{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FWZ5P5KNLEPIAGL52JFZMYPSKM","short_pith_number":"pith:FWZ5P5KN","schema_version":"1.0","canonical_sha256":"2db3d7f54d591e80197dd24b9661f2530e70fcc81bbf971f62d34e7a2a9b6ca1","source":{"kind":"arxiv","id":"2506.08059","version":1},"attestation_state":"computed","paper":{"title":"CaliciBoost: Performance-Driven Evaluation of Molecular Representations for Caco-2 Permeability Prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Bok Kyung Han, Huong Van Le, Hwi-yeol Yun, Inho Choi, Jae-Mun Choi, Jong Il Park, Junhong Kim, Weibin Ren, Young Bin Park, Young Jun Kim, Yukyung Yun","submitted_at":"2025-06-09T07:30:28Z","abstract_excerpt":"Caco-2 permeability serves as a critical in vitro indicator for predicting the oral absorption of drug candidates during early-stage drug discovery. To enhance the accuracy and efficiency of computational predictions, we systematically investigated the impact of eight molecular feature representation types including 2D/3D descriptors, structural fingerprints, and deep learning-based embeddings combined with automated machine learning techniques to predict Caco-2 permeability. Using two datasets of differing scale and diversity (TDC benchmark and curated OCHEM data), we assessed model performan"},"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":"2506.08059","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-06-09T07:30:28Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ef49c6aaeee66508e1b6bd33760be79c5cec0803e3b6429dd3dc11dd56a89ef2","abstract_canon_sha256":"138aa450ddb31c6fb0ecbb09650f668bc4949cc6d531f3fde8ebe64c02911e60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:44.246009Z","signature_b64":"W60dicWG2rwiMFT+KvM0IqQN9X39OwsWcs6uxnPNheaqBcaW/jm35gupEt08iIoEZ4Q6lBA+Nfi7MObs0DJ1Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2db3d7f54d591e80197dd24b9661f2530e70fcc81bbf971f62d34e7a2a9b6ca1","last_reissued_at":"2026-07-05T11:18:44.245570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:44.245570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CaliciBoost: Performance-Driven Evaluation of Molecular Representations for Caco-2 Permeability Prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Bok Kyung Han, Huong Van Le, Hwi-yeol Yun, Inho Choi, Jae-Mun Choi, Jong Il Park, Junhong Kim, Weibin Ren, Young Bin Park, Young Jun Kim, Yukyung Yun","submitted_at":"2025-06-09T07:30:28Z","abstract_excerpt":"Caco-2 permeability serves as a critical in vitro indicator for predicting the oral absorption of drug candidates during early-stage drug discovery. To enhance the accuracy and efficiency of computational predictions, we systematically investigated the impact of eight molecular feature representation types including 2D/3D descriptors, structural fingerprints, and deep learning-based embeddings combined with automated machine learning techniques to predict Caco-2 permeability. Using two datasets of differing scale and diversity (TDC benchmark and curated OCHEM data), we assessed model performan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08059","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/2506.08059/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":"2506.08059","created_at":"2026-07-05T11:18:44.245624+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.08059v1","created_at":"2026-07-05T11:18:44.245624+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08059","created_at":"2026-07-05T11:18:44.245624+00:00"},{"alias_kind":"pith_short_12","alias_value":"FWZ5P5KNLEPI","created_at":"2026-07-05T11:18:44.245624+00:00"},{"alias_kind":"pith_short_16","alias_value":"FWZ5P5KNLEPIAGL5","created_at":"2026-07-05T11:18:44.245624+00:00"},{"alias_kind":"pith_short_8","alias_value":"FWZ5P5KN","created_at":"2026-07-05T11:18:44.245624+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/FWZ5P5KNLEPIAGL52JFZMYPSKM","json":"https://pith.science/pith/FWZ5P5KNLEPIAGL52JFZMYPSKM.json","graph_json":"https://pith.science/api/pith-number/FWZ5P5KNLEPIAGL52JFZMYPSKM/graph.json","events_json":"https://pith.science/api/pith-number/FWZ5P5KNLEPIAGL52JFZMYPSKM/events.json","paper":"https://pith.science/paper/FWZ5P5KN"},"agent_actions":{"view_html":"https://pith.science/pith/FWZ5P5KNLEPIAGL52JFZMYPSKM","download_json":"https://pith.science/pith/FWZ5P5KNLEPIAGL52JFZMYPSKM.json","view_paper":"https://pith.science/paper/FWZ5P5KN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.08059&json=true","fetch_graph":"https://pith.science/api/pith-number/FWZ5P5KNLEPIAGL52JFZMYPSKM/graph.json","fetch_events":"https://pith.science/api/pith-number/FWZ5P5KNLEPIAGL52JFZMYPSKM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FWZ5P5KNLEPIAGL52JFZMYPSKM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FWZ5P5KNLEPIAGL52JFZMYPSKM/action/storage_attestation","attest_author":"https://pith.science/pith/FWZ5P5KNLEPIAGL52JFZMYPSKM/action/author_attestation","sign_citation":"https://pith.science/pith/FWZ5P5KNLEPIAGL52JFZMYPSKM/action/citation_signature","submit_replication":"https://pith.science/pith/FWZ5P5KNLEPIAGL52JFZMYPSKM/action/replication_record"}},"created_at":"2026-07-05T11:18:44.245624+00:00","updated_at":"2026-07-05T11:18:44.245624+00:00"}