{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VIBTUCNGBM5GZODTAN4SC7CLQM","short_pith_number":"pith:VIBTUCNG","schema_version":"1.0","canonical_sha256":"aa033a09a60b3a6cb8730379217c4b8332565382b3ecb0ac0b4a22efa33a5cad","source":{"kind":"arxiv","id":"2608.03855","version":1},"attestation_state":"computed","paper":{"title":"Bi-semantic Chemical Embedder for Joint Representation Learning of SMILES and Natural Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bojana Rankovi\\'c, David Ming Segura, Jeremy Goumaz, Joshua W. Sin, Philippe Schwaller","submitted_at":"2026-08-04T15:57:38Z","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-"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.03855","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-04T15:57:38Z","cross_cats_sorted":[],"title_canon_sha256":"f6915653f3ae695784e49981c8dd7099eeffdb55d3adf0deb7dfebc87131bc41","abstract_canon_sha256":"88c1ba323cb2bcc7dac3c20bf5a6ca10ff5a9fadb05033d3bdd1287dbf804266"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:37:15.701267Z","signature_b64":"SVH+JIGh19ryUhgGJxMLkYnHqDX3pjaRgJ4CFwuGZ2lRfgbuA6YQmJERjS3EGtv1wiwNZHo8iWVNK8WoUW+ADA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa033a09a60b3a6cb8730379217c4b8332565382b3ecb0ac0b4a22efa33a5cad","last_reissued_at":"2026-08-05T01:37:15.699929Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:37:15.699929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bi-semantic Chemical Embedder for Joint Representation Learning of SMILES and Natural Language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bojana Rankovi\\'c, David Ming Segura, Jeremy Goumaz, Joshua W. Sin, Philippe Schwaller","submitted_at":"2026-08-04T15:57:38Z","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-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03855","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/2608.03855/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.03855","created_at":"2026-08-05T01:37:15.700347+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03855v1","created_at":"2026-08-05T01:37:15.700347+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03855","created_at":"2026-08-05T01:37:15.700347+00:00"},{"alias_kind":"pith_short_12","alias_value":"VIBTUCNGBM5G","created_at":"2026-08-05T01:37:15.700347+00:00"},{"alias_kind":"pith_short_16","alias_value":"VIBTUCNGBM5GZODT","created_at":"2026-08-05T01:37:15.700347+00:00"},{"alias_kind":"pith_short_8","alias_value":"VIBTUCNG","created_at":"2026-08-05T01:37:15.700347+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VIBTUCNGBM5GZODTAN4SC7CLQM","json":"https://pith.science/pith/VIBTUCNGBM5GZODTAN4SC7CLQM.json","graph_json":"https://pith.science/api/pith-number/VIBTUCNGBM5GZODTAN4SC7CLQM/graph.json","events_json":"https://pith.science/api/pith-number/VIBTUCNGBM5GZODTAN4SC7CLQM/events.json","paper":"https://pith.science/paper/VIBTUCNG"},"agent_actions":{"view_html":"https://pith.science/pith/VIBTUCNGBM5GZODTAN4SC7CLQM","download_json":"https://pith.science/pith/VIBTUCNGBM5GZODTAN4SC7CLQM.json","view_paper":"https://pith.science/paper/VIBTUCNG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03855&json=true","fetch_graph":"https://pith.science/api/pith-number/VIBTUCNGBM5GZODTAN4SC7CLQM/graph.json","fetch_events":"https://pith.science/api/pith-number/VIBTUCNGBM5GZODTAN4SC7CLQM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VIBTUCNGBM5GZODTAN4SC7CLQM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VIBTUCNGBM5GZODTAN4SC7CLQM/action/storage_attestation","attest_author":"https://pith.science/pith/VIBTUCNGBM5GZODTAN4SC7CLQM/action/author_attestation","sign_citation":"https://pith.science/pith/VIBTUCNGBM5GZODTAN4SC7CLQM/action/citation_signature","submit_replication":"https://pith.science/pith/VIBTUCNGBM5GZODTAN4SC7CLQM/action/replication_record"}},"created_at":"2026-08-05T01:37:15.700347+00:00","updated_at":"2026-08-05T01:37:15.700347+00:00"}