{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BQ2PX54KYAZGNUMUDNLBZOYL2G","short_pith_number":"pith:BQ2PX54K","schema_version":"1.0","canonical_sha256":"0c34fbf78ac03266d1941b561cbb0bd1a4a46abad3b6b9490f26214c42a0b349","source":{"kind":"arxiv","id":"1905.09885","version":1},"attestation_state":"computed","paper":{"title":"A COLD Approach to Generating Optimal Samples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.BM","q-bio.QM","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jos\\'e Miguel Hern\\'andez-Lobato, Omar Mahmood","submitted_at":"2019-05-23T19:32:03Z","abstract_excerpt":"Optimising discrete data for a desired characteristic using gradient-based methods involves projecting the data into a continuous latent space and carrying out optimisation in this space. Carrying out global optimisation is difficult as optimisers are likely to follow gradients into regions of the latent space that the model has not been exposed to during training; samples generated from these regions are likely to be too dissimilar to the training data to be useful. We propose Constrained Optimisation with Latent Distributions (COLD), a constrained global optimisation procedure to find sample"},"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":"1905.09885","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-23T19:32:03Z","cross_cats_sorted":["q-bio.BM","q-bio.QM","stat.ML"],"title_canon_sha256":"a1ed63d548c31a8a203c5fe8731e844f192390f63bb541eb2908a9d21edd5d80","abstract_canon_sha256":"979042869eca68ffa0291c536b2f7c811ee5921a6a2fcd5d4c73e57ae1aaf501"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:14.163162Z","signature_b64":"9u1UsicYsAWp06YE2qPzkZmsWkkaWxrCHC+43dIH9pGkhPM1OupqnQx3wxP2Re8gWtVRaE/ruy2+uVowPflpAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c34fbf78ac03266d1941b561cbb0bd1a4a46abad3b6b9490f26214c42a0b349","last_reissued_at":"2026-05-17T23:45:14.162513Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:14.162513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A COLD Approach to Generating Optimal Samples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.BM","q-bio.QM","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jos\\'e Miguel Hern\\'andez-Lobato, Omar Mahmood","submitted_at":"2019-05-23T19:32:03Z","abstract_excerpt":"Optimising discrete data for a desired characteristic using gradient-based methods involves projecting the data into a continuous latent space and carrying out optimisation in this space. Carrying out global optimisation is difficult as optimisers are likely to follow gradients into regions of the latent space that the model has not been exposed to during training; samples generated from these regions are likely to be too dissimilar to the training data to be useful. We propose Constrained Optimisation with Latent Distributions (COLD), a constrained global optimisation procedure to find sample"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.09885","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":""},"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":"1905.09885","created_at":"2026-05-17T23:45:14.162591+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.09885v1","created_at":"2026-05-17T23:45:14.162591+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.09885","created_at":"2026-05-17T23:45:14.162591+00:00"},{"alias_kind":"pith_short_12","alias_value":"BQ2PX54KYAZG","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"BQ2PX54KYAZGNUMU","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"BQ2PX54K","created_at":"2026-05-18T12:33:12.712433+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/BQ2PX54KYAZGNUMUDNLBZOYL2G","json":"https://pith.science/pith/BQ2PX54KYAZGNUMUDNLBZOYL2G.json","graph_json":"https://pith.science/api/pith-number/BQ2PX54KYAZGNUMUDNLBZOYL2G/graph.json","events_json":"https://pith.science/api/pith-number/BQ2PX54KYAZGNUMUDNLBZOYL2G/events.json","paper":"https://pith.science/paper/BQ2PX54K"},"agent_actions":{"view_html":"https://pith.science/pith/BQ2PX54KYAZGNUMUDNLBZOYL2G","download_json":"https://pith.science/pith/BQ2PX54KYAZGNUMUDNLBZOYL2G.json","view_paper":"https://pith.science/paper/BQ2PX54K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.09885&json=true","fetch_graph":"https://pith.science/api/pith-number/BQ2PX54KYAZGNUMUDNLBZOYL2G/graph.json","fetch_events":"https://pith.science/api/pith-number/BQ2PX54KYAZGNUMUDNLBZOYL2G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BQ2PX54KYAZGNUMUDNLBZOYL2G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BQ2PX54KYAZGNUMUDNLBZOYL2G/action/storage_attestation","attest_author":"https://pith.science/pith/BQ2PX54KYAZGNUMUDNLBZOYL2G/action/author_attestation","sign_citation":"https://pith.science/pith/BQ2PX54KYAZGNUMUDNLBZOYL2G/action/citation_signature","submit_replication":"https://pith.science/pith/BQ2PX54KYAZGNUMUDNLBZOYL2G/action/replication_record"}},"created_at":"2026-05-17T23:45:14.162591+00:00","updated_at":"2026-05-17T23:45:14.162591+00:00"}