{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:M7O7MGVLNYFCUKG3ZOIAY4QUCW","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":"2e4b0223a4921f74124923ee6d84f3980ea1ae2144db610d90a4695cb20ccf46","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T13:16:31Z","title_canon_sha256":"bf2ff6e97e830afc9c064d9b81dea761dfdae294d82e16e524cc85c417401db1"},"schema_version":"1.0","source":{"id":"2607.02140","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.02140","created_at":"2026-07-03T01:17:43Z"},{"alias_kind":"arxiv_version","alias_value":"2607.02140v1","created_at":"2026-07-03T01:17:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02140","created_at":"2026-07-03T01:17:43Z"},{"alias_kind":"pith_short_12","alias_value":"M7O7MGVLNYFC","created_at":"2026-07-03T01:17:43Z"},{"alias_kind":"pith_short_16","alias_value":"M7O7MGVLNYFCUKG3","created_at":"2026-07-03T01:17:43Z"},{"alias_kind":"pith_short_8","alias_value":"M7O7MGVL","created_at":"2026-07-03T01:17:43Z"}],"graph_snapshots":[{"event_id":"sha256:d48fa454ba6e1e759084013157fd3ff49bc012f39c3ce6e4690938d6ea4958ba","target":"graph","created_at":"2026-07-03T01:17:43Z","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/2607.02140/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Chemical language models (CLMs) are trained with linearized representations such as SMILES, yet it remains unclear which chemically meaningful substructures they encode. To foster a better understanding of CLMs, we conduct a systematic study and probe for 78 molecular substructures across eight pre-trained and six randomly initialized models. We furthermore study how fine-tuning on chemical downstream tasks affects the learned representations of molecular substructures. Our results show that pre-training generally improves molecular structure awareness of CLMs, particularly in the upper layers","authors_text":"Anna Karnysheva, Dietrich Klakow, Ji-Ung Lee","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T13:16:31Z","title":"Probing Chemical Language Models: Effects of Pre-training and Fine-tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02140","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":"sha256:8eb07fb92b6f6390b53428c88ab82fded834aceb8b8441bcf077c4a3da41a5ae","target":"record","created_at":"2026-07-03T01:17:43Z","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":"2e4b0223a4921f74124923ee6d84f3980ea1ae2144db610d90a4695cb20ccf46","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T13:16:31Z","title_canon_sha256":"bf2ff6e97e830afc9c064d9b81dea761dfdae294d82e16e524cc85c417401db1"},"schema_version":"1.0","source":{"id":"2607.02140","kind":"arxiv","version":1}},"canonical_sha256":"67ddf61aab6e0a2a28dbcb900c7214158d0417fcb2bb5a563d919077ad640e4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67ddf61aab6e0a2a28dbcb900c7214158d0417fcb2bb5a563d919077ad640e4d","first_computed_at":"2026-07-03T01:17:43.233335Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:43.233335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wcYN5y4f76if0aY4L6QYYR83+gByCF5QlxDYpuSLMVMPFS6Fj3zLKKfq0CZfgSl8y37QoFcmVRpg5gbCueAPDw==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:43.233766Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.02140","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8eb07fb92b6f6390b53428c88ab82fded834aceb8b8441bcf077c4a3da41a5ae","sha256:d48fa454ba6e1e759084013157fd3ff49bc012f39c3ce6e4690938d6ea4958ba"],"state_sha256":"1d804a2a7cafb4dc8b5a4eb7c5272bd049ca7c385dca01beeac2884beab4838d"}