{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WPODIVM7ZQGCYWL4CFQC43Q3O4","short_pith_number":"pith:WPODIVM7","schema_version":"1.0","canonical_sha256":"b3dc34559fcc0c2c597c11602e6e1b771ae4324aeacf402755eb611c8cf29de3","source":{"kind":"arxiv","id":"2407.19039","version":1},"attestation_state":"computed","paper":{"title":"GraphBPE: Molecular Graphs Meet Byte-Pair Encoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","physics.chem-ph","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Barnab\\'as P\\'oczos, Yuchen Shen","submitted_at":"2024-07-26T18:45:09Z","abstract_excerpt":"With the increasing attention to molecular machine learning, various innovations have been made in designing better models or proposing more comprehensive benchmarks. However, less is studied on the data preprocessing schedule for molecular graphs, where a different view of the molecular graph could potentially boost the model's performance. Inspired by the Byte-Pair Encoding (BPE) algorithm, a subword tokenization method popularly adopted in Natural Language Processing, we propose GraphBPE, which tokenizes a molecular graph into different substructures and acts as a preprocessing schedule ind"},"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":"2407.19039","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-26T18:45:09Z","cross_cats_sorted":["cs.AI","physics.chem-ph","q-bio.BM"],"title_canon_sha256":"b5251e84e7f49247cb999f1e3e1ba43eb0efadeed69b11f9d7354283c0d8280e","abstract_canon_sha256":"13eefe86be29d05357b39bbe18eb50d4cc8b07e1b1b941f399edfc8b38c8474a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:49:38.016859Z","signature_b64":"X5bf4x0g55Cr+MLijvXlC3w15uoFoefOzUsSLTz0Q5GQYxOWHi1TaQ1GItKKl8T/DzfxbIsdAWPj329MgwLSAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3dc34559fcc0c2c597c11602e6e1b771ae4324aeacf402755eb611c8cf29de3","last_reissued_at":"2026-07-05T08:49:38.015580Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:49:38.015580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GraphBPE: Molecular Graphs Meet Byte-Pair Encoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","physics.chem-ph","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Barnab\\'as P\\'oczos, Yuchen Shen","submitted_at":"2024-07-26T18:45:09Z","abstract_excerpt":"With the increasing attention to molecular machine learning, various innovations have been made in designing better models or proposing more comprehensive benchmarks. However, less is studied on the data preprocessing schedule for molecular graphs, where a different view of the molecular graph could potentially boost the model's performance. Inspired by the Byte-Pair Encoding (BPE) algorithm, a subword tokenization method popularly adopted in Natural Language Processing, we propose GraphBPE, which tokenizes a molecular graph into different substructures and acts as a preprocessing schedule ind"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.19039","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/2407.19039/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":"2407.19039","created_at":"2026-07-05T08:49:38.015643+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.19039v1","created_at":"2026-07-05T08:49:38.015643+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.19039","created_at":"2026-07-05T08:49:38.015643+00:00"},{"alias_kind":"pith_short_12","alias_value":"WPODIVM7ZQGC","created_at":"2026-07-05T08:49:38.015643+00:00"},{"alias_kind":"pith_short_16","alias_value":"WPODIVM7ZQGCYWL4","created_at":"2026-07-05T08:49:38.015643+00:00"},{"alias_kind":"pith_short_8","alias_value":"WPODIVM7","created_at":"2026-07-05T08:49:38.015643+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27853","citing_title":"MolLingo: Molecule-Native Representations for LLM-Powered Scientific Agents","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23134","citing_title":"h-MINT: Modeling Pocket-Ligand Binding with Hierarchical Molecular Interaction Network","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WPODIVM7ZQGCYWL4CFQC43Q3O4","json":"https://pith.science/pith/WPODIVM7ZQGCYWL4CFQC43Q3O4.json","graph_json":"https://pith.science/api/pith-number/WPODIVM7ZQGCYWL4CFQC43Q3O4/graph.json","events_json":"https://pith.science/api/pith-number/WPODIVM7ZQGCYWL4CFQC43Q3O4/events.json","paper":"https://pith.science/paper/WPODIVM7"},"agent_actions":{"view_html":"https://pith.science/pith/WPODIVM7ZQGCYWL4CFQC43Q3O4","download_json":"https://pith.science/pith/WPODIVM7ZQGCYWL4CFQC43Q3O4.json","view_paper":"https://pith.science/paper/WPODIVM7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.19039&json=true","fetch_graph":"https://pith.science/api/pith-number/WPODIVM7ZQGCYWL4CFQC43Q3O4/graph.json","fetch_events":"https://pith.science/api/pith-number/WPODIVM7ZQGCYWL4CFQC43Q3O4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WPODIVM7ZQGCYWL4CFQC43Q3O4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WPODIVM7ZQGCYWL4CFQC43Q3O4/action/storage_attestation","attest_author":"https://pith.science/pith/WPODIVM7ZQGCYWL4CFQC43Q3O4/action/author_attestation","sign_citation":"https://pith.science/pith/WPODIVM7ZQGCYWL4CFQC43Q3O4/action/citation_signature","submit_replication":"https://pith.science/pith/WPODIVM7ZQGCYWL4CFQC43Q3O4/action/replication_record"}},"created_at":"2026-07-05T08:49:38.015643+00:00","updated_at":"2026-07-05T08:49:38.015643+00:00"}