{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GRXXVAR3JSQKBOPOLY44MUQZ7G","short_pith_number":"pith:GRXXVAR3","schema_version":"1.0","canonical_sha256":"346f7a823b4ca0a0b9ee5e39c65219f98a5b806f17a1c5c246e5039d7b12f45c","source":{"kind":"arxiv","id":"2503.23766","version":1},"attestation_state":"computed","paper":{"title":"Accelerating High-Efficiency Organic Photovoltaic Discovery via Pretrained Graph Neural Networks and Generative Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fankun Zeng, Hao Zhang, Hou Hei Lam, Jiangjie Qiu, Siwei Fu, Wentao Li, Xiaonan Wang, Xiuyuan Hu","submitted_at":"2025-03-31T06:31:15Z","abstract_excerpt":"Organic photovoltaic (OPV) materials offer a promising avenue toward cost-effective solar energy utilization. However, optimizing donor-acceptor (D-A) combinations to achieve high power conversion efficiency (PCE) remains a significant challenge. In this work, we propose a framework that integrates large-scale pretraining of graph neural networks (GNNs) with a GPT-2 (Generative Pretrained Transformer 2)-based reinforcement learning (RL) strategy to design OPV molecules with potentially high PCE. This approach produces candidate molecules with predicted efficiencies approaching 21\\%, although f"},"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":"2503.23766","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-31T06:31:15Z","cross_cats_sorted":[],"title_canon_sha256":"8547862c3594b89f94ff9b7b5994e34fcd148b0977914ba35a3b3f9467952e09","abstract_canon_sha256":"b6e2e3096dd0fb8ee7462a747159b2324a3441eaf6c077ead0d1075ca45acb9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:59.528260Z","signature_b64":"edsB3tIPYybUAyk4IQVeD/FyPty7hcshf3zRR/7k/1xYBE0tRxA90cpaIeEvDib8g/bZL+2lXRQY4uWoSSCNBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"346f7a823b4ca0a0b9ee5e39c65219f98a5b806f17a1c5c246e5039d7b12f45c","last_reissued_at":"2026-07-05T10:41:59.527775Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:59.527775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerating High-Efficiency Organic Photovoltaic Discovery via Pretrained Graph Neural Networks and Generative Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fankun Zeng, Hao Zhang, Hou Hei Lam, Jiangjie Qiu, Siwei Fu, Wentao Li, Xiaonan Wang, Xiuyuan Hu","submitted_at":"2025-03-31T06:31:15Z","abstract_excerpt":"Organic photovoltaic (OPV) materials offer a promising avenue toward cost-effective solar energy utilization. However, optimizing donor-acceptor (D-A) combinations to achieve high power conversion efficiency (PCE) remains a significant challenge. In this work, we propose a framework that integrates large-scale pretraining of graph neural networks (GNNs) with a GPT-2 (Generative Pretrained Transformer 2)-based reinforcement learning (RL) strategy to design OPV molecules with potentially high PCE. This approach produces candidate molecules with predicted efficiencies approaching 21\\%, although f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23766","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/2503.23766/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":"2503.23766","created_at":"2026-07-05T10:41:59.527827+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.23766v1","created_at":"2026-07-05T10:41:59.527827+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23766","created_at":"2026-07-05T10:41:59.527827+00:00"},{"alias_kind":"pith_short_12","alias_value":"GRXXVAR3JSQK","created_at":"2026-07-05T10:41:59.527827+00:00"},{"alias_kind":"pith_short_16","alias_value":"GRXXVAR3JSQKBOPO","created_at":"2026-07-05T10:41:59.527827+00:00"},{"alias_kind":"pith_short_8","alias_value":"GRXXVAR3","created_at":"2026-07-05T10:41:59.527827+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/GRXXVAR3JSQKBOPOLY44MUQZ7G","json":"https://pith.science/pith/GRXXVAR3JSQKBOPOLY44MUQZ7G.json","graph_json":"https://pith.science/api/pith-number/GRXXVAR3JSQKBOPOLY44MUQZ7G/graph.json","events_json":"https://pith.science/api/pith-number/GRXXVAR3JSQKBOPOLY44MUQZ7G/events.json","paper":"https://pith.science/paper/GRXXVAR3"},"agent_actions":{"view_html":"https://pith.science/pith/GRXXVAR3JSQKBOPOLY44MUQZ7G","download_json":"https://pith.science/pith/GRXXVAR3JSQKBOPOLY44MUQZ7G.json","view_paper":"https://pith.science/paper/GRXXVAR3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.23766&json=true","fetch_graph":"https://pith.science/api/pith-number/GRXXVAR3JSQKBOPOLY44MUQZ7G/graph.json","fetch_events":"https://pith.science/api/pith-number/GRXXVAR3JSQKBOPOLY44MUQZ7G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GRXXVAR3JSQKBOPOLY44MUQZ7G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GRXXVAR3JSQKBOPOLY44MUQZ7G/action/storage_attestation","attest_author":"https://pith.science/pith/GRXXVAR3JSQKBOPOLY44MUQZ7G/action/author_attestation","sign_citation":"https://pith.science/pith/GRXXVAR3JSQKBOPOLY44MUQZ7G/action/citation_signature","submit_replication":"https://pith.science/pith/GRXXVAR3JSQKBOPOLY44MUQZ7G/action/replication_record"}},"created_at":"2026-07-05T10:41:59.527827+00:00","updated_at":"2026-07-05T10:41:59.527827+00:00"}