{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AN5JIWJ2KIGL76JFT37QGYQ76M","short_pith_number":"pith:AN5JIWJ2","canonical_record":{"source":{"id":"2607.23607","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-26T11:29:23Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"dd77add8274605511f3e58bf1907b5cc0e2c50349b6cbe606a472f8d04eb88be","abstract_canon_sha256":"558ec989195581d245d09a94357d8354f83806f8f9611b9bf63c4381143e4fd3"},"schema_version":"1.0"},"canonical_sha256":"037a94593a520cbff9259eff03621ff33d3e02d8624bd79dc70c0ae444183945","source":{"kind":"arxiv","id":"2607.23607","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23607","created_at":"2026-07-28T01:23:01Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23607v1","created_at":"2026-07-28T01:23:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23607","created_at":"2026-07-28T01:23:01Z"},{"alias_kind":"pith_short_12","alias_value":"AN5JIWJ2KIGL","created_at":"2026-07-28T01:23:01Z"},{"alias_kind":"pith_short_16","alias_value":"AN5JIWJ2KIGL76JF","created_at":"2026-07-28T01:23:01Z"},{"alias_kind":"pith_short_8","alias_value":"AN5JIWJ2","created_at":"2026-07-28T01:23:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AN5JIWJ2KIGL76JFT37QGYQ76M","target":"record","payload":{"canonical_record":{"source":{"id":"2607.23607","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-26T11:29:23Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"dd77add8274605511f3e58bf1907b5cc0e2c50349b6cbe606a472f8d04eb88be","abstract_canon_sha256":"558ec989195581d245d09a94357d8354f83806f8f9611b9bf63c4381143e4fd3"},"schema_version":"1.0"},"canonical_sha256":"037a94593a520cbff9259eff03621ff33d3e02d8624bd79dc70c0ae444183945","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:23:01.750571Z","signature_b64":"9c9aRNeh1ZhoPvb9VsWAxl9uMLCiZBLkt7otzqi8iUMBOwva5NBnR0DCHIKsfsHPCf6PiXFTp2uTpGk79rNgCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"037a94593a520cbff9259eff03621ff33d3e02d8624bd79dc70c0ae444183945","last_reissued_at":"2026-07-28T01:23:01.749718Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:23:01.749718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.23607","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":"2026-07-28T01:23:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dXNkgwwDYIJBy2Ohwz9NP1v9qsD46xW0CYLailT/wDI6QC0mM0LjmcJOgh9nFRX9qJLxqX6IJu7fthCt48rDBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:11:34.970170Z"},"content_sha256":"831f9ffb7e55437a3d49d170bc005d55d460234789b946fc9d11bbcea717e7d5","schema_version":"1.0","event_id":"sha256:831f9ffb7e55437a3d49d170bc005d55d460234789b946fc9d11bbcea717e7d5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AN5JIWJ2KIGL76JFT37QGYQ76M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MS-GPT: Rethinking MS/MS De Novo Structure Elucidation as Spectrum-Induced Posterior Querying of a Molecule-Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Feng Zhu, Weichu Zheng, Xiaokang Yang, Xin Zhao, Yanyan Xu, Yaohui Jin, Yumin Liu, Zhuo Li","submitted_at":"2026-07-26T11:29:23Z","abstract_excerpt":"Molecular structure elucidation from tandem mass spectra (MS/MS) is a central inverse problem in analytical chemistry. Most existing approaches to MS/MS identification remain tied to reference libraries or predefined candidate sets, whereas de novo methods aim to generate structures directly from spectra. A common de novo route predicts a molecular fingerprint from the spectrum and then decodes structures from it, enabling decoder pretraining on large molecule-only corpora. However, this paradigm creates a training-inference mismatch: the decoder is trained on oracle fingerprints computed from"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23607","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/2607.23607/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":"2026-07-28T01:23:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3oHbqZCRhW6/dlR9b00r+QNzRihdLPwF8wc4DJTe3ulEmnJBr8/Wbk27G1myA+ZIYgrw1beidhILKBcaOupDCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:11:34.970961Z"},"content_sha256":"76cf8a6027d189679aab173b6cb477367e664b0d55496005d907ae58ef6aa11b","schema_version":"1.0","event_id":"sha256:76cf8a6027d189679aab173b6cb477367e664b0d55496005d907ae58ef6aa11b"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:AN5JIWJ2KIGL76JFT37QGYQ76M","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1186/1758-2946-6-5) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"P. Franco, N. Porta, John D. Holliday, and Peter Willett. 