{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:36JC2F7AV6DZEX4CJFVB5JBKZQ","short_pith_number":"pith:36JC2F7A","schema_version":"1.0","canonical_sha256":"df922d17e0af87925f82496a1ea42acc0ef6d5c4917cb03cfb3f51ee8464944d","source":{"kind":"arxiv","id":"2605.18791","version":1},"attestation_state":"computed","paper":{"title":"SpecX: A Large-Scale Benchmark for Multi-Modal Spectroscopy and Cross-Paradigm Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","q-bio.OT"],"primary_cat":"eess.IV","authors_text":"Chengrui Xiang, Haowen Chen, Tengfei Ma, Tong Wang, Xiangxiang Zeng, Yujie Chen","submitted_at":"2026-05-11T04:12:58Z","abstract_excerpt":"Existing spectral benchmarks are limited in scale, modality alignment, and evaluation scope, and typically focus on either specialized models or multimodal language models (MLLMs). We introduce SpecX, a large-scale benchmark for multi-modal spectroscopy with cross-paradigm evaluation. SpecX contains 1.7M molecules with diverse spectral modalities, including NMR (1H, 13C, HSQC), IR, MS,UV,Raman and FL, and is organized into three tiers: a large-scale dataset for pretraining, an aligned multi-spectral subset for benchmarking, and a high-quality experimental subset for evaluation. SpecX supports "},"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":"2605.18791","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2026-05-11T04:12:58Z","cross_cats_sorted":["cs.CV","cs.LG","q-bio.OT"],"title_canon_sha256":"73ff9e31da78d842652bdee3635d74bbfdaff6da423ff59e80eb725fa50ee9dc","abstract_canon_sha256":"6750199eff54ae442be454e097daa619756bdf56b774f0dfa709fe0621574a08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:22.507541Z","signature_b64":"kZNhdknvnIBVzId6zyrFTPJno4QTNgtN1SVvH4Qk3d8AEe2y3ZBYwoSMA/SQefm8msjhPkCOpYFPDU9MLpAKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df922d17e0af87925f82496a1ea42acc0ef6d5c4917cb03cfb3f51ee8464944d","last_reissued_at":"2026-05-20T00:06:22.506656Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:22.506656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SpecX: A Large-Scale Benchmark for Multi-Modal Spectroscopy and Cross-Paradigm Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG","q-bio.OT"],"primary_cat":"eess.IV","authors_text":"Chengrui Xiang, Haowen Chen, Tengfei Ma, Tong Wang, Xiangxiang Zeng, Yujie Chen","submitted_at":"2026-05-11T04:12:58Z","abstract_excerpt":"Existing spectral benchmarks are limited in scale, modality alignment, and evaluation scope, and typically focus on either specialized models or multimodal language models (MLLMs). We introduce SpecX, a large-scale benchmark for multi-modal spectroscopy with cross-paradigm evaluation. SpecX contains 1.7M molecules with diverse spectral modalities, including NMR (1H, 13C, HSQC), IR, MS,UV,Raman and FL, and is organized into three tiers: a large-scale dataset for pretraining, an aligned multi-spectral subset for benchmarking, and a high-quality experimental subset for evaluation. SpecX supports "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18791","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/2605.18791/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":"2605.18791","created_at":"2026-05-20T00:06:22.506805+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18791v1","created_at":"2026-05-20T00:06:22.506805+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18791","created_at":"2026-05-20T00:06:22.506805+00:00"},{"alias_kind":"pith_short_12","alias_value":"36JC2F7AV6DZ","created_at":"2026-05-20T00:06:22.506805+00:00"},{"alias_kind":"pith_short_16","alias_value":"36JC2F7AV6DZEX4C","created_at":"2026-05-20T00:06:22.506805+00:00"},{"alias_kind":"pith_short_8","alias_value":"36JC2F7A","created_at":"2026-05-20T00:06:22.506805+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/36JC2F7AV6DZEX4CJFVB5JBKZQ","json":"https://pith.science/pith/36JC2F7AV6DZEX4CJFVB5JBKZQ.json","graph_json":"https://pith.science/api/pith-number/36JC2F7AV6DZEX4CJFVB5JBKZQ/graph.json","events_json":"https://pith.science/api/pith-number/36JC2F7AV6DZEX4CJFVB5JBKZQ/events.json","paper":"https://pith.science/paper/36JC2F7A"},"agent_actions":{"view_html":"https://pith.science/pith/36JC2F7AV6DZEX4CJFVB5JBKZQ","download_json":"https://pith.science/pith/36JC2F7AV6DZEX4CJFVB5JBKZQ.json","view_paper":"https://pith.science/paper/36JC2F7A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18791&json=true","fetch_graph":"https://pith.science/api/pith-number/36JC2F7AV6DZEX4CJFVB5JBKZQ/graph.json","fetch_events":"https://pith.science/api/pith-number/36JC2F7AV6DZEX4CJFVB5JBKZQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/36JC2F7AV6DZEX4CJFVB5JBKZQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/36JC2F7AV6DZEX4CJFVB5JBKZQ/action/storage_attestation","attest_author":"https://pith.science/pith/36JC2F7AV6DZEX4CJFVB5JBKZQ/action/author_attestation","sign_citation":"https://pith.science/pith/36JC2F7AV6DZEX4CJFVB5JBKZQ/action/citation_signature","submit_replication":"https://pith.science/pith/36JC2F7AV6DZEX4CJFVB5JBKZQ/action/replication_record"}},"created_at":"2026-05-20T00:06:22.506805+00:00","updated_at":"2026-05-20T00:06:22.506805+00:00"}