{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CWS3F3J7VEZQQUI4UAJVHGHSE3","short_pith_number":"pith:CWS3F3J7","canonical_record":{"source":{"id":"2507.10273","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-14T13:42:39Z","cross_cats_sorted":["q-bio.BM"],"title_canon_sha256":"673086a8160d819e38eebec4ccca1cf906b660483dce93d38c7c311439262b59","abstract_canon_sha256":"f1b60609bee9f10f531c4aeb5f4ca1b99dbc2d18e82d78019c043918c72b8fc9"},"schema_version":"1.0"},"canonical_sha256":"15a5b2ed3fa93308511ca0135398f226d03c9ccda9d58a3639754580a0814b2c","source":{"kind":"arxiv","id":"2507.10273","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.10273","created_at":"2026-07-05T11:36:48Z"},{"alias_kind":"arxiv_version","alias_value":"2507.10273v1","created_at":"2026-07-05T11:36:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10273","created_at":"2026-07-05T11:36:48Z"},{"alias_kind":"pith_short_12","alias_value":"CWS3F3J7VEZQ","created_at":"2026-07-05T11:36:48Z"},{"alias_kind":"pith_short_16","alias_value":"CWS3F3J7VEZQQUI4","created_at":"2026-07-05T11:36:48Z"},{"alias_kind":"pith_short_8","alias_value":"CWS3F3J7","created_at":"2026-07-05T11:36:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CWS3F3J7VEZQQUI4UAJVHGHSE3","target":"record","payload":{"canonical_record":{"source":{"id":"2507.10273","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-14T13:42:39Z","cross_cats_sorted":["q-bio.BM"],"title_canon_sha256":"673086a8160d819e38eebec4ccca1cf906b660483dce93d38c7c311439262b59","abstract_canon_sha256":"f1b60609bee9f10f531c4aeb5f4ca1b99dbc2d18e82d78019c043918c72b8fc9"},"schema_version":"1.0"},"canonical_sha256":"15a5b2ed3fa93308511ca0135398f226d03c9ccda9d58a3639754580a0814b2c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:48.383919Z","signature_b64":"Xrh+TWXYB4rxx3JSxbPpDEbhKyfuMrMiMa12lFO6i++VF1ZaoYxAD48LsidL302NPB7zt9/Cmg924mIk/XEhAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15a5b2ed3fa93308511ca0135398f226d03c9ccda9d58a3639754580a0814b2c","last_reissued_at":"2026-07-05T11:36:48.383320Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:48.383320Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.10273","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":"2026-07-05T11:36:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3g8jn7npceYdvXQyc3nXimABRtRbLsPYK3FUNT+7JCJWj4a3D1w1mZ4IU6k21GMgwLcrBrD4HpmhVixlj0wwCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:24:50.855042Z"},"content_sha256":"1a1781c4fb76c4afe7d43467475dc507df220fc0872dadc920d074fb894d664d","schema_version":"1.0","event_id":"sha256:1a1781c4fb76c4afe7d43467475dc507df220fc0872dadc920d074fb894d664d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CWS3F3J7VEZQQUI4UAJVHGHSE3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Conditional Chemical Language Models are Versatile Tools in Drug Discovery","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Emmanuel Noutahi, Lu Zhu","submitted_at":"2025-07-14T13:42:39Z","abstract_excerpt":"Generative chemical language models (CLMs) have demonstrated strong capabilities in molecular design, yet their impact in drug discovery remains limited by the absence of reliable reward signals and the lack of interpretability in their outputs. We present SAFE-T, a generalist chemical modeling framework that conditions on biological context -- such as protein targets or mechanisms of action -- to prioritize and design molecules without relying on structural information or engineered scoring functions. SAFE-T models the conditional likelihood of fragment-based molecular sequences given a biolo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10273","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/2507.10273/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":"2026-07-05T11:36:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ALHmfTezJ3/rqdIaAnG2wKyuRCYQTH1tizAyTm1abNv8WM/QPL+WsnyZaBFmnNVUe3QeMrTC568m/+yTXBUbCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:24:50.855732Z"},"content_sha256":"8cacf1669b5cf81001cc8e10b125ba7b72624ac1e131cd5bd87e8ff4ea80a84e","schema_version":"1.0","event_id":"sha256:8cacf1669b5cf81001cc8e10b125ba7b72624ac1e131cd5bd87e8ff4ea80a84e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CWS3F3J7VEZQQUI4UAJVHGHSE3/bundle.json","state_url":"https://pith.science/pith/CWS3F3J7VEZQQUI4UAJVHGHSE3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CWS3F3J7VEZQQUI4UAJVHGHSE3/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":"2026-08-08T18:24:50Z","links":{"resolver":"https://pith.science/pith/CWS3F3J7VEZQQUI4UAJVHGHSE3","bundle":"https://pith.science/pith/CWS3F3J7VEZQQUI4UAJVHGHSE3/bundle.json","state":"https://pith.science/pith/CWS3F3J7VEZQQUI4UAJVHGHSE3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CWS3F3J7VEZQQUI4UAJVHGHSE3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CWS3F3J7VEZQQUI4UAJVHGHSE3","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":"f1b60609bee9f10f531c4aeb5f4ca1b99dbc2d18e82d78019c043918c72b8fc9","cross_cats_sorted":["q-bio.BM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-14T13:42:39Z","title_canon_sha256":"673086a8160d819e38eebec4ccca1cf906b660483dce93d38c7c311439262b59"},"schema_version":"1.0","source":{"id":"2507.10273","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.10273","created_at":"2026-07-05T11:36:48Z"},{"alias_kind":"arxiv_version","alias_value":"2507.10273v1","created_at":"2026-07-05T11:36:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10273","created_at":"2026-07-05T11:36:48Z"},{"alias_kind":"pith_short_12","alias_value":"CWS3F3J7VEZQ","created_at":"2026-07-05T11:36:48Z"},{"alias_kind":"pith_short_16","alias_value":"CWS3F3J7VEZQQUI4","created_at":"2026-07-05T11:36:48Z"},{"alias_kind":"pith_short_8","alias_value":"CWS3F3J7","created_at":"2026-07-05T11:36:48Z"}],"graph_snapshots":[{"event_id":"sha256:8cacf1669b5cf81001cc8e10b125ba7b72624ac1e131cd5bd87e8ff4ea80a84e","target":"graph","created_at":"2026-07-05T11:36:48Z","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/2507.10273/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative chemical language models (CLMs) have demonstrated strong capabilities in molecular design, yet their impact in drug discovery remains limited by the absence of reliable reward signals and the lack of interpretability in their outputs. We present SAFE-T, a generalist chemical modeling framework that conditions on biological context -- such as protein targets or mechanisms of action -- to prioritize and design molecules without relying on structural information or engineered scoring functions. SAFE-T models the conditional likelihood of fragment-based molecular sequences given a biolo","authors_text":"Emmanuel Noutahi, Lu Zhu","cross_cats":["q-bio.BM"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-14T13:42:39Z","title":"Conditional Chemical Language Models are Versatile Tools in Drug Discovery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10273","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":"sha256:1a1781c4fb76c4afe7d43467475dc507df220fc0872dadc920d074fb894d664d","target":"record","created_at":"2026-07-05T11:36:48Z","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":"f1b60609bee9f10f531c4aeb5f4ca1b99dbc2d18e82d78019c043918c72b8fc9","cross_cats_sorted":["q-bio.BM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-14T13:42:39Z","title_canon_sha256":"673086a8160d819e38eebec4ccca1cf906b660483dce93d38c7c311439262b59"},"schema_version":"1.0","source":{"id":"2507.10273","kind":"arxiv","version":1}},"canonical_sha256":"15a5b2ed3fa93308511ca0135398f226d03c9ccda9d58a3639754580a0814b2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15a5b2ed3fa93308511ca0135398f226d03c9ccda9d58a3639754580a0814b2c","first_computed_at":"2026-07-05T11:36:48.383320Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:48.383320Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Xrh+TWXYB4rxx3JSxbPpDEbhKyfuMrMiMa12lFO6i++VF1ZaoYxAD48LsidL302NPB7zt9/Cmg924mIk/XEhAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:48.383919Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.10273","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a1781c4fb76c4afe7d43467475dc507df220fc0872dadc920d074fb894d664d","sha256:8cacf1669b5cf81001cc8e10b125ba7b72624ac1e131cd5bd87e8ff4ea80a84e"],"state_sha256":"ccba974348cb5948a5b5451cf5a1b87da0d8d2678eb8a0ab4cabf4320f5ae08e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bj4HfxgjbZuznbJgbRTAG0cDgtqAG1qNxLJEQu9X00u0Y+9eVt+lLgoWBHmeVk+u3ICSMOSgPMwIVoDZ5+8oDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:24:50.861112Z","bundle_sha256":"3a944578f15d6910e73f3b1d50429541142395c249be3fb0af79cfd6d4e9236e"}}