{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:E5EYSILMONIS7JTQBBFCMWUTOG","short_pith_number":"pith:E5EYSILM","schema_version":"1.0","canonical_sha256":"274989216c73512fa670084a265a937198cdbbe228a6e985457987bc90a6526f","source":{"kind":"arxiv","id":"2606.17077","version":1},"attestation_state":"computed","paper":{"title":"Comprehensive pKa Data Augmentation from Limited Real Data through an Engineered Models-Quantum Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","quant-ph"],"primary_cat":"physics.chem-ph","authors_text":"Liu Dinghao, Wang Rui","submitted_at":"2026-06-10T16:17:21Z","abstract_excerpt":"Proton dissociation constants (pKa) are critical for functional molecule discovery and molecular modeling. Building on iBonD, the largest experimental pKa database established, we and other researchers have developed several methods including machine-learning-based empirical prediction and high-accuracy energy calculations. Despite this foundation, the rapid augmentation of high-quality pKa data remains fundamentally constrained. As part of this work, we performed large-scale regression-based pKa prediction on unlabeled molecular datasets using a collection of extensively optimized machine-lea"},"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":"2606.17077","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.chem-ph","submitted_at":"2026-06-10T16:17:21Z","cross_cats_sorted":["cs.AI","cs.LG","quant-ph"],"title_canon_sha256":"3f03da0370108e73f3db34704e2f484cea286a69cf96a9771517522d0762db0d","abstract_canon_sha256":"b0677eed626db7f4c2d14ad7515a0a33af2261f8b216ee2f962271bada872995"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:38.321767Z","signature_b64":"WYG2IAA0oJgLVccpr4PG0rzZVR/iZEz+SBJm8IEKtuxygzrugtyGzkwqXbz/j5h/pnCJEer8uukM9afKL5pqBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"274989216c73512fa670084a265a937198cdbbe228a6e985457987bc90a6526f","last_reissued_at":"2026-06-19T16:11:38.321400Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:38.321400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comprehensive pKa Data Augmentation from Limited Real Data through an Engineered Models-Quantum Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","quant-ph"],"primary_cat":"physics.chem-ph","authors_text":"Liu Dinghao, Wang Rui","submitted_at":"2026-06-10T16:17:21Z","abstract_excerpt":"Proton dissociation constants (pKa) are critical for functional molecule discovery and molecular modeling. Building on iBonD, the largest experimental pKa database established, we and other researchers have developed several methods including machine-learning-based empirical prediction and high-accuracy energy calculations. Despite this foundation, the rapid augmentation of high-quality pKa data remains fundamentally constrained. As part of this work, we performed large-scale regression-based pKa prediction on unlabeled molecular datasets using a collection of extensively optimized machine-lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17077","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/2606.17077/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":"2606.17077","created_at":"2026-06-19T16:11:38.321464+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.17077v1","created_at":"2026-06-19T16:11:38.321464+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17077","created_at":"2026-06-19T16:11:38.321464+00:00"},{"alias_kind":"pith_short_12","alias_value":"E5EYSILMONIS","created_at":"2026-06-19T16:11:38.321464+00:00"},{"alias_kind":"pith_short_16","alias_value":"E5EYSILMONIS7JTQ","created_at":"2026-06-19T16:11:38.321464+00:00"},{"alias_kind":"pith_short_8","alias_value":"E5EYSILM","created_at":"2026-06-19T16:11:38.321464+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E5EYSILMONIS7JTQBBFCMWUTOG","json":"https://pith.science/pith/E5EYSILMONIS7JTQBBFCMWUTOG.json","graph_json":"https://pith.science/api/pith-number/E5EYSILMONIS7JTQBBFCMWUTOG/graph.json","events_json":"https://pith.science/api/pith-number/E5EYSILMONIS7JTQBBFCMWUTOG/events.json","paper":"https://pith.science/paper/E5EYSILM"},"agent_actions":{"view_html":"https://pith.science/pith/E5EYSILMONIS7JTQBBFCMWUTOG","download_json":"https://pith.science/pith/E5EYSILMONIS7JTQBBFCMWUTOG.json","view_paper":"https://pith.science/paper/E5EYSILM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.17077&json=true","fetch_graph":"https://pith.science/api/pith-number/E5EYSILMONIS7JTQBBFCMWUTOG/graph.json","fetch_events":"https://pith.science/api/pith-number/E5EYSILMONIS7JTQBBFCMWUTOG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E5EYSILMONIS7JTQBBFCMWUTOG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E5EYSILMONIS7JTQBBFCMWUTOG/action/storage_attestation","attest_author":"https://pith.science/pith/E5EYSILMONIS7JTQBBFCMWUTOG/action/author_attestation","sign_citation":"https://pith.science/pith/E5EYSILMONIS7JTQBBFCMWUTOG/action/citation_signature","submit_replication":"https://pith.science/pith/E5EYSILMONIS7JTQBBFCMWUTOG/action/replication_record"}},"created_at":"2026-06-19T16:11:38.321464+00:00","updated_at":"2026-06-19T16:11:38.321464+00:00"}