{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:2I6QUHYTNXKW6X3LZY2CXV5UAS","short_pith_number":"pith:2I6QUHYT","canonical_record":{"source":{"id":"1911.04738","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-12T08:44:49Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"765c94fb961e2eeeb8e679b6445199bde91f2795ac8ba836f5077c9e43f185ab","abstract_canon_sha256":"dfdfe15cc5ae7ff0a9e47788cfce9017e31d4540c5a33f06ea23b3c4d976884f"},"schema_version":"1.0"},"canonical_sha256":"d23d0a1f136dd56f5f6bce342bd7b404b75cf9fee00e26da4003f190e7a48293","source":{"kind":"arxiv","id":"1911.04738","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.04738","created_at":"2026-07-05T00:18:44Z"},{"alias_kind":"arxiv_version","alias_value":"1911.04738v1","created_at":"2026-07-05T00:18:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.04738","created_at":"2026-07-05T00:18:44Z"},{"alias_kind":"pith_short_12","alias_value":"2I6QUHYTNXKW","created_at":"2026-07-05T00:18:44Z"},{"alias_kind":"pith_short_16","alias_value":"2I6QUHYTNXKW6X3L","created_at":"2026-07-05T00:18:44Z"},{"alias_kind":"pith_short_8","alias_value":"2I6QUHYT","created_at":"2026-07-05T00:18:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:2I6QUHYTNXKW6X3LZY2CXV5UAS","target":"record","payload":{"canonical_record":{"source":{"id":"1911.04738","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-12T08:44:49Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"765c94fb961e2eeeb8e679b6445199bde91f2795ac8ba836f5077c9e43f185ab","abstract_canon_sha256":"dfdfe15cc5ae7ff0a9e47788cfce9017e31d4540c5a33f06ea23b3c4d976884f"},"schema_version":"1.0"},"canonical_sha256":"d23d0a1f136dd56f5f6bce342bd7b404b75cf9fee00e26da4003f190e7a48293","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:18:44.663650Z","signature_b64":"HWEhivvPa6mv2KFPbo/bQjMG1Ez/JUuqFlixYCnziA+p+JwqOwLd/z1J2O3PqFHdW+vHrmfAyqlzLgvBivI0CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d23d0a1f136dd56f5f6bce342bd7b404b75cf9fee00e26da4003f190e7a48293","last_reissued_at":"2026-07-05T00:18:44.663279Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:18:44.663279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1911.04738","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":"2026-07-05T00:18:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5hqVhyrNIMUbanDw9MYeSWE080w3gJba/hLEkLZRHT3JD7FZpG1mEsDlmRVxqsuHMlOD1ckyDASSLaydJNcJBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T22:13:56.168633Z"},"content_sha256":"60d9061200a36e903c0cc4b8eb1fc4754b486b365933284d52ad70dd35bebccc","schema_version":"1.0","event_id":"sha256:60d9061200a36e903c0cc4b8eb1fc4754b486b365933284d52ad70dd35bebccc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:2I6QUHYTNXKW6X3LZY2CXV5UAS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SMILES Transformer: Pre-trained Molecular Fingerprint for Low Data Drug Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hiroki R. Ueda, Shion Honda, Shoi Shi","submitted_at":"2019-11-12T08:44:49Z","abstract_excerpt":"In drug-discovery-related tasks such as virtual screening, machine learning is emerging as a promising way to predict molecular properties. Conventionally, molecular fingerprints (numerical representations of molecules) are calculated through rule-based algorithms that map molecules to a sparse discrete space. However, these algorithms perform poorly for shallow prediction models or small datasets. To address this issue, we present SMILES Transformer. Inspired by Transformer and pre-trained language models from natural language processing, SMILES Transformer learns molecular fingerprints throu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.04738","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/1911.04738/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":"2026-07-05T00:18:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YMk1eoZcwkY9Jd/7k+WtuxMPQEjmkk806jICdM1Aqikm2MD25xice4/kNHaZx40aTLtj7Q3FQmFiLEsv1TNcDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T22:13:56.169783Z"},"content_sha256":"01eceebdba84e043604d5bb89e62d179a772025e8c21d6275a76ed5f74cfbbb9","schema_version":"1.0","event_id":"sha256:01eceebdba84e043604d5bb89e62d179a772025e8c21d6275a76ed5f74cfbbb9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2I6QUHYTNXKW6X3LZY2CXV5UAS/bundle.json","state_url":"https://pith