{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VIBTUCNGBM5GZODTAN4SC7CLQM","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":"88c1ba323cb2bcc7dac3c20bf5a6ca10ff5a9fadb05033d3bdd1287dbf804266","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T15:57:38Z","title_canon_sha256":"f6915653f3ae695784e49981c8dd7099eeffdb55d3adf0deb7dfebc87131bc41"},"schema_version":"1.0","source":{"id":"2608.03855","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03855","created_at":"2026-08-05T01:37:15Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03855v1","created_at":"2026-08-05T01:37:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03855","created_at":"2026-08-05T01:37:15Z"},{"alias_kind":"pith_short_12","alias_value":"VIBTUCNGBM5G","created_at":"2026-08-05T01:37:15Z"},{"alias_kind":"pith_short_16","alias_value":"VIBTUCNGBM5GZODT","created_at":"2026-08-05T01:37:15Z"},{"alias_kind":"pith_short_8","alias_value":"VIBTUCNG","created_at":"2026-08-05T01:37:15Z"}],"graph_snapshots":[{"event_id":"sha256:e445505c055ed77a39354bd31c3ed0203383b3ca3ecb21b7387a8580033ac948","target":"graph","created_at":"2026-08-05T01:37:15Z","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/2608.03855/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer models have revolutionized natural language processing (NLP), and text-based molecular representations like SMILES have successfully extended these architectures to chemistry. However, domain-adaptive pre-training often causes models to overfit to chemical syntax, catastrophically forgetting their foundational semantic capabilities. To address this challenge, we introduce CheMatE, a chemistry-oriented embedding model that jointly captures molecular structure and domain-specific natural language within the same representation space. Built on a ModernBERT backbone, CheMatE learns bi-","authors_text":"Bojana Rankovi\\'c, David Ming Segura, Jeremy Goumaz, Joshua W. Sin, Philippe Schwaller","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T15:57:38Z","title":"Bi-semantic Chemical Embedder for Joint Representation Learning of SMILES and Natural Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03855","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":"sha256:634c2279d66a6e707a0c1348414dd79940ea3108dc05ecd8e388afa59d7b6a8d","target":"record","created_at":"2026-08-05T01:37:15Z","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":"88c1ba323cb2bcc7dac3c20bf5a6ca10ff5a9fadb05033d3bdd1287dbf804266","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T15:57:38Z","title_canon_sha256":"f6915653f3ae695784e49981c8dd7099eeffdb55d3adf0deb7dfebc87131bc41"},"schema_version":"1.0","source":{"id":"2608.03855","kind":"arxiv","version":1}},"canonical_sha256":"aa033a09a60b3a6cb8730379217c4b8332565382b3ecb0ac0b4a22efa33a5cad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa033a09a60b3a6cb8730379217c4b8332565382b3ecb0ac0b4a22efa33a5cad","first_computed_at":"2026-08-05T01:37:15.699929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T01:37:15.699929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SVH+JIGh19ryUhgGJxMLkYnHqDX3pjaRgJ4CFwuGZ2lRfgbuA6YQmJERjS3EGtv1wiwNZHo8iWVNK8WoUW+ADA==","signature_status":"signed_v1","signed_at":"2026-08-05T01:37:15.701267Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03855","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:634c2279d66a6e707a0c1348414dd79940ea3108dc05ecd8e388afa59d7b6a8d","sha256:e445505c055ed77a39354bd31c3ed0203383b3ca3ecb21b7387a8580033ac948"],"state_sha256":"0fa1857dc66b5e3dde4f1041c20a45d9e7d86a017a1df206c5dd2d7a21d57b14"}