{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LDZGBIWHOQPI3XDFCE5SC6GEEH","short_pith_number":"pith:LDZGBIWH","schema_version":"1.0","canonical_sha256":"58f260a2c7741e8ddc65113b2178c421dd7ddc0f4f7cc5c4de420e8c5fb5fde2","source":{"kind":"arxiv","id":"2207.04869","version":3},"attestation_state":"computed","paper":{"title":"Graph-based Molecular Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Bozhao Nan, Chuxu Zhang, Kehan Guo, Nitesh V. Chawla, Olaf Wiest, Roshni G. Iyer, Wei Wang, Xiangliang Zhang, Yihong Ma, Yijun Tian, Zhichun Guo","submitted_at":"2022-07-08T17:43:20Z","abstract_excerpt":"Molecular representation learning (MRL) is a key step to build the connection between machine learning and chemical science. In particular, it encodes molecules as numerical vectors preserving the molecular structures and features, on top of which the downstream tasks (e.g., property prediction) can be performed. Recently, MRL has achieved considerable progress, especially in methods based on deep molecular graph learning. In this survey, we systematically review these graph-based molecular representation techniques, especially the methods incorporating chemical domain knowledge. Specifically,"},"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":"2207.04869","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2022-07-08T17:43:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0040e25451c768981c21c04c11b029adaa73b5a01555b49da51d3a3d42050160","abstract_canon_sha256":"e2c094de01dbf2798ea28bac8c45126f5bc0db66be32be3f06bbc613532618b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:17:51.815751Z","signature_b64":"FG3pyW8yt4e+qVrQfvIK0Vae6OWyg+SBnYpcvxpNzVzfvIqVVsRZ0aIE4lP1tah6HoFfKl2Y+FX2BUH2u+lGCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58f260a2c7741e8ddc65113b2178c421dd7ddc0f4f7cc5c4de420e8c5fb5fde2","last_reissued_at":"2026-07-05T07:17:51.815245Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:17:51.815245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph-based Molecular Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Bozhao Nan, Chuxu Zhang, Kehan Guo, Nitesh V. Chawla, Olaf Wiest, Roshni G. Iyer, Wei Wang, Xiangliang Zhang, Yihong Ma, Yijun Tian, Zhichun Guo","submitted_at":"2022-07-08T17:43:20Z","abstract_excerpt":"Molecular representation learning (MRL) is a key step to build the connection between machine learning and chemical science. In particular, it encodes molecules as numerical vectors preserving the molecular structures and features, on top of which the downstream tasks (e.g., property prediction) can be performed. Recently, MRL has achieved considerable progress, especially in methods based on deep molecular graph learning. In this survey, we systematically review these graph-based molecular representation techniques, especially the methods incorporating chemical domain knowledge. Specifically,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.04869","kind":"arxiv","version":3},"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/2207.04869/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":"2207.04869","created_at":"2026-07-05T07:17:51.815307+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.04869v3","created_at":"2026-07-05T07:17:51.815307+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.04869","created_at":"2026-07-05T07:17:51.815307+00:00"},{"alias_kind":"pith_short_12","alias_value":"LDZGBIWHOQPI","created_at":"2026-07-05T07:17:51.815307+00:00"},{"alias_kind":"pith_short_16","alias_value":"LDZGBIWHOQPI3XDF","created_at":"2026-07-05T07:17:51.815307+00:00"},{"alias_kind":"pith_short_8","alias_value":"LDZGBIWH","created_at":"2026-07-05T07:17:51.815307+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18893","citing_title":"Position: Graph Condensation Needs a Reset -- Move Beyond Full-dataset Training and Model-Dependence","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18893","citing_title":"Position: Graph Condensation Needs a Reset -- Move Beyond Full-dataset Training and Model-Dependence","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LDZGBIWHOQPI3XDFCE5SC6GEEH","json":"https://pith.science/pith/LDZGBIWHOQPI3XDFCE5SC6GEEH.json","graph_json":"https://pith.science/api/pith-number/LDZGBIWHOQPI3XDFCE5SC6GEEH/graph.json","events_json":"https://pith.science/api/pith-number/LDZGBIWHOQPI3XDFCE5SC6GEEH/events.json","paper":"https://pith.science/paper/LDZGBIWH"},"agent_actions":{"view_html":"https://pith.science/pith/LDZGBIWHOQPI3XDFCE5SC6GEEH","download_json":"https://pith.science/pith/LDZGBIWHOQPI3XDFCE5SC6GEEH.json","view_paper":"https://pith.science/paper/LDZGBIWH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.04869&json=true","fetch_graph":"https://pith.science/api/pith-number/LDZGBIWHOQPI3XDFCE5SC6GEEH/graph.json","fetch_events":"https://pith.science/api/pith-number/LDZGBIWHOQPI3XDFCE5SC6GEEH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LDZGBIWHOQPI3XDFCE5SC6GEEH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LDZGBIWHOQPI3XDFCE5SC6GEEH/action/storage_attestation","attest_author":"https://pith.science/pith/LDZGBIWHOQPI3XDFCE5SC6GEEH/action/author_attestation","sign_citation":"https://pith.science/pith/LDZGBIWHOQPI3XDFCE5SC6GEEH/action/citation_signature","submit_replication":"https://pith.science/pith/LDZGBIWHOQPI3XDFCE5SC6GEEH/action/replication_record"}},"created_at":"2026-07-05T07:17:51.815307+00:00","updated_at":"2026-07-05T07:17:51.815307+00:00"}