{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:K7YLIDBMHXUDWBW2P52OLWQFPU","short_pith_number":"pith:K7YLIDBM","canonical_record":{"source":{"id":"2505.16340","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T07:54:39Z","cross_cats_sorted":[],"title_canon_sha256":"f70f04feac8c71e3633e396d91ccc5ee3d2eeecd2dcfc4f4e1343dc64dfba83b","abstract_canon_sha256":"d40f53717719333728937ecc397b470d46ead453d6bbb89553d5e9e720dfbd93"},"schema_version":"1.0"},"canonical_sha256":"57f0b40c2c3de83b06da7f74e5da057d1f017a5d0e4858680b9c28b691ae120c","source":{"kind":"arxiv","id":"2505.16340","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16340","created_at":"2026-07-05T11:07:34Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16340v1","created_at":"2026-07-05T11:07:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16340","created_at":"2026-07-05T11:07:34Z"},{"alias_kind":"pith_short_12","alias_value":"K7YLIDBMHXUD","created_at":"2026-07-05T11:07:34Z"},{"alias_kind":"pith_short_16","alias_value":"K7YLIDBMHXUDWBW2","created_at":"2026-07-05T11:07:34Z"},{"alias_kind":"pith_short_8","alias_value":"K7YLIDBM","created_at":"2026-07-05T11:07:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:K7YLIDBMHXUDWBW2P52OLWQFPU","target":"record","payload":{"canonical_record":{"source":{"id":"2505.16340","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T07:54:39Z","cross_cats_sorted":[],"title_canon_sha256":"f70f04feac8c71e3633e396d91ccc5ee3d2eeecd2dcfc4f4e1343dc64dfba83b","abstract_canon_sha256":"d40f53717719333728937ecc397b470d46ead453d6bbb89553d5e9e720dfbd93"},"schema_version":"1.0"},"canonical_sha256":"57f0b40c2c3de83b06da7f74e5da057d1f017a5d0e4858680b9c28b691ae120c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:34.005964Z","signature_b64":"yegVtGgveXTdjr0FqTk93qxXZTyUzathAJabxYnv0kPVwq8lWPYdDPhKnLUaHrnyqDHST3uOf7bWJPuRWYaQAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57f0b40c2c3de83b06da7f74e5da057d1f017a5d0e4858680b9c28b691ae120c","last_reissued_at":"2026-07-05T11:07:34.005481Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:34.005481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.16340","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:07:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H6JFQlQr6TB4EYau7UX8zEFqCHfKhWwXRsbeQag19JMxJoPm8TjSTreM5CD3Mq9eF/75GzueuGiiKGEf9z7mAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:15:53.901898Z"},"content_sha256":"f9bcdd7199415a21ba27e7ea6173dcb478103ac704681a29b9057a0f227aefa4","schema_version":"1.0","event_id":"sha256:f9bcdd7199415a21ba27e7ea6173dcb478103ac704681a29b9057a0f227aefa4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:K7YLIDBMHXUDWBW2P52OLWQFPU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Chemical Understanding of LLMs via SMILES Parsing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jaehyung Kim, Sungsoo Ahn, Yunhui Jang","submitted_at":"2025-05-22T07:54:39Z","abstract_excerpt":"Large language models (LLMs) are increasingly recognized as powerful tools for scientific discovery, particularly in molecular science. A fundamental requirement for these models is the ability to accurately understand molecular structures, commonly encoded in the SMILES representation. However, current LLMs struggle to interpret SMILES, even failing to carry out basic tasks such as counting molecular rings. To address this limitation, we introduce CLEANMOL, a novel framework that formulates SMILES parsing into a suite of clean and deterministic tasks explicitly designed to promote graph-level"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16340","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/2505.16340/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:07:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JI14GIYiYvNsGBC9rsDnWPDuuzF8PFl7qIBgpR+NpPT7OuItEs3uVZJpbIGbu64OdvfOGFwf1autjcNynDUeAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T01:15:53.902448Z"},"content_sha256":"6dba82e221df29853222f321a8388ff7d84a41bc689521dd0a6caf482ad37dac","schema_version":"1.0","event_id":"sha256:6dba82e221df29853222f321a8388ff7d84a41bc689521dd0a6caf482ad37dac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K7YLIDBMHXUDWBW2P52OLWQFPU/bundle.json","state_url":"https