{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UQIUNHRBF676QMO7ZPZSQ5PHUT","short_pith_number":"pith:UQIUNHRB","schema_version":"1.0","canonical_sha256":"a411469e212fbfe831dfcbf32875e7a4c082190f9cf030f81f13a3e38dcc76d3","source":{"kind":"arxiv","id":"2606.07258","version":1},"attestation_state":"computed","paper":{"title":"CaliPPer: quantifying, predicting and improving AI model performance for binding prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.QM"],"primary_cat":"cs.CE","authors_text":"Elie Antoun, Hantao Lou, Jian-Qing Zheng, Sam Farrar, Tao Dong, Xiangxi Wang, Xuetao Cao, Yuze Zhou, Zinan Yin","submitted_at":"2026-06-05T13:34:47Z","abstract_excerpt":"Binding prediction models accelerate therapeutic antibody and TCR discovery, but their performance on new datasets is unpredictable, often leading to low discovery rates. Density-ratio methods (PAPE, M-CBPE) provide label-free performance estimation for binary classification, but their assumptions and aggregate-only outputs limit binding prediction on neoepitopes, antigen variants and chemical scaffolds. Here we present CaliPPer (Calibration and Prediction of Performance), a post-hoc framework pairing a multi-chain Sample-to-Domain Distance (S2DD) with distance-aware Bayesian recalibration, op"},"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":"2606.07258","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CE","submitted_at":"2026-06-05T13:34:47Z","cross_cats_sorted":["q-bio.QM"],"title_canon_sha256":"e87c21a977d51558ed8f6fdcad61eccffb715a5a79f9dd08d3d03d4cd483830f","abstract_canon_sha256":"37fcd691d63313be077e51257c75844b8ff403cb56bfc2f9ac275778387f3fb4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:05:16.274191Z","signature_b64":"IeaOZyxEKKRPYYMHwCVEhOYQU59M16sY/w8D2qWTyAoYRLiAEPuraziWf3f47xUtmShmep1qdhJpUxe7/Q4kBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a411469e212fbfe831dfcbf32875e7a4c082190f9cf030f81f13a3e38dcc76d3","last_reissued_at":"2026-06-08T01:05:16.273227Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:05:16.273227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CaliPPer: quantifying, predicting and improving AI model performance for binding prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.QM"],"primary_cat":"cs.CE","authors_text":"Elie Antoun, Hantao Lou, Jian-Qing Zheng, Sam Farrar, Tao Dong, Xiangxi Wang, Xuetao Cao, Yuze Zhou, Zinan Yin","submitted_at":"2026-06-05T13:34:47Z","abstract_excerpt":"Binding prediction models accelerate therapeutic antibody and TCR discovery, but their performance on new datasets is unpredictable, often leading to low discovery rates. Density-ratio methods (PAPE, M-CBPE) provide label-free performance estimation for binary classification, but their assumptions and aggregate-only outputs limit binding prediction on neoepitopes, antigen variants and chemical scaffolds. Here we present CaliPPer (Calibration and Prediction of Performance), a post-hoc framework pairing a multi-chain Sample-to-Domain Distance (S2DD) with distance-aware Bayesian recalibration, op"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07258","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/2606.07258/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":"2606.07258","created_at":"2026-06-08T01:05:16.273372+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07258v1","created_at":"2026-06-08T01:05:16.273372+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07258","created_at":"2026-06-08T01:05:16.273372+00:00"},{"alias_kind":"pith_short_12","alias_value":"UQIUNHRBF676","created_at":"2026-06-08T01:05:16.273372+00:00"},{"alias_kind":"pith_short_16","alias_value":"UQIUNHRBF676QMO7","created_at":"2026-06-08T01:05:16.273372+00:00"},{"alias_kind":"pith_short_8","alias_value":"UQIUNHRB","created_at":"2026-06-08T01:05:16.273372+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/UQIUNHRBF676QMO7ZPZSQ5PHUT","json":"https://pith.science/pith/UQIUNHRBF676QMO7ZPZSQ5PHUT.json","graph_json":"https://pith.science/api/pith-number/UQIUNHRBF676QMO7ZPZSQ5PHUT/graph.json","events_json":"https://pith.science/api/pith-number/UQIUNHRBF676QMO7ZPZSQ5PHUT/events.json","paper":"https://pith.science/paper/UQIUNHRB"},"agent_actions":{"view_html":"https://pith.science/pith/UQIUNHRBF676QMO7ZPZSQ5PHUT","download_json":"https://pith.science/pith/UQIUNHRBF676QMO7ZPZSQ5PHUT.json","view_paper":"https://pith.science/paper/UQIUNHRB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07258&json=true","fetch_graph":"https://pith.science/api/pith-number/UQIUNHRBF676QMO7ZPZSQ5PHUT/graph.json","fetch_events":"https://pith.science/api/pith-number/UQIUNHRBF676QMO7ZPZSQ5PHUT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UQIUNHRBF676QMO7ZPZSQ5PHUT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UQIUNHRBF676QMO7ZPZSQ5PHUT/action/storage_attestation","attest_author":"https://pith.science/pith/UQIUNHRBF676QMO7ZPZSQ5PHUT/action/author_attestation","sign_citation":"https://pith.science/pith/UQIUNHRBF676QMO7ZPZSQ5PHUT/action/citation_signature","submit_replication":"https://pith.science/pith/UQIUNHRBF676QMO7ZPZSQ5PHUT/action/replication_record"}},"created_at":"2026-06-08T01:05:16.273372+00:00","updated_at":"2026-06-08T01:05:16.273372+00:00"}