{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LE4EXPJPCHF25XC62AN6YTCHE6","short_pith_number":"pith:LE4EXPJP","schema_version":"1.0","canonical_sha256":"59384bbd2f11cbaedc5ed01bec4c4727a076b563820deb1679af97f30cb43ef2","source":{"kind":"arxiv","id":"2503.00152","version":1},"attestation_state":"computed","paper":{"title":"Invariant Tokenization of Crystalline Materials for Language Model Enabled Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cond-mat.mtrl-sci"],"primary_cat":"cs.LG","authors_text":"Carl Edwards, Heng Ji, Hongyi Ling, Kenna Ashen, Keqiang Yan, Marinka Zitnik, Raymundo Arr\\'oyave, Shuiwang Ji, Xiaofeng Qian, Xiaoning Qian, Xiner Li","submitted_at":"2025-02-28T20:02:53Z","abstract_excerpt":"We consider the problem of crystal materials generation using language models (LMs). A key step is to convert 3D crystal structures into 1D sequences to be processed by LMs. Prior studies used the crystallographic information framework (CIF) file stream, which fails to ensure SE(3) and periodic invariance and may not lead to unique sequence representations for a given crystal structure. Here, we propose a novel method, known as Mat2Seq, to tackle this challenge. Mat2Seq converts 3D crystal structures into 1D sequences and ensures that different mathematical descriptions of the same crystal are"},"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":"2503.00152","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-28T20:02:53Z","cross_cats_sorted":["cond-mat.mtrl-sci"],"title_canon_sha256":"e7d48988c6f454f81b075ad93e45f59546f8e0bd90415337a088cb382a90b5de","abstract_canon_sha256":"45121a990a33351a8ffbd95e92c8d7277beb846faceed257c7aceff8a72366ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:18.115209Z","signature_b64":"JDMkvzmrRkeiNjEl2QnZ3Ds1jWCx3fiDBFEN8BtuxRJsMK7ca4eBMCLWhRSXORbbAUH19otdiI2WnWFMc2s+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59384bbd2f11cbaedc5ed01bec4c4727a076b563820deb1679af97f30cb43ef2","last_reissued_at":"2026-07-05T10:22:18.114672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:18.114672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Invariant Tokenization of Crystalline Materials for Language Model Enabled Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cond-mat.mtrl-sci"],"primary_cat":"cs.LG","authors_text":"Carl Edwards, Heng Ji, Hongyi Ling, Kenna Ashen, Keqiang Yan, Marinka Zitnik, Raymundo Arr\\'oyave, Shuiwang Ji, Xiaofeng Qian, Xiaoning Qian, Xiner Li","submitted_at":"2025-02-28T20:02:53Z","abstract_excerpt":"We consider the problem of crystal materials generation using language models (LMs). A key step is to convert 3D crystal structures into 1D sequences to be processed by LMs. Prior studies used the crystallographic information framework (CIF) file stream, which fails to ensure SE(3) and periodic invariance and may not lead to unique sequence representations for a given crystal structure. Here, we propose a novel method, known as Mat2Seq, to tackle this challenge. Mat2Seq converts 3D crystal structures into 1D sequences and ensures that different mathematical descriptions of the same crystal are"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00152","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/2503.00152/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":"2503.00152","created_at":"2026-07-05T10:22:18.114741+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.00152v1","created_at":"2026-07-05T10:22:18.114741+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00152","created_at":"2026-07-05T10:22:18.114741+00:00"},{"alias_kind":"pith_short_12","alias_value":"LE4EXPJPCHF2","created_at":"2026-07-05T10:22:18.114741+00:00"},{"alias_kind":"pith_short_16","alias_value":"LE4EXPJPCHF25XC6","created_at":"2026-07-05T10:22:18.114741+00:00"},{"alias_kind":"pith_short_8","alias_value":"LE4EXPJP","created_at":"2026-07-05T10:22:18.114741+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/LE4EXPJPCHF25XC62AN6YTCHE6","json":"https://pith.science/pith/LE4EXPJPCHF25XC62AN6YTCHE6.json","graph_json":"https://pith.science/api/pith-number/LE4EXPJPCHF25XC62AN6YTCHE6/graph.json","events_json":"https://pith.science/api/pith-number/LE4EXPJPCHF25XC62AN6YTCHE6/events.json","paper":"https://pith.science/paper/LE4EXPJP"},"agent_actions":{"view_html":"https://pith.science/pith/LE4EXPJPCHF25XC62AN6YTCHE6","download_json":"https://pith.science/pith/LE4EXPJPCHF25XC62AN6YTCHE6.json","view_paper":"https://pith.science/paper/LE4EXPJP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.00152&json=true","fetch_graph":"https://pith.science/api/pith-number/LE4EXPJPCHF25XC62AN6YTCHE6/graph.json","fetch_events":"https://pith.science/api/pith-number/LE4EXPJPCHF25XC62AN6YTCHE6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LE4EXPJPCHF25XC62AN6YTCHE6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LE4EXPJPCHF25XC62AN6YTCHE6/action/storage_attestation","attest_author":"https://pith.science/pith/LE4EXPJPCHF25XC62AN6YTCHE6/action/author_attestation","sign_citation":"https://pith.science/pith/LE4EXPJPCHF25XC62AN6YTCHE6/action/citation_signature","submit_replication":"https://pith.science/pith/LE4EXPJPCHF25XC62AN6YTCHE6/action/replication_record"}},"created_at":"2026-07-05T10:22:18.114741+00:00","updated_at":"2026-07-05T10:22:18.114741+00:00"}