{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SN23465JPUNAAL4BKDCJASYCXR","short_pith_number":"pith:SN23465J","schema_version":"1.0","canonical_sha256":"9375be7ba97d1a002f8150c4904b02bc76347b7c9a199c21323df3842da1199e","source":{"kind":"arxiv","id":"2402.00086","version":1},"attestation_state":"computed","paper":{"title":"Retrosynthesis prediction enhanced by in-silico reaction data augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Wenguan Wang, Xu Zhang, Yiming Mo, Yi Yang","submitted_at":"2024-01-31T07:40:37Z","abstract_excerpt":"Recent advances in machine learning (ML) have expedited retrosynthesis research by assisting chemists to design experiments more efficiently. However, all ML-based methods consume substantial amounts of paired training data (i.e., chemical reaction: product-reactant(s) pair), which is costly to obtain. Moreover, companies view reaction data as a valuable asset and restrict the accessibility to researchers. These issues prevent the creation of more powerful retrosynthesis models due to their data-driven nature. As a response, we exploit easy-to-access unpaired data (i.e., one component of produ"},"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":"2402.00086","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-31T07:40:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8b21ade90cff5da6122be285c94027c954e552774b57272b616117cdae031de6","abstract_canon_sha256":"bdcb710d23d40ed9e8c9de08378e798302dcf1f7eb46107034a7af2b572977f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:39:48.504111Z","signature_b64":"re8xDnGJLF3T+n6SfFqZa4dBGZWbj/HTYbLX8ivCc/+t47WYc/BaP64od9evtnFgW3GS92I4tVBtqC3M9p6CAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9375be7ba97d1a002f8150c4904b02bc76347b7c9a199c21323df3842da1199e","last_reissued_at":"2026-07-05T07:39:48.503659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:39:48.503659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrosynthesis prediction enhanced by in-silico reaction data augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Wenguan Wang, Xu Zhang, Yiming Mo, Yi Yang","submitted_at":"2024-01-31T07:40:37Z","abstract_excerpt":"Recent advances in machine learning (ML) have expedited retrosynthesis research by assisting chemists to design experiments more efficiently. However, all ML-based methods consume substantial amounts of paired training data (i.e., chemical reaction: product-reactant(s) pair), which is costly to obtain. Moreover, companies view reaction data as a valuable asset and restrict the accessibility to researchers. These issues prevent the creation of more powerful retrosynthesis models due to their data-driven nature. As a response, we exploit easy-to-access unpaired data (i.e., one component of produ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.00086","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/2402.00086/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":"2402.00086","created_at":"2026-07-05T07:39:48.503711+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.00086v1","created_at":"2026-07-05T07:39:48.503711+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.00086","created_at":"2026-07-05T07:39:48.503711+00:00"},{"alias_kind":"pith_short_12","alias_value":"SN23465JPUNA","created_at":"2026-07-05T07:39:48.503711+00:00"},{"alias_kind":"pith_short_16","alias_value":"SN23465JPUNAAL4B","created_at":"2026-07-05T07:39:48.503711+00:00"},{"alias_kind":"pith_short_8","alias_value":"SN23465J","created_at":"2026-07-05T07:39:48.503711+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.05269","citing_title":"Chemist-aligned retrosynthesis by ensembling diverse inductive bias models","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SN23465JPUNAAL4BKDCJASYCXR","json":"https://pith.science/pith/SN23465JPUNAAL4BKDCJASYCXR.json","graph_json":"https://pith.science/api/pith-number/SN23465JPUNAAL4BKDCJASYCXR/graph.json","events_json":"https://pith.science/api/pith-number/SN23465JPUNAAL4BKDCJASYCXR/events.json","paper":"https://pith.science/paper/SN23465J"},"agent_actions":{"view_html":"https://pith.science/pith/SN23465JPUNAAL4BKDCJASYCXR","download_json":"https://pith.science/pith/SN23465JPUNAAL4BKDCJASYCXR.json","view_paper":"https://pith.science/paper/SN23465J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.00086&json=true","fetch_graph":"https://pith.science/api/pith-number/SN23465JPUNAAL4BKDCJASYCXR/graph.json","fetch_events":"https://pith.science/api/pith-number/SN23465JPUNAAL4BKDCJASYCXR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SN23465JPUNAAL4BKDCJASYCXR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SN23465JPUNAAL4BKDCJASYCXR/action/storage_attestation","attest_author":"https://pith.science/pith/SN23465JPUNAAL4BKDCJASYCXR/action/author_attestation","sign_citation":"https://pith.science/pith/SN23465JPUNAAL4BKDCJASYCXR/action/citation_signature","submit_replication":"https://pith.science/pith/SN23465JPUNAAL4BKDCJASYCXR/action/replication_record"}},"created_at":"2026-07-05T07:39:48.503711+00:00","updated_at":"2026-07-05T07:39:48.503711+00:00"}