{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OCS6MAZG6R7TKIK6DVNRW7MZDQ","short_pith_number":"pith:OCS6MAZG","schema_version":"1.0","canonical_sha256":"70a5e60326f47f35215e1d5b1b7d991c2b839837841835d0983e41a3f1eff295","source":{"kind":"arxiv","id":"2410.23326","version":3},"attestation_state":"computed","paper":{"title":"MassSpecGym: A benchmark for the discovery and identification of molecules","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Adamo Young, Anton Bushuiev, Apurva Kalia, Bo Wang, Corinna Brungs, David S. Wishart, Fei Wang, Fleming Kretschmer, Florian Huber, Hannes Rost, Janne Heirman, Josef Sivic, Juho Rousu, Justin J.J. van der Hooft, Kai D\\\"uhrkop, Li-Ping Liu, Luke Zhang, Marcus Ludwig, Michael A. Stravs, Niek F. de Jonge, Nils A. Haupt, Raman Samusevich, Robin Schmid, Roman Bushuiev, Russell Greiner, Sebastian B\\\"ocker, Soha Hassoun, Tom\\'a\\v{s} Pluskal, Tytus D. Mak, Wout Bittremieux","submitted_at":"2024-10-30T15:08:05Z","abstract_excerpt":"The discovery and identification of molecules in biological and environmental samples is crucial for advancing biomedical and chemical sciences. Tandem mass spectrometry (MS/MS) is the leading technique for high-throughput elucidation of molecular structures. However, decoding a molecular structure from its mass spectrum is exceptionally challenging, even when performed by human experts. As a result, the vast majority of acquired MS/MS spectra remain uninterpreted, thereby limiting our understanding of the underlying (bio)chemical processes. Despite decades of progress in machine learning appl"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.23326","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2024-10-30T15:08:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d1d823caf83169b1ebb68eae02e21eb3aa5ea73c13268ddd0d60a70930ae9db3","abstract_canon_sha256":"39feee2814498dcc75720b05fc6e85692e968a66953710f81886eec6b4f5bdb5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:24.836424Z","signature_b64":"2otAVuhiUkrKP2aVOE1ySuyNqV6TaiWVdqd8fg/WN0JWvk3AGEG3sFrEV5YFOsR03GrR+sdrxyLbszJxO1UpCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70a5e60326f47f35215e1d5b1b7d991c2b839837841835d0983e41a3f1eff295","last_reissued_at":"2026-07-05T10:14:24.835927Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:24.835927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MassSpecGym: A benchmark for the discovery and identification of molecules","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Adamo Young, Anton Bushuiev, Apurva Kalia, Bo Wang, Corinna Brungs, David S. Wishart, Fei Wang, Fleming Kretschmer, Florian Huber, Hannes Rost, Janne Heirman, Josef Sivic, Juho Rousu, Justin J.J. van der Hooft, Kai D\\\"uhrkop, Li-Ping Liu, Luke Zhang, Marcus Ludwig, Michael A. Stravs, Niek F. de Jonge, Nils A. Haupt, Raman Samusevich, Robin Schmid, Roman Bushuiev, Russell Greiner, Sebastian B\\\"ocker, Soha Hassoun, Tom\\'a\\v{s} Pluskal, Tytus D. Mak, Wout Bittremieux","submitted_at":"2024-10-30T15:08:05Z","abstract_excerpt":"The discovery and identification of molecules in biological and environmental samples is crucial for advancing biomedical and chemical sciences. Tandem mass spectrometry (MS/MS) is the leading technique for high-throughput elucidation of molecular structures. However, decoding a molecular structure from its mass spectrum is exceptionally challenging, even when performed by human experts. As a result, the vast majority of acquired MS/MS spectra remain uninterpreted, thereby limiting our understanding of the underlying (bio)chemical processes. Despite decades of progress in machine learning appl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23326","kind":"arxiv","version":3},"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/2410.23326/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.23326","created_at":"2026-07-05T10:14:24.835986+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.23326v3","created_at":"2026-07-05T10:14:24.835986+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23326","created_at":"2026-07-05T10:14:24.835986+00:00"},{"alias_kind":"pith_short_12","alias_value":"OCS6MAZG6R7T","created_at":"2026-07-05T10:14:24.835986+00:00"},{"alias_kind":"pith_short_16","alias_value":"OCS6MAZG6R7TKIK6","created_at":"2026-07-05T10:14:24.835986+00:00"},{"alias_kind":"pith_short_8","alias_value":"OCS6MAZG","created_at":"2026-07-05T10:14:24.835986+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18570","citing_title":"Streamlining Analysis and Design of Two-Dimensional Electronic Spectroscopy using Machine Learning","ref_index":164,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16648","citing_title":"FRIGID: Scaling Diffusion-Based Molecular Generation from Mass Spectra at Training and Inference Time","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OCS6MAZG6R7TKIK6DVNRW7MZDQ","json":"https://pith.science/pith/OCS6MAZG6R7TKIK6DVNRW7MZDQ.json","graph_json":"https://pith.science/api/pith-number/OCS6MAZG6R7TKIK6DVNRW7MZDQ/graph.json","events_json":"https://pith.science/api/pith-number/OCS6MAZG6R7TKIK6DVNRW7MZDQ/events.json","paper":"https://pith.science/paper/OCS6MAZG"},"agent_actions":{"view_html":"https://pith.science/pith/OCS6MAZG6R7TKIK6DVNRW7MZDQ","download_json":"https://pith.science/pith/OCS6MAZG6R7TKIK6DVNRW7MZDQ.json","view_paper":"https://pith.science/paper/OCS6MAZG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.23326&json=true","fetch_graph":"https://pith.science/api/pith-number/OCS6MAZG6R7TKIK6DVNRW7MZDQ/graph.json","fetch_events":"https://pith.science/api/pith-number/OCS6MAZG6R7TKIK6DVNRW7MZDQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OCS6MAZG6R7TKIK6DVNRW7MZDQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OCS6MAZG6R7TKIK6DVNRW7MZDQ/action/storage_attestation","attest_author":"https://pith.science/pith/OCS6MAZG6R7TKIK6DVNRW7MZDQ/action/author_attestation","sign_citation":"https://pith.science/pith/OCS6MAZG6R7TKIK6DVNRW7MZDQ/action/citation_signature","submit_replication":"https://pith.science/pith/OCS6MAZG6R7TKIK6DVNRW7MZDQ/action/replication_record"}},"created_at":"2026-07-05T10:14:24.835986+00:00","updated_at":"2026-07-05T10:14:24.835986+00:00"}