2014. The use of 2D fingerprint methods to support the assessment of structural similarity in orphan drug legislation.Journal of Cheminformatics6, 1 (2014), 5. doi:10.1186/1758- 2946","arxiv_id":"2607.23607","detector":"doi_compliance","evidence":{"ref_index":12,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.1186/1758-","reconstructed_doi":"10.1186/1758-2946-6-5"},"severity":"advisory","ref_index":12,"audited_at":"2026-07-30T17:51:41.554695Z","event_type":"pith.integrity.v1","detected_doi":"10.1186/1758-2946-6-5","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"717055c6faf312b05340894695773cbb706aba9c39fe99db246925d02afddc14","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":14011,"payload_sha256":"79727734839bf0d130b03e218fc0bf897ae2647ce20706ddb8848af8e8919cee","signature_b64":null,"signing_key_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-30T17:56:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6vDkF8+OM4tWCj8BZA1nG93ikviNpMMx8vW1FXFfcQBzP4JL+kYIXbiW98lvfRmX49GiccM4TItoTO1yOHFZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:11:34.974617Z"},"content_sha256":"13d1fde1620b8fa0108120b4bd11bade6cef36a510cf262d7415917b8ba05824","schema_version":"1.0","event_id":"sha256:13d1fde1620b8fa0108120b4bd11bade6cef36a510cf262d7415917b8ba05824"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AN5JIWJ2KIGL76JFT37QGYQ76M/bundle.json","state_url":"https://pith.science/pith/AN5JIWJ2KIGL76JFT37QGYQ76M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AN5JIWJ2KIGL76JFT37QGYQ76M/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":"2026-08-04T12:11:34Z","links":{"resolver":"https://pith.science/pith/AN5JIWJ2KIGL76JFT37QGYQ76M","bundle":"https://pith.science/pith/AN5JIWJ2KIGL76JFT37QGYQ76M/bundle.json","state":"https://pith.science/pith/AN5JIWJ2KIGL76JFT37QGYQ76M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AN5JIWJ2KIGL76JFT37QGYQ76M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AN5JIWJ2KIGL76JFT37QGYQ76M","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"558ec989195581d245d09a94357d8354f83806f8f9611b9bf63c4381143e4fd3","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-26T11:29:23Z","title_canon_sha256":"dd77add8274605511f3e58bf1907b5cc0e2c50349b6cbe606a472f8d04eb88be"},"schema_version":"1.0","source":{"id":"2607.23607","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23607","created_at":"2026-07-28T01:23:01Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23607v1","created_at":"2026-07-28T01:23:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23607","created_at":"2026-07-28T01:23:01Z"},{"alias_kind":"pith_short_12","alias_value":"AN5JIWJ2KIGL","created_at":"2026-07-28T01:23:01Z"},{"alias_kind":"pith_short_16","alias_value":"AN5JIWJ2KIGL76JF","created_at":"2026-07-28T01:23:01Z"},{"alias_kind":"pith_short_8","alias_value":"AN5JIWJ2","created_at":"2026-07-28T01:23:01Z"}],"graph_snapshots":[{"event_id":"sha256:76cf8a6027d189679aab173b6cb477367e664b0d55496005d907ae58ef6aa11b","target":"graph","created_at":"2026-07-28T01:23:01Z","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/2607.23607/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Molecular structure elucidation from tandem mass spectra (MS/MS) is a central inverse problem in analytical chemistry. Most existing approaches to MS/MS identification remain tied to reference libraries or predefined candidate sets, whereas de novo methods aim to generate structures directly from spectra. A common de novo route predicts a molecular fingerprint from the spectrum and then decodes structures from it, enabling decoder pretraining on large molecule-only corpora. However, this paradigm creates a training-inference mismatch: the decoder is trained on oracle fingerprints computed from","authors_text":"Feng Zhu, Weichu Zheng, Xiaokang Yang, Xin Zhao, Yanyan Xu, Yaohui Jin, Yumin Liu, Zhuo Li","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-26T11:29:23Z","title":"MS-GPT: Rethinking MS/MS De Novo Structure Elucidation as Spectrum-Induced Posterior Querying of a Molecule-Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23607","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":"sha256:831f9ffb7e55437a3d49d170bc005d55d460234789b946fc9d11bbcea717e7d5","target":"record","created_at":"2026-07-28T01:23:01Z","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":"558ec989195581d245d09a94357d8354f83806f8f9611b9bf63c4381143e4fd3","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-26T11:29:23Z","title_canon_sha256":"dd77add8274605511f3e58bf1907b5cc0e2c50349b6cbe606a472f8d04eb88be"},"schema_version":"1.0","source":{"id":"2607.23607","kind":"arxiv","version":1}},"canonical_sha256":"037a94593a520cbff9259eff03621ff33d3e02d8624bd79dc70c0ae444183945","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"037a94593a520cbff9259eff03621ff33d3e02d8624bd79dc70c0ae444183945","first_computed_at":"2026-07-28T01:23:01.749718Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:23:01.749718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9c9aRNeh1ZhoPvb9VsWAxl9uMLCiZBLkt7otzqi8iUMBOwva5NBnR0DCHIKsfsHPCf6PiXFTp2uTpGk79rNgCg==","signature_status":"signed_v1","signed_at":"2026-07-28T01:23:01.750571Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.23607","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:831f9ffb7e55437a3d49d170bc005d55d460234789b946fc9d11bbcea717e7d5","sha256:76cf8a6027d189679aab173b6cb477367e664b0d55496005d907ae58ef6aa11b","sha256:13d1fde1620b8fa0108120b4bd11bade6cef36a510cf262d7415917b8ba05824"],"state_sha256":"2ca7909f215ec39945d95920054910a0b86b439ba18f4115dc15613b80ce102a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Op3QMWOje93TycGMgyd6Ir/aNF1zuzB+DNSEbVCIZf3RRPHk1kZK9Tjh1REA4Ui6hLV+bZNtYBHDORUu63K6CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T12:11:34.977274Z","bundle_sha256":"b34405af29db1a50a0ba3fe1f51cae89e4279653f32c40e2136465217362dbf0"}}