{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NJEVQ5HV2OKGXTP73GJX24H4FJ","short_pith_number":"pith:NJEVQ5HV","canonical_record":{"source":{"id":"2607.03007","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-03T06:41:33Z","cross_cats_sorted":["cs.AI","q-bio.BM"],"title_canon_sha256":"c3d2fe53b9b1a6ff36a73fc3ee8932a2fc0da5ab6025fdaccd2461125b563bed","abstract_canon_sha256":"d8e0dfd1739ab062d50706195bdba61276984f96abe6962694bcc0cc5838d3b3"},"schema_version":"1.0"},"canonical_sha256":"6a495874f5d3946bcdffd9937d70fc2a4f5f99ab3267d31f30fa649cc8ce1bb9","source":{"kind":"arxiv","id":"2607.03007","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.03007","created_at":"2026-07-07T01:16:39Z"},{"alias_kind":"arxiv_version","alias_value":"2607.03007v1","created_at":"2026-07-07T01:16:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03007","created_at":"2026-07-07T01:16:39Z"},{"alias_kind":"pith_short_12","alias_value":"NJEVQ5HV2OKG","created_at":"2026-07-07T01:16:39Z"},{"alias_kind":"pith_short_16","alias_value":"NJEVQ5HV2OKGXTP7","created_at":"2026-07-07T01:16:39Z"},{"alias_kind":"pith_short_8","alias_value":"NJEVQ5HV","created_at":"2026-07-07T01:16:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NJEVQ5HV2OKGXTP73GJX24H4FJ","target":"record","payload":{"canonical_record":{"source":{"id":"2607.03007","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-03T06:41:33Z","cross_cats_sorted":["cs.AI","q-bio.BM"],"title_canon_sha256":"c3d2fe53b9b1a6ff36a73fc3ee8932a2fc0da5ab6025fdaccd2461125b563bed","abstract_canon_sha256":"d8e0dfd1739ab062d50706195bdba61276984f96abe6962694bcc0cc5838d3b3"},"schema_version":"1.0"},"canonical_sha256":"6a495874f5d3946bcdffd9937d70fc2a4f5f99ab3267d31f30fa649cc8ce1bb9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T01:16:39.201976Z","signature_b64":"XdtHf4M5xP1d8nY9aGQd1gF9Xvm2AoZjbYgioeEy8ZX12iA0hzevZ2RiK9mwGbN3gK/s8ZHJGlnwfx0mN+YJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a495874f5d3946bcdffd9937d70fc2a4f5f99ab3267d31f30fa649cc8ce1bb9","last_reissued_at":"2026-07-07T01:16:39.201507Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T01:16:39.201507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.03007","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":"2026-07-07T01:16:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IYTkxuyb/4PfPND4vyHWQPzCN2nkMO0+G0oQkjLjt8XCCtuZQZv+tXyjuDMtA/GUq4G+iorLrqeYnxTV9E0UBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T14:56:17.315199Z"},"content_sha256":"feef97b3a46d24e57394f34e1f20e5d663d5fbc5e3d28e6119f0d1d98f1341bb","schema_version":"1.0","event_id":"sha256:feef97b3a46d24e57394f34e1f20e5d663d5fbc5e3d28e6119f0d1d98f1341bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NJEVQ5HV2OKGXTP73GJX24H4FJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Back to Basics: Improving Molecular Understanding in LLMs via SMILES-Graph Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Jinjia Feng, Wenda Wang, Zhewei Wei","submitted_at":"2026-07-03T06:41:33Z","abstract_excerpt":"Recent advances in molecular large language models have led to strong performance on molecular understanding and generation tasks, yet these gains often come without reliable structural grounding. In particular, existing approaches conflict with the chemistry principle that structure determines function: despite their downstream success, current molecular LLMs perform poorly on basic structure recognition, suggesting that they fail to capture molecular graphs from canonical SMILES. To remedy this, we propose MolBasic, a structure-first framework that strengthens structural comprehension via SM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03007","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/2607.03007/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":"2026-07-07T01:16:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N5nQt9xLdSP4g6rXMUdlzWiLW8dSRnDxeAXPF8MHNDQLTGEUlXqOVuIJCIMh3AwqppSQOf35+Q39Jz9hXeVOBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T14:56:17.315718Z"},"content_sha256":"91758db88fb0172b3100fa685c9c599dd22cf143b77ae1bd0dcc112d294baff3","schema_version":"1.0","event_id":"sha256:91758db88fb0172b3100fa685c9c599dd22cf143b77ae1bd0dcc112d294baff3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NJEVQ5HV2OKGXTP73GJX24H4FJ/bundle.json","state_url":"https://pith.science/pith/NJEVQ5HV2OKGXTP73