{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:P5JSNQ5HHFJZPBIYOLOLLZG3MX","short_pith_number":"pith:P5JSNQ5H","schema_version":"1.0","canonical_sha256":"7f5326c3a7395397851872dcb5e4db65f2efa760dd8f0d53aac7a162c7a35f87","source":{"kind":"arxiv","id":"2310.01704","version":1},"attestation_state":"computed","paper":{"title":"Transformers are efficient hierarchical chemical graph learners","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aaron R. Dinner, Chih-chan Tien, Risi Kondor, Zihan Pengmei, Zimu Li","submitted_at":"2023-10-02T23:57:04Z","abstract_excerpt":"Transformers, adapted from natural language processing, are emerging as a leading approach for graph representation learning. Contemporary graph transformers often treat nodes or edges as separate tokens. This approach leads to computational challenges for even moderately-sized graphs due to the quadratic scaling of self-attention complexity with token count. In this paper, we introduce SubFormer, a graph transformer that operates on subgraphs that aggregate information by a message-passing mechanism. This approach reduces the number of tokens and enhances learning long-range interactions. We "},"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":"2310.01704","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-02T23:57:04Z","cross_cats_sorted":[],"title_canon_sha256":"b42a33afd4df50ad7f0b2eb306f734f3226ed8f7c4326a3a0e90a3687f447403","abstract_canon_sha256":"a47a7d7abcb6890d30b1ff8cf5ba7ea87143742ca1b12da269a22ba8afae439d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:56:45.001990Z","signature_b64":"mwAsKtKw9w2EPTzCjbtVXcaADkVFc6zlmFIeDeawUBY8Z4yn/TfPA2gBkeLOuimKuXOxys+xhJ9U+h2o1iwlDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f5326c3a7395397851872dcb5e4db65f2efa760dd8f0d53aac7a162c7a35f87","last_reissued_at":"2026-07-05T06:56:45.001512Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:56:45.001512Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformers are efficient hierarchical chemical graph learners","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aaron R. Dinner, Chih-chan Tien, Risi Kondor, Zihan Pengmei, Zimu Li","submitted_at":"2023-10-02T23:57:04Z","abstract_excerpt":"Transformers, adapted from natural language processing, are emerging as a leading approach for graph representation learning. Contemporary graph transformers often treat nodes or edges as separate tokens. This approach leads to computational challenges for even moderately-sized graphs due to the quadratic scaling of self-attention complexity with token count. In this paper, we introduce SubFormer, a graph transformer that operates on subgraphs that aggregate information by a message-passing mechanism. This approach reduces the number of tokens and enhances learning long-range interactions. We "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01704","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/2310.01704/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":"2310.01704","created_at":"2026-07-05T06:56:45.001570+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.01704v1","created_at":"2026-07-05T06:56:45.001570+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01704","created_at":"2026-07-05T06:56:45.001570+00:00"},{"alias_kind":"pith_short_12","alias_value":"P5JSNQ5HHFJZ","created_at":"2026-07-05T06:56:45.001570+00:00"},{"alias_kind":"pith_short_16","alias_value":"P5JSNQ5HHFJZPBIY","created_at":"2026-07-05T06:56:45.001570+00:00"},{"alias_kind":"pith_short_8","alias_value":"P5JSNQ5H","created_at":"2026-07-05T06:56:45.001570+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12541","citing_title":"BSA: Ball Sparse Attention for Large-scale Geometries","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P5JSNQ5HHFJZPBIYOLOLLZG3MX","json":"https://pith.science/pith/P5JSNQ5HHFJZPBIYOLOLLZG3MX.json","graph_json":"https://pith.science/api/pith-number/P5JSNQ5HHFJZPBIYOLOLLZG3MX/graph.json","events_json":"https://pith.science/api/pith-number/P5JSNQ5HHFJZPBIYOLOLLZG3MX/events.json","paper":"https://pith.science/paper/P5JSNQ5H"},"agent_actions":{"view_html":"https://pith.science/pith/P5JSNQ5HHFJZPBIYOLOLLZG3MX","download_json":"https://pith.science/pith/P5JSNQ5HHFJZPBIYOLOLLZG3MX.json","view_paper":"https://pith.science/paper/P5JSNQ5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.01704&json=true","fetch_graph":"https://pith.science/api/pith-number/P5JSNQ5HHFJZPBIYOLOLLZG3MX/graph.json","fetch_events":"https://pith.science/api/pith-number/P5JSNQ5HHFJZPBIYOLOLLZG3MX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P5JSNQ5HHFJZPBIYOLOLLZG3MX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P5JSNQ5HHFJZPBIYOLOLLZG3MX/action/storage_attestation","attest_author":"https://pith.science/pith/P5JSNQ5HHFJZPBIYOLOLLZG3MX/action/author_attestation","sign_citation":"https://pith.science/pith/P5JSNQ5HHFJZPBIYOLOLLZG3MX/action/citation_signature","submit_replication":"https://pith.science/pith/P5JSNQ5HHFJZPBIYOLOLLZG3MX/action/replication_record"}},"created_at":"2026-07-05T06:56:45.001570+00:00","updated_at":"2026-07-05T06:56:45.001570+00:00"}