias_kind":"pith_short_8","alias_value":"MFNPCOFE","created_at":"2026-07-05T01:56:49.500839+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/MFNPCOFE3GWS4N4WRTUKA63GKB","json":"https://pith.science/pith/MFNPCOFE3GWS4N4WRTUKA63GKB.json","graph_json":"https://pith.science/api/pith-number/MFNPCOFE3GWS4N4WRTUKA63GKB/graph.json","events_json":"https://pith.science/api/pith-number/MFNPCOFE3GWS4N4WRTUKA63GKB/events.json","paper":"https://pith.science/paper/MFNPCOFE"},"agent_actions":{"view_html":"https://pith.science/pith/MFNPCOFE3GWS4N4WRTUKA63GKB","download_json":"https://pith.science/pith/MFNPCOFE3GWS4N4WRTUKA63GKB.json","view_paper":"https://pith.science/paper/MFNPCOFE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.01736&json=true","fetch_graph":"https://pith.science/api/pith-number/MFNPCOFE3GWS4N4WRTUKA63GKB/graph.json","fetch_events":"https://pith.science/api/pith-number/MFNPCOFE3GWS4N4WRTUKA63GKB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MFNPCOFE3GWS4N4WRTUKA63GKB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MFNPCOFE3GWS4N4WRTUKA63GKB/action/storage_attestation","attest_author":"https://pith.science/pith/MFNPCOFE3GWS4N4WRTUKA63GKB/action/author_attestation","sign_citation":"https://pith.science/pith/MFNPCOFE3GWS4N4WRTUKA63GKB/action/citation_signature","submit_replication":"https://pith.science/pith/MFNPCOFE3GWS4N4WRTUKA63GKB/action/replication_record"}},"created_at":"2026-07-05T01:56:49.500839+00:00","updated_at":"2026-07-05T01:56:49.500839+00:00"}