{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CAQMXCEFPYSY43KCMJZVTXYHK4","short_pith_number":"pith:CAQMXCEF","schema_version":"1.0","canonical_sha256":"1020cb88857e258e6d42627359df07571395ebc689cb60fa08b53b323abf0ba5","source":{"kind":"arxiv","id":"2511.21299","version":2},"attestation_state":"computed","paper":{"title":"Discovery and recovery of crystalline materials with property-conditioned transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Amil Aligayev, Bradley A. A. Martin, Cyprien Bone, Javier Dominguez, Keith T. Butler, Kuangdai Leng, Luis M. Antunes, Matthew Walker, Ricardo Grau-Crespo","submitted_at":"2025-11-26T11:42:28Z","abstract_excerpt":"Generative models have recently shown great promise for accelerating the design and discovery of new functional materials. Conditional generation enhances this capacity by allowing inverse design, where specific desired properties can be requested during the generation process. However, conditioning of transformer-based approaches, in particular, is constrained by discrete tokenisation schemes and the risk of catastrophic forgetting during fine-tuning. This work introduces CrystaLLM-{\\pi} (property injection), a conditional autoregressive framework that integrates continuous property represent"},"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":"2511.21299","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2025-11-26T11:42:28Z","cross_cats_sorted":["cond-mat.dis-nn"],"title_canon_sha256":"81152303007772cf431325d33e8d4454ec1d3cadcde8cf91bb11e9452630f901","abstract_canon_sha256":"552abc24d6a4962fdb6a78414b24fbdd4744c8d4149609e301a6cf905365b80e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:04:58.843931Z","signature_b64":"OYtU8uvIX0FkoBRmhOZqT3nC6R8OU2vTvYIDvLSkyF6aHDn8zR6BLgL90CprHkIlJSCI3JZM6hnRmbHKsu+aDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1020cb88857e258e6d42627359df07571395ebc689cb60fa08b53b323abf0ba5","last_reissued_at":"2026-05-29T01:04:58.843244Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:04:58.843244Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discovery and recovery of crystalline materials with property-conditioned transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn"],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Amil Aligayev, Bradley A. A. Martin, Cyprien Bone, Javier Dominguez, Keith T. Butler, Kuangdai Leng, Luis M. Antunes, Matthew Walker, Ricardo Grau-Crespo","submitted_at":"2025-11-26T11:42:28Z","abstract_excerpt":"Generative models have recently shown great promise for accelerating the design and discovery of new functional materials. Conditional generation enhances this capacity by allowing inverse design, where specific desired properties can be requested during the generation process. However, conditioning of transformer-based approaches, in particular, is constrained by discrete tokenisation schemes and the risk of catastrophic forgetting during fine-tuning. This work introduces CrystaLLM-{\\pi} (property injection), a conditional autoregressive framework that integrates continuous property represent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.21299","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/2511.21299/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":"2511.21299","created_at":"2026-05-29T01:04:58.843342+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.21299v2","created_at":"2026-05-29T01:04:58.843342+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.21299","created_at":"2026-05-29T01:04:58.843342+00:00"},{"alias_kind":"pith_short_12","alias_value":"CAQMXCEFPYSY","created_at":"2026-05-29T01:04:58.843342+00:00"},{"alias_kind":"pith_short_16","alias_value":"CAQMXCEFPYSY43KC","created_at":"2026-05-29T01:04:58.843342+00:00"},{"alias_kind":"pith_short_8","alias_value":"CAQMXCEF","created_at":"2026-05-29T01:04:58.843342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.16612","citing_title":"PRISMat: Policy-Driven, Permutation-Invariant Autoregressive Material Generation","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27709","citing_title":"Conditional Generative Models Enable Targeted Exploration of MAX Phase Design Space","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CAQMXCEFPYSY43KCMJZVTXYHK4","json":"https://pith.science/pith/CAQMXCEFPYSY43KCMJZVTXYHK4.json","graph_json":"https://pith.science/api/pith-number/CAQMXCEFPYSY43KCMJZVTXYHK4/graph.json","events_json":"https://pith.science/api/pith-number/CAQMXCEFPYSY43KCMJZVTXYHK4/events.json","paper":"https://pith.science/paper/CAQMXCEF"},"agent_actions":{"view_html":"https://pith.science/pith/CAQMXCEFPYSY43KCMJZVTXYHK4","download_json":"https://pith.science/pith/CAQMXCEFPYSY43KCMJZVTXYHK4.json","view_paper":"https://pith.science/paper/CAQMXCEF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.21299&json=true","fetch_graph":"https://pith.science/api/pith-number/CAQMXCEFPYSY43KCMJZVTXYHK4/graph.json","fetch_events":"https://pith.science/api/pith-number/CAQMXCEFPYSY43KCMJZVTXYHK4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CAQMXCEFPYSY43KCMJZVTXYHK4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CAQMXCEFPYSY43KCMJZVTXYHK4/action/storage_attestation","attest_author":"https://pith.science/pith/CAQMXCEFPYSY43KCMJZVTXYHK4/action/author_attestation","sign_citation":"https://pith.science/pith/CAQMXCEFPYSY43KCMJZVTXYHK4/action/citation_signature","submit_replication":"https://pith.science/pith/CAQMXCEFPYSY43KCMJZVTXYHK4/action/replication_record"}},"created_at":"2026-05-29T01:04:58.843342+00:00","updated_at":"2026-05-29T01:04:58.843342+00:00"}