{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3MGQXSQZVEEFJHXTJCI47KDJQB","short_pith_number":"pith:3MGQXSQZ","schema_version":"1.0","canonical_sha256":"db0d0bca19a908549ef34891cfa8698062c656e0ef98360f5d6a599c3be1c235","source":{"kind":"arxiv","id":"2405.18075","version":1},"attestation_state":"computed","paper":{"title":"Implicitly Guided Design with PropEn: Match your Data to Follow the Gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andreas Loukas, Kyunghyun Cho, Nata\\v{s}a Tagasovska, Vladimir Gligorijevi\\'c","submitted_at":"2024-05-28T11:30:19Z","abstract_excerpt":"Across scientific domains, generating new models or optimizing existing ones while meeting specific criteria is crucial. Traditional machine learning frameworks for guided design use a generative model and a surrogate model (discriminator), requiring large datasets. However, real-world scientific applications often have limited data and complex landscapes, making data-hungry models inefficient or impractical. We propose a new framework, PropEn, inspired by ``matching'', which enables implicit guidance without training a discriminator. By matching each sample with a similar one that has a bette"},"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":"2405.18075","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T11:30:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"aabe8323854b6a0a2aebbd6ab3fd9386effd9bc10db4775df87f61bad1936974","abstract_canon_sha256":"3f6dd0e56fff593a581cd09f3bc0710ae082e9c347516aee05f63b46e107c0f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:15.350669Z","signature_b64":"1TuM1EZrM9eWoMZ7aBagsd95QMTSWLFGEVMbZi+g87r7hf0sTuRNj2bD97pP06Cjk8Vc8DWkQ1IpHSVTRS+qBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db0d0bca19a908549ef34891cfa8698062c656e0ef98360f5d6a599c3be1c235","last_reissued_at":"2026-07-05T08:24:15.350193Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:15.350193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Implicitly Guided Design with PropEn: Match your Data to Follow the Gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andreas Loukas, Kyunghyun Cho, Nata\\v{s}a Tagasovska, Vladimir Gligorijevi\\'c","submitted_at":"2024-05-28T11:30:19Z","abstract_excerpt":"Across scientific domains, generating new models or optimizing existing ones while meeting specific criteria is crucial. Traditional machine learning frameworks for guided design use a generative model and a surrogate model (discriminator), requiring large datasets. However, real-world scientific applications often have limited data and complex landscapes, making data-hungry models inefficient or impractical. We propose a new framework, PropEn, inspired by ``matching'', which enables implicit guidance without training a discriminator. By matching each sample with a similar one that has a bette"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18075","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/2405.18075/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":"2405.18075","created_at":"2026-07-05T08:24:15.350249+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.18075v1","created_at":"2026-07-05T08:24:15.350249+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18075","created_at":"2026-07-05T08:24:15.350249+00:00"},{"alias_kind":"pith_short_12","alias_value":"3MGQXSQZVEEF","created_at":"2026-07-05T08:24:15.350249+00:00"},{"alias_kind":"pith_short_16","alias_value":"3MGQXSQZVEEFJHXT","created_at":"2026-07-05T08:24:15.350249+00:00"},{"alias_kind":"pith_short_8","alias_value":"3MGQXSQZ","created_at":"2026-07-05T08:24:15.350249+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.09103","citing_title":"Similarity-Quantized Relative Difference Learning for Improved Molecular Activity Prediction","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3MGQXSQZVEEFJHXTJCI47KDJQB","json":"https://pith.science/pith/3MGQXSQZVEEFJHXTJCI47KDJQB.json","graph_json":"https://pith.science/api/pith-number/3MGQXSQZVEEFJHXTJCI47KDJQB/graph.json","events_json":"https://pith.science/api/pith-number/3MGQXSQZVEEFJHXTJCI47KDJQB/events.json","paper":"https://pith.science/paper/3MGQXSQZ"},"agent_actions":{"view_html":"https://pith.science/pith/3MGQXSQZVEEFJHXTJCI47KDJQB","download_json":"https://pith.science/pith/3MGQXSQZVEEFJHXTJCI47KDJQB.json","view_paper":"https://pith.science/paper/3MGQXSQZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.18075&json=true","fetch_graph":"https://pith.science/api/pith-number/3MGQXSQZVEEFJHXTJCI47KDJQB/graph.json","fetch_events":"https://pith.science/api/pith-number/3MGQXSQZVEEFJHXTJCI47KDJQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3MGQXSQZVEEFJHXTJCI47KDJQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3MGQXSQZVEEFJHXTJCI47KDJQB/action/storage_attestation","attest_author":"https://pith.science/pith/3MGQXSQZVEEFJHXTJCI47KDJQB/action/author_attestation","sign_citation":"https://pith.science/pith/3MGQXSQZVEEFJHXTJCI47KDJQB/action/citation_signature","submit_replication":"https://pith.science/pith/3MGQXSQZVEEFJHXTJCI47KDJQB/action/replication_record"}},"created_at":"2026-07-05T08:24:15.350249+00:00","updated_at":"2026-07-05T08:24:15.350249+00:00"}