{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GGULXS7OXWP4CCSOAS4RSEHMO7","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":"c307a54b842f31ce0074bc287f7ec61c7174acba1c2bf0be197dfb2912a67b83","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-19T00:04:48Z","title_canon_sha256":"e5c7ae83651b65ae3bbe218bae614d0e839bec2e06e81942e9e41fca6299c4fa"},"schema_version":"1.0","source":{"id":"2508.13408","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.13408","created_at":"2026-07-05T11:57:39Z"},{"alias_kind":"arxiv_version","alias_value":"2508.13408v2","created_at":"2026-07-05T11:57:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.13408","created_at":"2026-07-05T11:57:39Z"},{"alias_kind":"pith_short_12","alias_value":"GGULXS7OXWP4","created_at":"2026-07-05T11:57:39Z"},{"alias_kind":"pith_short_16","alias_value":"GGULXS7OXWP4CCSO","created_at":"2026-07-05T11:57:39Z"},{"alias_kind":"pith_short_8","alias_value":"GGULXS7O","created_at":"2026-07-05T11:57:39Z"}],"graph_snapshots":[{"event_id":"sha256:0cdd83e76d293e0749bd49f71225660b91609d6d6e79128f5f5d9ee53d2d6500","target":"graph","created_at":"2026-07-05T11:57:39Z","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/2508.13408/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Designing de-novo molecules with desired property profiles requires efficient exploration of the vast chemical space ranging from $10^{23}$ to $10^{60}$ possible synthesizable candidates. While various deep generative models have been developed to design small molecules using diverse input representations, Molecular Large Language Models (Mol-LLMs) based on string representations have emerged as a scalable approach capable of exploring billions of molecules. However, there remains limited understanding regarding how standard language modeling practices such as textual representations, tokeniza","authors_text":"Kamran Chitsaz, Nirav Pravinbhai Bhatt, Quentin Fournier, Roshan Balaji, Sarath Chandar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-19T00:04:48Z","title":"NovoMolGen: Rethinking Molecular Language Model Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.13408","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:dd3c80653eea9adb0f92e47adb65a750eda71a5602249f86ba85897f980bd9fc","target":"record","created_at":"2026-07-05T11:57:39Z","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":"c307a54b842f31ce0074bc287f7ec61c7174acba1c2bf0be197dfb2912a67b83","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-19T00:04:48Z","title_canon_sha256":"e5c7ae83651b65ae3bbe218bae614d0e839bec2e06e81942e9e41fca6299c4fa"},"schema_version":"1.0","source":{"id":"2508.13408","kind":"arxiv","version":2}},"canonical_sha256":"31a8bbcbeebd9fc10a4e04b91910ec77cd67ec0f71414fb969e6e1fbb2f76b1e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31a8bbcbeebd9fc10a4e04b91910ec77cd67ec0f71414fb969e6e1fbb2f76b1e","first_computed_at":"2026-07-05T11:57:39.013847Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:57:39.013847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oYdOlhvd7tZ8iw0NJ1Din1LY1tHyjXdvaYjURFJ25iIdXB4zuMQTaGPohxZ4RB1cjOnV6EFph5HCoqrmF+XzDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:57:39.014299Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.13408","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd3c80653eea9adb0f92e47adb65a750eda71a5602249f86ba85897f980bd9fc","sha256:0cdd83e76d293e0749bd49f71225660b91609d6d6e79128f5f5d9ee53d2d6500"],"state_sha256":"bf24b8f074e1cb7c450511cb34cedfdc4287dc9824daca3636c338ade9220454"}