{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XVKDCQ6JM54PEMJ5722EOGS6NQ","short_pith_number":"pith:XVKDCQ6J","schema_version":"1.0","canonical_sha256":"bd543143c96778f2313dfeb4471a5e6c01eb92a783f597a842c7a9da7454b3e7","source":{"kind":"arxiv","id":"2102.00546","version":2},"attestation_state":"computed","paper":{"title":"GraphEBM: Molecular Graph Generation with Energy-Based Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bora Oztekin, Keqiang Yan, Meng Liu, Shuiwang Ji","submitted_at":"2021-01-31T21:45:12Z","abstract_excerpt":"We note that most existing approaches for molecular graph generation fail to guarantee the intrinsic property of permutation invariance, resulting in unexpected bias in generative models. In this work, we propose GraphEBM to generate molecular graphs using energy-based models. In particular, we parameterize the energy function in a permutation invariant manner, thus making GraphEBM permutation invariant. We apply Langevin dynamics to train the energy function by approximately maximizing likelihood and generate samples with low energies. Furthermore, to generate molecules with a desirable prope"},"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":"2102.00546","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-01-31T21:45:12Z","cross_cats_sorted":[],"title_canon_sha256":"354af3bdb862d3af3ed34d8d31c330585649ee6546bc28ab5fa0185dff0675d7","abstract_canon_sha256":"36ad9e64b915af6f76dfe0f5388a74bd49ad6d8c2d069aec894ea258d52e5bfd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:31:03.968311Z","signature_b64":"U5GBLDE4u7CKIxVFxYt83MQg3/OjrTYNKpoGRGbg4j8StbRFsADDZbMhVNfLkTIdhPvk9oOefyl3criwttdfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd543143c96778f2313dfeb4471a5e6c01eb92a783f597a842c7a9da7454b3e7","last_reissued_at":"2026-07-05T02:31:03.967759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:31:03.967759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GraphEBM: Molecular Graph Generation with Energy-Based Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bora Oztekin, Keqiang Yan, Meng Liu, Shuiwang Ji","submitted_at":"2021-01-31T21:45:12Z","abstract_excerpt":"We note that most existing approaches for molecular graph generation fail to guarantee the intrinsic property of permutation invariance, resulting in unexpected bias in generative models. In this work, we propose GraphEBM to generate molecular graphs using energy-based models. In particular, we parameterize the energy function in a permutation invariant manner, thus making GraphEBM permutation invariant. We apply Langevin dynamics to train the energy function by approximately maximizing likelihood and generate samples with low energies. Furthermore, to generate molecules with a desirable prope"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.00546","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/2102.00546/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":"2102.00546","created_at":"2026-07-05T02:31:03.967820+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.00546v2","created_at":"2026-07-05T02:31:03.967820+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.00546","created_at":"2026-07-05T02:31:03.967820+00:00"},{"alias_kind":"pith_short_12","alias_value":"XVKDCQ6JM54P","created_at":"2026-07-05T02:31:03.967820+00:00"},{"alias_kind":"pith_short_16","alias_value":"XVKDCQ6JM54PEMJ5","created_at":"2026-07-05T02:31:03.967820+00:00"},{"alias_kind":"pith_short_8","alias_value":"XVKDCQ6J","created_at":"2026-07-05T02:31:03.967820+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31660","citing_title":"Contrastive Regularization of Machine Learning Potentials","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00776","citing_title":"Latent Diffusion Pretraining for Crystal Property Prediction","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2409.09183","citing_title":"Quantum-inspired Reinforcement Learning for Synthesizable Drug Design","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2504.16559","citing_title":"Synergistic Benefits of Joint Molecule Generation and Property Prediction","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XVKDCQ6JM54PEMJ5722EOGS6NQ","json":"https://pith.science/pith/XVKDCQ6JM54PEMJ5722EOGS6NQ.json","graph_json":"https://pith.science/api/pith-number/XVKDCQ6JM54PEMJ5722EOGS6NQ/graph.json","events_json":"https://pith.science/api/pith-number/XVKDCQ6JM54PEMJ5722EOGS6NQ/events.json","paper":"https://pith.science/paper/XVKDCQ6J"},"agent_actions":{"view_html":"https://pith.science/pith/XVKDCQ6JM54PEMJ5722EOGS6NQ","download_json":"https://pith.science/pith/XVKDCQ6JM54PEMJ5722EOGS6NQ.json","view_paper":"https://pith.science/paper/XVKDCQ6J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.00546&json=true","fetch_graph":"https://pith.science/api/pith-number/XVKDCQ6JM54PEMJ5722EOGS6NQ/graph.json","fetch_events":"https://pith.science/api/pith-number/XVKDCQ6JM54PEMJ5722EOGS6NQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XVKDCQ6JM54PEMJ5722EOGS6NQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XVKDCQ6JM54PEMJ5722EOGS6NQ/action/storage_attestation","attest_author":"https://pith.science/pith/XVKDCQ6JM54PEMJ5722EOGS6NQ/action/author_attestation","sign_citation":"https://pith.science/pith/XVKDCQ6JM54PEMJ5722EOGS6NQ/action/citation_signature","submit_replication":"https://pith.science/pith/XVKDCQ6JM54PEMJ5722EOGS6NQ/action/replication_record"}},"created_at":"2026-07-05T02:31:03.967820+00:00","updated_at":"2026-07-05T02:31:03.967820+00:00"}