{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XN7JKINTB7ZAT6ZJ6GRAMHANYF","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":"9c7aeefda0fe0a1fe2fe1d07a90f4eaf7cf35185114a9b8e90ed76cc20e79ee6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T12:19:35Z","title_canon_sha256":"d10fc07a07c7ca3ad7c22363b7db786fc778b45320878b3410b3aca3ebe93f22"},"schema_version":"1.0","source":{"id":"2605.19752","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19752","created_at":"2026-05-20T01:06:12Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19752v1","created_at":"2026-05-20T01:06:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19752","created_at":"2026-05-20T01:06:12Z"},{"alias_kind":"pith_short_12","alias_value":"XN7JKINTB7ZA","created_at":"2026-05-20T01:06:12Z"},{"alias_kind":"pith_short_16","alias_value":"XN7JKINTB7ZAT6ZJ","created_at":"2026-05-20T01:06:12Z"},{"alias_kind":"pith_short_8","alias_value":"XN7JKINT","created_at":"2026-05-20T01:06:12Z"}],"graph_snapshots":[{"event_id":"sha256:c0b9432def5ea2b86dc03dff326d3d4cb6c5bd60abcc984f3f2a0655e01e1604","target":"graph","created_at":"2026-05-20T01:06:12Z","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/2605.19752/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Accurately identifying metabolites i.e. small molecules from mass spectrometry data remains a core challenge in metabolomics, with broad applications in drug discovery, environmental analysis, and clinical research. We address the Molecule Retrieval task, which consists in recovering the chemical structure of a metabolite from its MS/MS spectrum given a set of candidate molecules. While the recent release of benchmark datasets such as MassSpecGym and Spectraverse has considerably accelerated the development of novel machine learning approaches, the complexity of data preprocessing pipelines an","authors_text":"Camille Lan\\c{c}on, Charlotte Laclau, Etienne Th\\'evenot, Florence d'Alch\\'e-Buc, Gabriel Melo, Paul Krzakala, R\\'emi Flamary","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T12:19:35Z","title":"MSAlign: Aligning Molecule and Mass Spectra Foundation Models for Metabolite Identification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19752","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":"sha256:0354b82b1d5206ad2d084a5c0d6a9c6757c68368151ebfeb9f63d0fe9a2cc5bd","target":"record","created_at":"2026-05-20T01:06:12Z","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":"9c7aeefda0fe0a1fe2fe1d07a90f4eaf7cf35185114a9b8e90ed76cc20e79ee6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T12:19:35Z","title_canon_sha256":"d10fc07a07c7ca3ad7c22363b7db786fc778b45320878b3410b3aca3ebe93f22"},"schema_version":"1.0","source":{"id":"2605.19752","kind":"arxiv","version":1}},"canonical_sha256":"bb7e9521b30ff209fb29f1a2061c0dc14717ad5ff9c9e10ec8b1282b4d3fe008","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb7e9521b30ff209fb29f1a2061c0dc14717ad5ff9c9e10ec8b1282b4d3fe008","first_computed_at":"2026-05-20T01:06:12.131747Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:06:12.131747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"feISexRXpEx/tCXNAjoGRpedG3M52qfSOfI3mJIn16iu3li2VizvG2sBMvrhwfNn3bG+wIj2jxlBBxqE7AVRCg==","signature_status":"signed_v1","signed_at":"2026-05-20T01:06:12.132231Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.19752","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0354b82b1d5206ad2d084a5c0d6a9c6757c68368151ebfeb9f63d0fe9a2cc5bd","sha256:c0b9432def5ea2b86dc03dff326d3d4cb6c5bd60abcc984f3f2a0655e01e1604"],"state_sha256":"f5beaed698d2c11e257a09f0477cca1898d05e5ded3ea5dfb144ee2a2d3ab7ce"}