{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RJIRK776VNSSS3U2QEZCH6EEGL","short_pith_number":"pith:RJIRK776","canonical_record":{"source":{"id":"2407.13780","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2024-07-02T16:01:37Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"1450df9641591964198ed5732116dbc5c9898e571fc687d3c517af61512bad20","abstract_canon_sha256":"044b453b5c4467cc4e54ff5f17afa39d7ee21188538e0e32bf018c0b5522aa93"},"schema_version":"1.0"},"canonical_sha256":"8a51157ffeab65296e9a813223f88432f348f802b07c75ffd10dbd60175212c4","source":{"kind":"arxiv","id":"2407.13780","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.13780","created_at":"2026-07-05T08:45:53Z"},{"alias_kind":"arxiv_version","alias_value":"2407.13780v1","created_at":"2026-07-05T08:45:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13780","created_at":"2026-07-05T08:45:53Z"},{"alias_kind":"pith_short_12","alias_value":"RJIRK776VNSS","created_at":"2026-07-05T08:45:53Z"},{"alias_kind":"pith_short_16","alias_value":"RJIRK776VNSSS3U2","created_at":"2026-07-05T08:45:53Z"},{"alias_kind":"pith_short_8","alias_value":"RJIRK776","created_at":"2026-07-05T08:45:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RJIRK776VNSSS3U2QEZCH6EEGL","target":"record","payload":{"canonical_record":{"source":{"id":"2407.13780","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2024-07-02T16:01:37Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"1450df9641591964198ed5732116dbc5c9898e571fc687d3c517af61512bad20","abstract_canon_sha256":"044b453b5c4467cc4e54ff5f17afa39d7ee21188538e0e32bf018c0b5522aa93"},"schema_version":"1.0"},"canonical_sha256":"8a51157ffeab65296e9a813223f88432f348f802b07c75ffd10dbd60175212c4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:53.294279Z","signature_b64":"6qPDw7EgdgXvhks0aDQFs/WSt5TRkA2/kgCDm28o1kGHJyhKdYa+hAua45IZ1IGRsnGcC09cA3ZCWCBb/NK7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a51157ffeab65296e9a813223f88432f348f802b07c75ffd10dbd60175212c4","last_reissued_at":"2026-07-05T08:45:53.293869Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:53.293869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.13780","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:45:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"boLJJ0VMTV+P2lYU9syRctCwJMz60NOAB07t+mkbav6QORwofh/B43eDBNoO1nqP0ARvk8S1YBBUkgYivWTvCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:48:27.928643Z"},"content_sha256":"13622f875ee9fd73b3f204bf69535a9287e556ae0ad2bf0265780f95ffcb0492","schema_version":"1.0","event_id":"sha256:13622f875ee9fd73b3f204bf69535a9287e556ae0ad2bf0265780f95ffcb0492"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RJIRK776VNSSS3U2QEZCH6EEGL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generative Model for Small Molecules with Latent Space RL Fine-Tuning to Protein Targets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Andries P. Smit, Arnu Pretorius, Miguel Arbes\\'u, Oliver Bent, Qiulin Li, Ulrich A. Mbou Sob","submitted_at":"2024-07-02T16:01:37Z","abstract_excerpt":"A specific challenge with deep learning approaches for molecule generation is generating both syntactically valid and chemically plausible molecular string representations. To address this, we propose a novel generative latent-variable transformer model for small molecules that leverages a recently proposed molecular string representation called SAFE. We introduce a modification to SAFE to reduce the number of invalid fragmented molecules generated during training and use this to train our model. Our experiments show that our model can generate novel molecules with a validity rate > 90% and a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13780","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/2407.13780/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:45:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ybvBw+HDaUor8xy6YC+BfXekeif76r6O1OuWn3QCetShuflbdRbRx2rSjrJSYWMsDoxWe396J2GzONLQWcCtDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:48:27.929030Z"},"content_sha256":"c2b104aa48193ead64d7a54237930cf5dc5349015c9cc1c7e16615fbe25627ac","schema_version":"1.0","event_id":"sha256:c2b104aa48193ead64d7a54237930cf5dc5349015c9cc1c7e16615fbe25627ac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RJIRK776VNSSS3U2QEZCH6EEGL/bundle.json","state_url":"https://pith.science/pith/RJIRK776VNSSS3