{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XS5F5J54IXQUL2QNDZLTGJZHOY","short_pith_number":"pith:XS5F5J54","schema_version":"1.0","canonical_sha256":"bcba5ea7bc45e145ea0d1e5733272776251de62bde3d5aa2cb8c091634e47ac5","source":{"kind":"arxiv","id":"2502.09571","version":2},"attestation_state":"computed","paper":{"title":"DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Connor W. Coley, Montgomery Bohde, Mrunali Manjrekar, Runzhong Wang, Shuiwang Ji","submitted_at":"2025-02-13T18:29:48Z","abstract_excerpt":"Mass spectrometry plays a fundamental role in elucidating the structures of unknown molecules and subsequent scientific discoveries. One formulation of the structure elucidation task is the conditional de novo generation of molecular structure given a mass spectrum. Toward a more accurate and efficient scientific discovery pipeline for small molecules, we present DiffMS, a formula-restricted encoder-decoder generative network that achieves state-of-the-art performance on this task. The encoder utilizes a transformer architecture and models mass spectra domain knowledge such as peak formulae an"},"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":"2502.09571","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T18:29:48Z","cross_cats_sorted":["q-bio.QM"],"title_canon_sha256":"6dab0fcf7e098fa209849be9e2abe7abac062b5d326182c2278c662f206a97f6","abstract_canon_sha256":"664389ab5c7f6c6fed24213202a00df95ef9dcdb8edf024462b2668e0484b803"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:52.383027Z","signature_b64":"a4wyMh05opoOlj0BhSe/kVp8V8YVlwzsbahksWhmOKEeIJ4CtLXOpqN5y4iPytj01RWCbw0OoKGFvzfNvQOICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcba5ea7bc45e145ea0d1e5733272776251de62bde3d5aa2cb8c091634e47ac5","last_reissued_at":"2026-07-05T11:10:52.382531Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:52.382531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Connor W. Coley, Montgomery Bohde, Mrunali Manjrekar, Runzhong Wang, Shuiwang Ji","submitted_at":"2025-02-13T18:29:48Z","abstract_excerpt":"Mass spectrometry plays a fundamental role in elucidating the structures of unknown molecules and subsequent scientific discoveries. One formulation of the structure elucidation task is the conditional de novo generation of molecular structure given a mass spectrum. Toward a more accurate and efficient scientific discovery pipeline for small molecules, we present DiffMS, a formula-restricted encoder-decoder generative network that achieves state-of-the-art performance on this task. The encoder utilizes a transformer architecture and models mass spectra domain knowledge such as peak formulae an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09571","kind":"arxiv","version":2},"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/2502.09571/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":"2502.09571","created_at":"2026-07-05T11:10:52.382586+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.09571v2","created_at":"2026-07-05T11:10:52.382586+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09571","created_at":"2026-07-05T11:10:52.382586+00:00"},{"alias_kind":"pith_short_12","alias_value":"XS5F5J54IXQU","created_at":"2026-07-05T11:10:52.382586+00:00"},{"alias_kind":"pith_short_16","alias_value":"XS5F5J54IXQUL2QN","created_at":"2026-07-05T11:10:52.382586+00:00"},{"alias_kind":"pith_short_8","alias_value":"XS5F5J54","created_at":"2026-07-05T11:10:52.382586+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01595","citing_title":"Uncertainty-Calibrated Diffusion for Reliable 3D Molecular Graph Generation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18570","citing_title":"Streamlining Analysis and Design of Two-Dimensional Electronic Spectroscopy using Machine Learning","ref_index":196,"is_internal_anchor":false},{"citing_arxiv_id":"2508.08441","citing_title":"SpectraLLM: Uncovering the Ability of LLMs for Molecular Structure Elucidation from Multi-Spectral Data","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12980","citing_title":"CoRe-Gen: Robust Spectrum-to-Structure Generation under Imperfect Fingerprint Conditions","ref_index":5,"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":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XS5F5J54IXQUL2QNDZLTGJZHOY","json":"https://pith.science/pith/XS5F5J54IXQUL2QNDZLTGJZHOY.json","graph_json":"https://pith.science/api/pith-number/XS5F5J54IXQUL2QNDZLTGJZHOY/graph.json","events_json":"https://pith.science/api/pith-number/XS5F5J54IXQUL2QNDZLTGJZHOY/events.json","paper":"https://pith.science/paper/XS5F5J54"},"agent_actions":{"view_html":"https://pith.science/pith/XS5F5J54IXQUL2QNDZLTGJZHOY","download_json":"https://pith.science/pith/XS5F5J54IXQUL2QNDZLTGJZHOY.json","view_paper":"https://pith.science/paper/XS5F5J54","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.09571&json=true","fetch_graph":"https://pith.science/api/pith-number/XS5F5J54IXQUL2QNDZLTGJZHOY/graph.json","fetch_events":"https://pith.science/api/pith-number/XS5F5J54IXQUL2QNDZLTGJZHOY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XS5F5J54IXQUL2QNDZLTGJZHOY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XS5F5J54IXQUL2QNDZLTGJZHOY/action/storage_attestation","attest_author":"https://pith.science/pith/XS5F5J54IXQUL2QNDZLTGJZHOY/action/author_attestation","sign_citation":"https://pith.science/pith/XS5F5J54IXQUL2QNDZLTGJZHOY/action/citation_signature","submit_replication":"https://pith.science/pith/XS5F5J54IXQUL2QNDZLTGJZHOY/action/replication_record"}},"created_at":"2026-07-05T11:10:52.382586+00:00","updated_at":"2026-07-05T11:10:52.382586+00:00"}