GJX24H4FJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NJEVQ5HV2OKGXTP73GJX24H4FJ/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":"2026-08-03T14:56:17Z","links":{"resolver":"https://pith.science/pith/NJEVQ5HV2OKGXTP73GJX24H4FJ","bundle":"https://pith.science/pith/NJEVQ5HV2OKGXTP73GJX24H4FJ/bundle.json","state":"https://pith.science/pith/NJEVQ5HV2OKGXTP73GJX24H4FJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NJEVQ5HV2OKGXTP73GJX24H4FJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NJEVQ5HV2OKGXTP73GJX24H4FJ","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":"d8e0dfd1739ab062d50706195bdba61276984f96abe6962694bcc0cc5838d3b3","cross_cats_sorted":["cs.AI","q-bio.BM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-03T06:41:33Z","title_canon_sha256":"c3d2fe53b9b1a6ff36a73fc3ee8932a2fc0da5ab6025fdaccd2461125b563bed"},"schema_version":"1.0","source":{"id":"2607.03007","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.03007","created_at":"2026-07-07T01:16:39Z"},{"alias_kind":"arxiv_version","alias_value":"2607.03007v1","created_at":"2026-07-07T01:16:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03007","created_at":"2026-07-07T01:16:39Z"},{"alias_kind":"pith_short_12","alias_value":"NJEVQ5HV2OKG","created_at":"2026-07-07T01:16:39Z"},{"alias_kind":"pith_short_16","alias_value":"NJEVQ5HV2OKGXTP7","created_at":"2026-07-07T01:16:39Z"},{"alias_kind":"pith_short_8","alias_value":"NJEVQ5HV","created_at":"2026-07-07T01:16:39Z"}],"graph_snapshots":[{"event_id":"sha256:91758db88fb0172b3100fa685c9c599dd22cf143b77ae1bd0dcc112d294baff3","target":"graph","created_at":"2026-07-07T01:16:39Z","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/2607.03007/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in molecular large language models have led to strong performance on molecular understanding and generation tasks, yet these gains often come without reliable structural grounding. In particular, existing approaches conflict with the chemistry principle that structure determines function: despite their downstream success, current molecular LLMs perform poorly on basic structure recognition, suggesting that they fail to capture molecular graphs from canonical SMILES. To remedy this, we propose MolBasic, a structure-first framework that strengthens structural comprehension via SM","authors_text":"Jinjia Feng, Wenda Wang, Zhewei Wei","cross_cats":["cs.AI","q-bio.BM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-03T06:41:33Z","title":"Back to Basics: Improving Molecular Understanding in LLMs via SMILES-Graph Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03007","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:feef97b3a46d24e57394f34e1f20e5d663d5fbc5e3d28e6119f0d1d98f1341bb","target":"record","created_at":"2026-07-07T01:16:39Z","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":"d8e0dfd1739ab062d50706195bdba61276984f96abe6962694bcc0cc5838d3b3","cross_cats_sorted":["cs.AI","q-bio.BM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-03T06:41:33Z","title_canon_sha256":"c3d2fe53b9b1a6ff36a73fc3ee8932a2fc0da5ab6025fdaccd2461125b563bed"},"schema_version":"1.0","source":{"id":"2607.03007","kind":"arxiv","version":1}},"canonical_sha256":"6a495874f5d3946bcdffd9937d70fc2a4f5f99ab3267d31f30fa649cc8ce1bb9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a495874f5d3946bcdffd9937d70fc2a4f5f99ab3267d31f30fa649cc8ce1bb9","first_computed_at":"2026-07-07T01:16:39.201507Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T01:16:39.201507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XdtHf4M5xP1d8nY9aGQd1gF9Xvm2AoZjbYgioeEy8ZX12iA0hzevZ2RiK9mwGbN3gK/s8ZHJGlnwfx0mN+YJDw==","signature_status":"signed_v1","signed_at":"2026-07-07T01:16:39.201976Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.03007","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:feef97b3a46d24e57394f34e1f20e5d663d5fbc5e3d28e6119f0d1d98f1341bb","sha256:91758db88fb0172b3100fa685c9c599dd22cf143b77ae1bd0dcc112d294baff3"],"state_sha256":"36a1de16de83d0d6be2fcde35cf98e4f0019989cce6321ea372b118ba988a5d1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SIhdiUeziTtt4Aj8CfCd1jp7VrbTUFdDFAjOmZGMdtHKsgHZ0Q4VvrBEMuU+8/g0QbaVtuYZZ+dxGZ8wq5VuAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T14:56:17.319610Z","bundle_sha256":"b09c869fe968e23501cb7e8eaa2ad4175512622cca1f175c824284a3443696e7"}}