{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KXQCHSWVBIGZVS67SM6YPWRJUU","short_pith_number":"pith:KXQCHSWV","canonical_record":{"source":{"id":"2607.01800","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T07:16:28Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"eb573fb234569c0b0145bccbf2997da41e1175e0a2cc14b2092963760d46e08d","abstract_canon_sha256":"e2a1d5043ac3ec3dee7cb92fec1cc3557bcc2fc5e227228534a187345df5b5ad"},"schema_version":"1.0"},"canonical_sha256":"55e023cad50a0d9acbdf933d87da29a52fcce979dc666275d0b53da2c9fbddf9","source":{"kind":"arxiv","id":"2607.01800","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01800","created_at":"2026-07-03T01:17:30Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01800v1","created_at":"2026-07-03T01:17:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01800","created_at":"2026-07-03T01:17:30Z"},{"alias_kind":"pith_short_12","alias_value":"KXQCHSWVBIGZ","created_at":"2026-07-03T01:17:30Z"},{"alias_kind":"pith_short_16","alias_value":"KXQCHSWVBIGZVS67","created_at":"2026-07-03T01:17:30Z"},{"alias_kind":"pith_short_8","alias_value":"KXQCHSWV","created_at":"2026-07-03T01:17:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KXQCHSWVBIGZVS67SM6YPWRJUU","target":"record","payload":{"canonical_record":{"source":{"id":"2607.01800","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T07:16:28Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"eb573fb234569c0b0145bccbf2997da41e1175e0a2cc14b2092963760d46e08d","abstract_canon_sha256":"e2a1d5043ac3ec3dee7cb92fec1cc3557bcc2fc5e227228534a187345df5b5ad"},"schema_version":"1.0"},"canonical_sha256":"55e023cad50a0d9acbdf933d87da29a52fcce979dc666275d0b53da2c9fbddf9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:30.248699Z","signature_b64":"W69uaW99Yg2K0ury5SNmv72WSgEDJaXRIUJ/HWlwzWuScYzvCF65qgnZydn1/QJobqO/wfqu931KK8kXQ1t0DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55e023cad50a0d9acbdf933d87da29a52fcce979dc666275d0b53da2c9fbddf9","last_reissued_at":"2026-07-03T01:17:30.248265Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:30.248265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.01800","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":"2026-07-03T01:17:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KTxB7aenZQ6/sIwq7DwYYqUKJ1nQlMSekCfbqJTbNkZzo3skUJxMp3qWBeV8AXywDcAXfeqXsGWSGcXjQRflBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T07:00:59.739772Z"},"content_sha256":"88bb8729212bb69405228043c04d1ce0425a09abdb6be94ce3a97093c2e9ad16","schema_version":"1.0","event_id":"sha256:88bb8729212bb69405228043c04d1ce0425a09abdb6be94ce3a97093c2e9ad16"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KXQCHSWVBIGZVS67SM6YPWRJUU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do LLMs Truly Generalize in the Molecular Domain? A Perturbation-Based Analysis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Changmeng Zheng, Jiatong Li, Qing Li, Shufei Zhang, Weida Wang, Xiao-Yong Wei, Yatao Bian","submitted_at":"2026-07-02T07:16:28Z","abstract_excerpt":"Large Language Models (LLMs) have recently shown promise in molecular discovery, yet a gap remains between their probabilistic nature over discrete sequential tokens and the rigid topological constraints of chemical space. This raises the question of whether molecular LLMs can generalize beyond the local neighborhoods induced by their sequence-based representations. To systematically investigate this question, we introduce a Molecular Perturbation framework that generates syntax-valid structural variants of training molecules under controlled Graph Edit Distance (GED) to probe the manifold reg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01800","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/2607.01800/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":"2026-07-03T01:17:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2OREbpX78Rj7305GqrKSg0VbFd6WJTmSaOaKyw383Pe4kFDuQoLLrpfdJEmkY7DumFXHhvIvxC5aFS3X2W71Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T07:00:59.740149Z"},"content_sha256":"af90d762592140b7bb400e771a67bb72f952363821e8592b8bc35179f51cc76b","schema_version":"1.0","event_id":"sha256:af90d762592140b7bb400e771a67bb72f952363821e8592b8bc35179f51cc76b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KXQCHSWVBIGZVS67SM6YPWRJUU/bundle.json","state