{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:J66HEQT3TR6L2QI5PMAGRNJM62","short_pith_number":"pith:J66HEQT3","schema_version":"1.0","canonical_sha256":"4fbc72427b9c7cbd411d7b0068b52cf69a15b64c02d50ef16315993ee797d939","source":{"kind":"arxiv","id":"2508.10775","version":1},"attestation_state":"computed","paper":{"title":"IBEX: Information-Bottleneck-EXplored Coarse-to-Fine Molecular Generation under Limited Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Dong Xu, Jenna Xinyi Yao, Junkai Ji, Shuangbao Song, Zexuan Zhu, Zhangfan Yang","submitted_at":"2025-08-14T15:59:22Z","abstract_excerpt":"Three-dimensional generative models increasingly drive structure-based drug discovery, yet it remains constrained by the scarce publicly available protein-ligand complexes. Under such data scarcity, almost all existing pipelines struggle to learn transferable geometric priors and consequently overfit to training-set biases. As such, we present IBEX, an Information-Bottleneck-EXplored coarse-to-fine pipeline to tackle the chronic shortage of protein-ligand complex data in structure-based drug design. Specifically, we use PAC-Bayesian information-bottleneck theory to quantify the information den"},"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":"2508.10775","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-14T15:59:22Z","cross_cats_sorted":["q-bio.BM"],"title_canon_sha256":"efa7d683c3b1b51eefd536188687fcdcfdf644a569f0165623c1e85d0a8bbb8e","abstract_canon_sha256":"2673df5e7e76f19c176ee5a617eb17e3407c95643c5e8f6c1cd63a62b27afc4c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:02.332572Z","signature_b64":"KN65Q9S8uFqqtWHZzC24jnEIxKGvd8Ib8oju8evNUGYdbexiQ2oV0M7FxQA+1LO7PR8YPB+RW5dk0M4AKdaLDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4fbc72427b9c7cbd411d7b0068b52cf69a15b64c02d50ef16315993ee797d939","last_reissued_at":"2026-07-05T11:54:02.332096Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:02.332096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IBEX: Information-Bottleneck-EXplored Coarse-to-Fine Molecular Generation under Limited Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Dong Xu, Jenna Xinyi Yao, Junkai Ji, Shuangbao Song, Zexuan Zhu, Zhangfan Yang","submitted_at":"2025-08-14T15:59:22Z","abstract_excerpt":"Three-dimensional generative models increasingly drive structure-based drug discovery, yet it remains constrained by the scarce publicly available protein-ligand complexes. Under such data scarcity, almost all existing pipelines struggle to learn transferable geometric priors and consequently overfit to training-set biases. As such, we present IBEX, an Information-Bottleneck-EXplored coarse-to-fine pipeline to tackle the chronic shortage of protein-ligand complex data in structure-based drug design. Specifically, we use PAC-Bayesian information-bottleneck theory to quantify the information den"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10775","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/2508.10775/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":"2508.10775","created_at":"2026-07-05T11:54:02.332154+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.10775v1","created_at":"2026-07-05T11:54:02.332154+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10775","created_at":"2026-07-05T11:54:02.332154+00:00"},{"alias_kind":"pith_short_12","alias_value":"J66HEQT3TR6L","created_at":"2026-07-05T11:54:02.332154+00:00"},{"alias_kind":"pith_short_16","alias_value":"J66HEQT3TR6L2QI5","created_at":"2026-07-05T11:54:02.332154+00:00"},{"alias_kind":"pith_short_8","alias_value":"J66HEQT3","created_at":"2026-07-05T11:54:02.332154+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20545","citing_title":"Sample Complexity of Transfer Learning: An Optimal Transport Approach","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J66HEQT3TR6L2QI5PMAGRNJM62","json":"https://pith.science/pith/J66HEQT3TR6L2QI5PMAGRNJM62.json","graph_json":"https://pith.science/api/pith-number/J66HEQT3TR6L2QI5PMAGRNJM62/graph.json","events_json":"https://pith.science/api/pith-number/J66HEQT3TR6L2QI5PMAGRNJM62/events.json","paper":"https://pith.science/paper/J66HEQT3"},"agent_actions":{"view_html":"https://pith.science/pith/J66HEQT3TR6L2QI5PMAGRNJM62","download_json":"https://pith.science/pith/J66HEQT3TR6L2QI5PMAGRNJM62.json","view_paper":"https://pith.science/paper/J66HEQT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.10775&json=true","fetch_graph":"https://pith.science/api/pith-number/J66HEQT3TR6L2QI5PMAGRNJM62/graph.json","fetch_events":"https://pith.science/api/pith-number/J66HEQT3TR6L2QI5PMAGRNJM62/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J66HEQT3TR6L2QI5PMAGRNJM62/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J66HEQT3TR6L2QI5PMAGRNJM62/action/storage_attestation","attest_author":"https://pith.science/pith/J66HEQT3TR6L2QI5PMAGRNJM62/action/author_attestation","sign_citation":"https://pith.science/pith/J66HEQT3TR6L2QI5PMAGRNJM62/action/citation_signature","submit_replication":"https://pith.science/pith/J66HEQT3TR6L2QI5PMAGRNJM62/action/replication_record"}},"created_at":"2026-07-05T11:54:02.332154+00:00","updated_at":"2026-07-05T11:54:02.332154+00:00"}