{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:S2SJUVB44S7G3RQ2GCT5GDLNOW","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":"2d9b3750ad1a3496331e94fecf6765290e5e4324d4479ebffa61a804546a7bf6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-06T15:16:40Z","title_canon_sha256":"e6173671a175c95ac9e8c4a632c161673b99d4afe6a3bd6c3cec301cd2f08019"},"schema_version":"1.0","source":{"id":"2606.08221","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08221","created_at":"2026-06-09T01:05:30Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08221v1","created_at":"2026-06-09T01:05:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08221","created_at":"2026-06-09T01:05:30Z"},{"alias_kind":"pith_short_12","alias_value":"S2SJUVB44S7G","created_at":"2026-06-09T01:05:30Z"},{"alias_kind":"pith_short_16","alias_value":"S2SJUVB44S7G3RQ2","created_at":"2026-06-09T01:05:30Z"},{"alias_kind":"pith_short_8","alias_value":"S2SJUVB4","created_at":"2026-06-09T01:05:30Z"}],"graph_snapshots":[{"event_id":"sha256:b326213385564e62453f454f855cc7d04655ab9e13ce651a52f3fba9084f9c5e","target":"graph","created_at":"2026-06-09T01:05:30Z","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/2606.08221/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Designing OLED molecules with targeted optical properties remains challenging due to the scarcity of high-quality data and the limited reliability of conditional control in generative models across chemical motifs. Here, we benchmark a token-conditioned autoregressive language model for OLED molecular generation in a realistic low-data regime. A GPT2 model is pretrained on large chemical corpora, augmented with discrete property tokens, and fine-tuned using multi-task optimisation. Conditioning targets vertical absorption energy and oscillator strength, with the HOMO-LUMO gap included as an au","authors_text":"Al\\'an Aspuru-Guzik, Haozhe Huang, Hyun Suk Park, Jorge A. Campos-Gonzalez-Angulo, Manuel Gonzalez Lastre, Xinjian Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-06T15:16:40Z","title":"De novo molecular generation with optical property preconditioning at the token level"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08221","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":"sha256:69d18ed9dba43fe12bfb63427341b765f7e6ce3c517e5ac4953859d88dbfa7b2","target":"record","created_at":"2026-06-09T01:05:30Z","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":"2d9b3750ad1a3496331e94fecf6765290e5e4324d4479ebffa61a804546a7bf6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-06T15:16:40Z","title_canon_sha256":"e6173671a175c95ac9e8c4a632c161673b99d4afe6a3bd6c3cec301cd2f08019"},"schema_version":"1.0","source":{"id":"2606.08221","kind":"arxiv","version":1}},"canonical_sha256":"96a49a543ce4be6dc61a30a7d30d6d758e9608fa8d1c333cdc05aae177afe95b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96a49a543ce4be6dc61a30a7d30d6d758e9608fa8d1c333cdc05aae177afe95b","first_computed_at":"2026-06-09T01:05:30.487503Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:30.487503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OFcdb4THOtRVaNt4EfFkukQyKfBSlgGexHxEAvdGxnBzk+eyAZpPbE8bL9oTHLe+u5to+XSREARYZC+M2vdtCw==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:30.487995Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08221","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:69d18ed9dba43fe12bfb63427341b765f7e6ce3c517e5ac4953859d88dbfa7b2","sha256:b326213385564e62453f454f855cc7d04655ab9e13ce651a52f3fba9084f9c5e"],"state_sha256":"30bdad7204f8e352000b5ff666f85c0b8c1deab7eb905b24b23c823acb6474fa"}