{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:7USSD6OGEQ33IIIT34R5CBSPCK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c5458fb2de89a262cced29a612c02a4e7e2e763c7b2734764419211bec5f0188","cross_cats_sorted":["cs.AI","q-bio.BM","q-bio.QM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-18T18:32:48Z","title_canon_sha256":"251ddf340fe63f92bd31e72926ad25c2205fbca9a21451f5ce2a846407aad48b"},"schema_version":"1.0","source":{"id":"2208.09016","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.09016","created_at":"2026-07-05T05:56:14Z"},{"alias_kind":"arxiv_version","alias_value":"2208.09016v2","created_at":"2026-07-05T05:56:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.09016","created_at":"2026-07-05T05:56:14Z"},{"alias_kind":"pith_short_12","alias_value":"7USSD6OGEQ33","created_at":"2026-07-05T05:56:14Z"},{"alias_kind":"pith_short_16","alias_value":"7USSD6OGEQ33IIIT","created_at":"2026-07-05T05:56:14Z"},{"alias_kind":"pith_short_8","alias_value":"7USSD6OG","created_at":"2026-07-05T05:56:14Z"}],"graph_snapshots":[{"event_id":"sha256:58c1c5884b85c01661756249eca910c197f2ecc9bfca7ceb84b70f8e08364986","target":"graph","created_at":"2026-07-05T05:56:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2208.09016/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We address the task of controlled generation of small molecules, which entails finding novel molecules with desired properties under certain constraints (e.g., similarity to a reference molecule). Here we introduce MolMIM, a probabilistic auto-encoder for small molecule drug discovery that learns an informative and clustered latent space. MolMIM is trained with Mutual Information Machine (MIM) learning, and provides a fixed length representation of variable length SMILES strings. Since encoder-decoder models can learn representations with ``holes'' of invalid samples, here we propose a novel e","authors_text":"Danny Reidenbach, Johnny Israeli, Micha Livne, Michelle Gill, Rajesh K. Ilango","cross_cats":["cs.AI","q-bio.BM","q-bio.QM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-18T18:32:48Z","title":"Improving Small Molecule Generation using Mutual Information Machine"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.09016","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d97814ab26a6fa5f7a29f8dd3764038dadcf909fe209a95b119e3d6f5e23f45a","target":"record","created_at":"2026-07-05T05:56:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c5458fb2de89a262cced29a612c02a4e7e2e763c7b2734764419211bec5f0188","cross_cats_sorted":["cs.AI","q-bio.BM","q-bio.QM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-18T18:32:48Z","title_canon_sha256":"251ddf340fe63f92bd31e72926ad25c2205fbca9a21451f5ce2a846407aad48b"},"schema_version":"1.0","source":{"id":"2208.09016","kind":"arxiv","version":2}},"canonical_sha256":"fd2521f9c62437b42113df23d1064f129cb7f7c19b96c8b40edffe46e580b765","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd2521f9c62437b42113df23d1064f129cb7f7c19b96c8b40edffe46e580b765","first_computed_at":"2026-07-05T05:56:14.380472Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:56:14.380472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z0ONpqzYsKwhDzvllE9GQatiEWUCmX9YE91CxXf8bEqOwZGQ6J3D45lgTgbW1YxY5vhKa9MhfB22dv6AtO06AA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:56:14.380968Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.09016","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d97814ab26a6fa5f7a29f8dd3764038dadcf909fe209a95b119e3d6f5e23f45a","sha256:58c1c5884b85c01661756249eca910c197f2ecc9bfca7ceb84b70f8e08364986"],"state_sha256":"d88bee02e89d1ac71eb7c59219c37c1f3d2a0a606c0d43572b8b827620dafdfe"}