.science/pith/2I6QUHYTNXKW6X3LZY2CXV5UAS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2I6QUHYTNXKW6X3LZY2CXV5UAS/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":"2026-08-17T22:13:56Z","links":{"resolver":"https://pith.science/pith/2I6QUHYTNXKW6X3LZY2CXV5UAS","bundle":"https://pith.science/pith/2I6QUHYTNXKW6X3LZY2CXV5UAS/bundle.json","state":"https://pith.science/pith/2I6QUHYTNXKW6X3LZY2CXV5UAS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2I6QUHYTNXKW6X3LZY2CXV5UAS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:2I6QUHYTNXKW6X3LZY2CXV5UAS","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":"dfdfe15cc5ae7ff0a9e47788cfce9017e31d4540c5a33f06ea23b3c4d976884f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-12T08:44:49Z","title_canon_sha256":"765c94fb961e2eeeb8e679b6445199bde91f2795ac8ba836f5077c9e43f185ab"},"schema_version":"1.0","source":{"id":"1911.04738","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.04738","created_at":"2026-07-05T00:18:44Z"},{"alias_kind":"arxiv_version","alias_value":"1911.04738v1","created_at":"2026-07-05T00:18:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.04738","created_at":"2026-07-05T00:18:44Z"},{"alias_kind":"pith_short_12","alias_value":"2I6QUHYTNXKW","created_at":"2026-07-05T00:18:44Z"},{"alias_kind":"pith_short_16","alias_value":"2I6QUHYTNXKW6X3L","created_at":"2026-07-05T00:18:44Z"},{"alias_kind":"pith_short_8","alias_value":"2I6QUHYT","created_at":"2026-07-05T00:18:44Z"}],"graph_snapshots":[{"event_id":"sha256:01eceebdba84e043604d5bb89e62d179a772025e8c21d6275a76ed5f74cfbbb9","target":"graph","created_at":"2026-07-05T00:18:44Z","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/1911.04738/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In drug-discovery-related tasks such as virtual screening, machine learning is emerging as a promising way to predict molecular properties. Conventionally, molecular fingerprints (numerical representations of molecules) are calculated through rule-based algorithms that map molecules to a sparse discrete space. However, these algorithms perform poorly for shallow prediction models or small datasets. To address this issue, we present SMILES Transformer. Inspired by Transformer and pre-trained language models from natural language processing, SMILES Transformer learns molecular fingerprints throu","authors_text":"Hiroki R. Ueda, Shion Honda, Shoi Shi","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-12T08:44:49Z","title":"SMILES Transformer: Pre-trained Molecular Fingerprint for Low Data Drug Discovery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.04738","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":"sha256:60d9061200a36e903c0cc4b8eb1fc4754b486b365933284d52ad70dd35bebccc","target":"record","created_at":"2026-07-05T00:18:44Z","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":"dfdfe15cc5ae7ff0a9e47788cfce9017e31d4540c5a33f06ea23b3c4d976884f","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-12T08:44:49Z","title_canon_sha256":"765c94fb961e2eeeb8e679b6445199bde91f2795ac8ba836f5077c9e43f185ab"},"schema_version":"1.0","source":{"id":"1911.04738","kind":"arxiv","version":1}},"canonical_sha256":"d23d0a1f136dd56f5f6bce342bd7b404b75cf9fee00e26da4003f190e7a48293","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d23d0a1f136dd56f5f6bce342bd7b404b75cf9fee00e26da4003f190e7a48293","first_computed_at":"2026-07-05T00:18:44.663279Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:18:44.663279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HWEhivvPa6mv2KFPbo/bQjMG1Ez/JUuqFlixYCnziA+p+JwqOwLd/z1J2O3PqFHdW+vHrmfAyqlzLgvBivI0CA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:18:44.663650Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.04738","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60d9061200a36e903c0cc4b8eb1fc4754b486b365933284d52ad70dd35bebccc","sha256:01eceebdba84e043604d5bb89e62d179a772025e8c21d6275a76ed5f74cfbbb9"],"state_sha256":"52c9e04018cf6dfa6c63475d60834a79f8ef96453ecb62cf7b34b0802bcc287b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e8/oNJwB6wGLbCzySEbL0LDte5HIZixqULzaVN+qAuF0ykbclhjIAqQlKC9YUP3CdBssGS+UyWBqOwNyfHBvAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T22:13:56.185288Z","bundle_sha256":"4b87b5eaef7658164100bab9843fdd49b8ee53ff49527fb11c7eb555f4682aa0"}}