{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:QYQ2XMK7WDZLG3W2K3YLPUF254","short_pith_number":"pith:QYQ2XMK7","schema_version":"1.0","canonical_sha256":"8621abb15fb0f2b36eda56f0b7d0baef2c6f3dd556f0eb9e0134f3734bbeb609","source":{"kind":"arxiv","id":"2007.13437","version":2},"attestation_state":"computed","paper":{"title":"Energy-based View of Retrosynthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-bio.QM"],"primary_cat":"physics.chem-ph","authors_text":"Bo Dai, Hanjun Dai, Li Li, Ruoxi Sun, Steven Kearnes","submitted_at":"2020-07-14T18:51:06Z","abstract_excerpt":"Retrosynthesis -- the process of identifying a set of reactants to synthesize a target molecule -- is of vital importance to material design and drug discovery. Existing machine learning approaches based on language models and graph neural networks have achieved encouraging results. In this paper, we propose a framework that unifies sequence- and graph-based methods as energy-based models (EBMs) with different energy functions. This unified perspective provides critical insights about EBM variants through a comprehensive assessment of performance. Additionally, we present a novel dual variant "},"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":"2007.13437","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2020-07-14T18:51:06Z","cross_cats_sorted":["cs.LG","q-bio.QM"],"title_canon_sha256":"4f28f501aa0e5c7cc8c52cffac89a391de7e1f2664750a38dfc37db04be221dd","abstract_canon_sha256":"4fa3c3932061a5e9a8b13bf71971843072cfa22c340e1f6c35f8714ceb85e0a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:39:11.462077Z","signature_b64":"CRGNdDgQZJHB+huL9HQ/iQ0qmpbsBlcQvY/NVj9gTgT+WJCVFqaD6pgsxBvE5KyPZSrQFYlDUpPnSdUfoUmbDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8621abb15fb0f2b36eda56f0b7d0baef2c6f3dd556f0eb9e0134f3734bbeb609","last_reissued_at":"2026-07-05T03:39:11.461581Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:39:11.461581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Energy-based View of Retrosynthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-bio.QM"],"primary_cat":"physics.chem-ph","authors_text":"Bo Dai, Hanjun Dai, Li Li, Ruoxi Sun, Steven Kearnes","submitted_at":"2020-07-14T18:51:06Z","abstract_excerpt":"Retrosynthesis -- the process of identifying a set of reactants to synthesize a target molecule -- is of vital importance to material design and drug discovery. Existing machine learning approaches based on language models and graph neural networks have achieved encouraging results. In this paper, we propose a framework that unifies sequence- and graph-based methods as energy-based models (EBMs) with different energy functions. This unified perspective provides critical insights about EBM variants through a comprehensive assessment of performance. Additionally, we present a novel dual variant "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.13437","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/2007.13437/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":"2007.13437","created_at":"2026-07-05T03:39:11.461634+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.13437v2","created_at":"2026-07-05T03:39:11.461634+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.13437","created_at":"2026-07-05T03:39:11.461634+00:00"},{"alias_kind":"pith_short_12","alias_value":"QYQ2XMK7WDZL","created_at":"2026-07-05T03:39:11.461634+00:00"},{"alias_kind":"pith_short_16","alias_value":"QYQ2XMK7WDZLG3W2","created_at":"2026-07-05T03:39:11.461634+00:00"},{"alias_kind":"pith_short_8","alias_value":"QYQ2XMK7","created_at":"2026-07-05T03:39:11.461634+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07181","citing_title":"RETROSPECT: RETROsynthesis via Sequential Prediction, and Chemically Transformed-ranking","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QYQ2XMK7WDZLG3W2K3YLPUF254","json":"https://pith.science/pith/QYQ2XMK7WDZLG3W2K3YLPUF254.json","graph_json":"https://pith.science/api/pith-number/QYQ2XMK7WDZLG3W2K3YLPUF254/graph.json","events_json":"https://pith.science/api/pith-number/QYQ2XMK7WDZLG3W2K3YLPUF254/events.json","paper":"https://pith.science/paper/QYQ2XMK7"},"agent_actions":{"view_html":"https://pith.science/pith/QYQ2XMK7WDZLG3W2K3YLPUF254","download_json":"https://pith.science/pith/QYQ2XMK7WDZLG3W2K3YLPUF254.json","view_paper":"https://pith.science/paper/QYQ2XMK7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.13437&json=true","fetch_graph":"https://pith.science/api/pith-number/QYQ2XMK7WDZLG3W2K3YLPUF254/graph.json","fetch_events":"https://pith.science/api/pith-number/QYQ2XMK7WDZLG3W2K3YLPUF254/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QYQ2XMK7WDZLG3W2K3YLPUF254/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QYQ2XMK7WDZLG3W2K3YLPUF254/action/storage_attestation","attest_author":"https://pith.science/pith/QYQ2XMK7WDZLG3W2K3YLPUF254/action/author_attestation","sign_citation":"https://pith.science/pith/QYQ2XMK7WDZLG3W2K3YLPUF254/action/citation_signature","submit_replication":"https://pith.science/pith/QYQ2XMK7WDZLG3W2K3YLPUF254/action/replication_record"}},"created_at":"2026-07-05T03:39:11.461634+00:00","updated_at":"2026-07-05T03:39:11.461634+00:00"}