{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PTYC4L33TSVZEDPHDXKYLV7IVU","short_pith_number":"pith:PTYC4L33","schema_version":"1.0","canonical_sha256":"7cf02e2f7b9cab920de71dd585d7e8ad3dde057fd598efff1d5e9f7750d8228c","source":{"kind":"arxiv","id":"2311.09235","version":2},"attestation_state":"computed","paper":{"title":"Scalable Diffusion for Materials Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amil Merchant, Dale Schuurmans, Ekin Dogus Cubuk, Igor Mordatch, KwangHwan Cho, Pieter Abbeel, Sherry Yang","submitted_at":"2023-10-18T15:49:39Z","abstract_excerpt":"Generative models trained on internet-scale data are capable of generating novel and realistic texts, images, and videos. A natural next question is whether these models can advance science, for example by generating novel stable materials. Traditionally, models with explicit structures (e.g., graphs) have been used in modeling structural relationships in scientific data (e.g., atoms and bonds in crystals), but generating structures can be difficult to scale to large and complex systems. Another challenge in generating materials is the mismatch between standard generative modeling metrics and "},"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":"2311.09235","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-18T15:49:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d8a07ca1a1a878ec876a5609632f8aa3efd0b6a57314aad4f40972d592f1f3e1","abstract_canon_sha256":"e87c2b4d49a106423227b7b1d5ba5bbe46395dcd4f56af5cb5e87159dc96b12d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:43.097226Z","signature_b64":"G3HIuHPtXO8sRx7PA0ikZnWB/0xdO4IDPI6+WQDdnMBBzWsxuyo2h1jt34wfWSzn5NhQZIaF/E6XYlop4nRCBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cf02e2f7b9cab920de71dd585d7e8ad3dde057fd598efff1d5e9f7750d8228c","last_reissued_at":"2026-07-05T08:26:43.096731Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:43.096731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable Diffusion for Materials Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amil Merchant, Dale Schuurmans, Ekin Dogus Cubuk, Igor Mordatch, KwangHwan Cho, Pieter Abbeel, Sherry Yang","submitted_at":"2023-10-18T15:49:39Z","abstract_excerpt":"Generative models trained on internet-scale data are capable of generating novel and realistic texts, images, and videos. A natural next question is whether these models can advance science, for example by generating novel stable materials. Traditionally, models with explicit structures (e.g., graphs) have been used in modeling structural relationships in scientific data (e.g., atoms and bonds in crystals), but generating structures can be difficult to scale to large and complex systems. Another challenge in generating materials is the mismatch between standard generative modeling metrics and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09235","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/2311.09235/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":"2311.09235","created_at":"2026-07-05T08:26:43.096789+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.09235v2","created_at":"2026-07-05T08:26:43.096789+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09235","created_at":"2026-07-05T08:26:43.096789+00:00"},{"alias_kind":"pith_short_12","alias_value":"PTYC4L33TSVZ","created_at":"2026-07-05T08:26:43.096789+00:00"},{"alias_kind":"pith_short_16","alias_value":"PTYC4L33TSVZEDPH","created_at":"2026-07-05T08:26:43.096789+00:00"},{"alias_kind":"pith_short_8","alias_value":"PTYC4L33","created_at":"2026-07-05T08:26:43.096789+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17445","citing_title":"Toward Controllable Catalyst Inverse Design via Large-Scale Autoregressive Pretraining","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17254","citing_title":"CatalyticMLLM: A Graph-Text Multimodal Large Language Model for Catalytic Materials","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2602.20210","citing_title":"Multimodal Crystal Flow: Any-to-Any Modality Generation for Unified Crystal Modeling","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17254","citing_title":"CatalyticMLLM: A Graph-Text Multimodal Large Language Model for Catalytic Materials","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17254","citing_title":"CatalyticMLLM: A Graph-Text Multimodal Large Language Model for Catalytic Materials","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PTYC4L33TSVZEDPHDXKYLV7IVU","json":"https://pith.science/pith/PTYC4L33TSVZEDPHDXKYLV7IVU.json","graph_json":"https://pith.science/api/pith-number/PTYC4L33TSVZEDPHDXKYLV7IVU/graph.json","events_json":"https://pith.science/api/pith-number/PTYC4L33TSVZEDPHDXKYLV7IVU/events.json","paper":"https://pith.science/paper/PTYC4L33"},"agent_actions":{"view_html":"https://pith.science/pith/PTYC4L33TSVZEDPHDXKYLV7IVU","download_json":"https://pith.science/pith/PTYC4L33TSVZEDPHDXKYLV7IVU.json","view_paper":"https://pith.science/paper/PTYC4L33","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.09235&json=true","fetch_graph":"https://pith.science/api/pith-number/PTYC4L33TSVZEDPHDXKYLV7IVU/graph.json","fetch_events":"https://pith.science/api/pith-number/PTYC4L33TSVZEDPHDXKYLV7IVU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PTYC4L33TSVZEDPHDXKYLV7IVU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PTYC4L33TSVZEDPHDXKYLV7IVU/action/storage_attestation","attest_author":"https://pith.science/pith/PTYC4L33TSVZEDPHDXKYLV7IVU/action/author_attestation","sign_citation":"https://pith.science/pith/PTYC4L33TSVZEDPHDXKYLV7IVU/action/citation_signature","submit_replication":"https://pith.science/pith/PTYC4L33TSVZEDPHDXKYLV7IVU/action/replication_record"}},"created_at":"2026-07-05T08:26:43.096789+00:00","updated_at":"2026-07-05T08:26:43.096789+00:00"}