://pith.science/pith/K7YLIDBMHXUDWBW2P52OLWQFPU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K7YLIDBMHXUDWBW2P52OLWQFPU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T01:15:53Z","links":{"resolver":"https://pith.science/pith/K7YLIDBMHXUDWBW2P52OLWQFPU","bundle":"https://pith.science/pith/K7YLIDBMHXUDWBW2P52OLWQFPU/bundle.json","state":"https://pith.science/pith/K7YLIDBMHXUDWBW2P52OLWQFPU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K7YLIDBMHXUDWBW2P52OLWQFPU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:K7YLIDBMHXUDWBW2P52OLWQFPU","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":"d40f53717719333728937ecc397b470d46ead453d6bbb89553d5e9e720dfbd93","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T07:54:39Z","title_canon_sha256":"f70f04feac8c71e3633e396d91ccc5ee3d2eeecd2dcfc4f4e1343dc64dfba83b"},"schema_version":"1.0","source":{"id":"2505.16340","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16340","created_at":"2026-07-05T11:07:34Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16340v1","created_at":"2026-07-05T11:07:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16340","created_at":"2026-07-05T11:07:34Z"},{"alias_kind":"pith_short_12","alias_value":"K7YLIDBMHXUD","created_at":"2026-07-05T11:07:34Z"},{"alias_kind":"pith_short_16","alias_value":"K7YLIDBMHXUDWBW2","created_at":"2026-07-05T11:07:34Z"},{"alias_kind":"pith_short_8","alias_value":"K7YLIDBM","created_at":"2026-07-05T11:07:34Z"}],"graph_snapshots":[{"event_id":"sha256:6dba82e221df29853222f321a8388ff7d84a41bc689521dd0a6caf482ad37dac","target":"graph","created_at":"2026-07-05T11:07:34Z","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/2505.16340/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly recognized as powerful tools for scientific discovery, particularly in molecular science. A fundamental requirement for these models is the ability to accurately understand molecular structures, commonly encoded in the SMILES representation. However, current LLMs struggle to interpret SMILES, even failing to carry out basic tasks such as counting molecular rings. To address this limitation, we introduce CLEANMOL, a novel framework that formulates SMILES parsing into a suite of clean and deterministic tasks explicitly designed to promote graph-level","authors_text":"Jaehyung Kim, Sungsoo Ahn, Yunhui Jang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T07:54:39Z","title":"Improving Chemical Understanding of LLMs via SMILES Parsing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16340","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:f9bcdd7199415a21ba27e7ea6173dcb478103ac704681a29b9057a0f227aefa4","target":"record","created_at":"2026-07-05T11:07:34Z","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":"d40f53717719333728937ecc397b470d46ead453d6bbb89553d5e9e720dfbd93","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T07:54:39Z","title_canon_sha256":"f70f04feac8c71e3633e396d91ccc5ee3d2eeecd2dcfc4f4e1343dc64dfba83b"},"schema_version":"1.0","source":{"id":"2505.16340","kind":"arxiv","version":1}},"canonical_sha256":"57f0b40c2c3de83b06da7f74e5da057d1f017a5d0e4858680b9c28b691ae120c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57f0b40c2c3de83b06da7f74e5da057d1f017a5d0e4858680b9c28b691ae120c","first_computed_at":"2026-07-05T11:07:34.005481Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:34.005481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yegVtGgveXTdjr0FqTk93qxXZTyUzathAJabxYnv0kPVwq8lWPYdDPhKnLUaHrnyqDHST3uOf7bWJPuRWYaQAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:34.005964Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.16340","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9bcdd7199415a21ba27e7ea6173dcb478103ac704681a29b9057a0f227aefa4","sha256:6dba82e221df29853222f321a8388ff7d84a41bc689521dd0a6caf482ad37dac"],"state_sha256":"460ca615ae226571dcb932fafff1e405fd134cc038d4a049f4b847a97bf7ffdc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qf5bVHNrl2gQYYjdBwZNyBxm2UmHpNBu/WUSomvc8zHi291USJn6YVnzEAQw4yy9DdOXIvkE3TmLA/14UAsiCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T01:15:53.907414Z","bundle_sha256":"b2436d2bc6243b2537e8e3cd38ee5af59a25961fc5e32f7fb6fb198c5314ce40"}}