_url":"https://pith.science/pith/KXQCHSWVBIGZVS67SM6YPWRJUU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KXQCHSWVBIGZVS67SM6YPWRJUU/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":"2026-07-04T07:00:59Z","links":{"resolver":"https://pith.science/pith/KXQCHSWVBIGZVS67SM6YPWRJUU","bundle":"https://pith.science/pith/KXQCHSWVBIGZVS67SM6YPWRJUU/bundle.json","state":"https://pith.science/pith/KXQCHSWVBIGZVS67SM6YPWRJUU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KXQCHSWVBIGZVS67SM6YPWRJUU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KXQCHSWVBIGZVS67SM6YPWRJUU","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":"e2a1d5043ac3ec3dee7cb92fec1cc3557bcc2fc5e227228534a187345df5b5ad","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T07:16:28Z","title_canon_sha256":"eb573fb234569c0b0145bccbf2997da41e1175e0a2cc14b2092963760d46e08d"},"schema_version":"1.0","source":{"id":"2607.01800","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01800","created_at":"2026-07-03T01:17:30Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01800v1","created_at":"2026-07-03T01:17:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01800","created_at":"2026-07-03T01:17:30Z"},{"alias_kind":"pith_short_12","alias_value":"KXQCHSWVBIGZ","created_at":"2026-07-03T01:17:30Z"},{"alias_kind":"pith_short_16","alias_value":"KXQCHSWVBIGZVS67","created_at":"2026-07-03T01:17:30Z"},{"alias_kind":"pith_short_8","alias_value":"KXQCHSWV","created_at":"2026-07-03T01:17:30Z"}],"graph_snapshots":[{"event_id":"sha256:af90d762592140b7bb400e771a67bb72f952363821e8592b8bc35179f51cc76b","target":"graph","created_at":"2026-07-03T01:17:30Z","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/2607.01800/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have recently shown promise in molecular discovery, yet a gap remains between their probabilistic nature over discrete sequential tokens and the rigid topological constraints of chemical space. This raises the question of whether molecular LLMs can generalize beyond the local neighborhoods induced by their sequence-based representations. To systematically investigate this question, we introduce a Molecular Perturbation framework that generates syntax-valid structural variants of training molecules under controlled Graph Edit Distance (GED) to probe the manifold reg","authors_text":"Changmeng Zheng, Jiatong Li, Qing Li, Shufei Zhang, Weida Wang, Xiao-Yong Wei, Yatao Bian","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T07:16:28Z","title":"Do LLMs Truly Generalize in the Molecular Domain? A Perturbation-Based Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01800","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":"sha256:88bb8729212bb69405228043c04d1ce0425a09abdb6be94ce3a97093c2e9ad16","target":"record","created_at":"2026-07-03T01:17:30Z","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":"e2a1d5043ac3ec3dee7cb92fec1cc3557bcc2fc5e227228534a187345df5b5ad","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T07:16:28Z","title_canon_sha256":"eb573fb234569c0b0145bccbf2997da41e1175e0a2cc14b2092963760d46e08d"},"schema_version":"1.0","source":{"id":"2607.01800","kind":"arxiv","version":1}},"canonical_sha256":"55e023cad50a0d9acbdf933d87da29a52fcce979dc666275d0b53da2c9fbddf9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55e023cad50a0d9acbdf933d87da29a52fcce979dc666275d0b53da2c9fbddf9","first_computed_at":"2026-07-03T01:17:30.248265Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:30.248265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"W69uaW99Yg2K0ury5SNmv72WSgEDJaXRIUJ/HWlwzWuScYzvCF65qgnZydn1/QJobqO/wfqu931KK8kXQ1t0DA==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:30.248699Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.01800","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:88bb8729212bb69405228043c04d1ce0425a09abdb6be94ce3a97093c2e9ad16","sha256:af90d762592140b7bb400e771a67bb72f952363821e8592b8bc35179f51cc76b"],"state_sha256":"8b42e5707b1d763f0eddd29ab9209d7c3cc5dcf5eead10385a0a5890f28be337"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UNeCH1X8IgL1FqH30YD5/tTFUL2WNGRl97EBrfkgkLDJPeBUNM7JJ2VhrgmIVzeCpjinA0rrn+MX08pxhp3WDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T07:00:59.742196Z","bundle_sha256":"13cfa3f4b66fbd76a43e696ede5ff6b6adc42278cd29cabf885f27aef56bdbf5"}}