U2QEZCH6EEGL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RJIRK776VNSSS3U2QEZCH6EEGL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T08:48:27Z","links":{"resolver":"https://pith.science/pith/RJIRK776VNSSS3U2QEZCH6EEGL","bundle":"https://pith.science/pith/RJIRK776VNSSS3U2QEZCH6EEGL/bundle.json","state":"https://pith.science/pith/RJIRK776VNSSS3U2QEZCH6EEGL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RJIRK776VNSSS3U2QEZCH6EEGL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RJIRK776VNSSS3U2QEZCH6EEGL","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":"044b453b5c4467cc4e54ff5f17afa39d7ee21188538e0e32bf018c0b5522aa93","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2024-07-02T16:01:37Z","title_canon_sha256":"1450df9641591964198ed5732116dbc5c9898e571fc687d3c517af61512bad20"},"schema_version":"1.0","source":{"id":"2407.13780","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.13780","created_at":"2026-07-05T08:45:53Z"},{"alias_kind":"arxiv_version","alias_value":"2407.13780v1","created_at":"2026-07-05T08:45:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13780","created_at":"2026-07-05T08:45:53Z"},{"alias_kind":"pith_short_12","alias_value":"RJIRK776VNSS","created_at":"2026-07-05T08:45:53Z"},{"alias_kind":"pith_short_16","alias_value":"RJIRK776VNSSS3U2","created_at":"2026-07-05T08:45:53Z"},{"alias_kind":"pith_short_8","alias_value":"RJIRK776","created_at":"2026-07-05T08:45:53Z"}],"graph_snapshots":[{"event_id":"sha256:c2b104aa48193ead64d7a54237930cf5dc5349015c9cc1c7e16615fbe25627ac","target":"graph","created_at":"2026-07-05T08:45:53Z","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/2407.13780/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A specific challenge with deep learning approaches for molecule generation is generating both syntactically valid and chemically plausible molecular string representations. To address this, we propose a novel generative latent-variable transformer model for small molecules that leverages a recently proposed molecular string representation called SAFE. We introduce a modification to SAFE to reduce the number of invalid fragmented molecules generated during training and use this to train our model. Our experiments show that our model can generate novel molecules with a validity rate > 90% and a ","authors_text":"Andries P. Smit, Arnu Pretorius, Miguel Arbes\\'u, Oliver Bent, Qiulin Li, Ulrich A. Mbou Sob","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2024-07-02T16:01:37Z","title":"Generative Model for Small Molecules with Latent Space RL Fine-Tuning to Protein Targets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13780","kind":"arxiv","version":1},"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":"sha256:13622f875ee9fd73b3f204bf69535a9287e556ae0ad2bf0265780f95ffcb0492","target":"record","created_at":"2026-07-05T08:45:53Z","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":"044b453b5c4467cc4e54ff5f17afa39d7ee21188538e0e32bf018c0b5522aa93","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2024-07-02T16:01:37Z","title_canon_sha256":"1450df9641591964198ed5732116dbc5c9898e571fc687d3c517af61512bad20"},"schema_version":"1.0","source":{"id":"2407.13780","kind":"arxiv","version":1}},"canonical_sha256":"8a51157ffeab65296e9a813223f88432f348f802b07c75ffd10dbd60175212c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a51157ffeab65296e9a813223f88432f348f802b07c75ffd10dbd60175212c4","first_computed_at":"2026-07-05T08:45:53.293869Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:53.293869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6qPDw7EgdgXvhks0aDQFs/WSt5TRkA2/kgCDm28o1kGHJyhKdYa+hAua45IZ1IGRsnGcC09cA3ZCWCBb/NK7DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:53.294279Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.13780","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:13622f875ee9fd73b3f204bf69535a9287e556ae0ad2bf0265780f95ffcb0492","sha256:c2b104aa48193ead64d7a54237930cf5dc5349015c9cc1c7e16615fbe25627ac"],"state_sha256":"404b980095ee1adcb323d08a70166fceb4f405fed13ede4e9cd880f4e551983d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o4No7abE2lBEcw2Y8M0hlZUah4nlVRwlMyvUsHnOWOGbxhgK5vB6lmGfLm9dX46DU31UZaYXDia38/SaAu6TDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T08:48:27.931323Z","bundle_sha256":"69129baa0d16f8a35e452b2d3c2c74f8ec3b6966d4620628747c03c756ffa06c"}}