{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JBTZV24NCF36R6MDKWA4I3GCS6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0bdb9c4bd14bf5cad951fb7a646714c65c7c12ff606ddbc0218f41eb58da9063","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T16:15:44Z","title_canon_sha256":"2738a19eb7fcf4335e29cd16beac96be5ab4d14f149d13976e3cff929fa76091"},"schema_version":"1.0","source":{"id":"2605.25998","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25998","created_at":"2026-05-26T02:05:22Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25998v1","created_at":"2026-05-26T02:05:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25998","created_at":"2026-05-26T02:05:22Z"},{"alias_kind":"pith_short_12","alias_value":"JBTZV24NCF36","created_at":"2026-05-26T02:05:22Z"},{"alias_kind":"pith_short_16","alias_value":"JBTZV24NCF36R6MD","created_at":"2026-05-26T02:05:22Z"},{"alias_kind":"pith_short_8","alias_value":"JBTZV24N","created_at":"2026-05-26T02:05:22Z"}],"graph_snapshots":[{"event_id":"sha256:7e48a98250963f149623d1b750625829857f86248bb038dd658f8ca004474a0c","target":"graph","created_at":"2026-05-26T02:05:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2605.25998/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model (LLM) development is currently driven by large-scale empirical iteration over data mixtures, reward models, routing strategies, and evaluation pipelines. Here, we argue that many central questions in LLM development and evaluation are inherently causal: What is the effect of adding a data domain during pretraining? How do annotator preferences change when LLMs generate text in a different style? Should a prompt be routed to a larger or smaller model given inference cost constraints? In general, causal methods are well-suited to such settings where interventions change outc","authors_text":"Abdurahman Maarouf, Athiya Deviyani, Dennis Frauen, Haorui Ma, Jonas Schweisthal, Konstantin Hess, Maresa Schr\\\"oder, Marie Brockschmidt, Rahul G. Krishnan, Sonali Parbhoo, Stefan Feuerriegel, Yuchen Ma, Yuxin Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T16:15:44Z","title":"Causal methods for LLM development and evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25998","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8fb30174e5c57e1da80d6c394500668dec1f32b5fcadaf817592c2aa5d93de98","target":"record","created_at":"2026-05-26T02:05:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0bdb9c4bd14bf5cad951fb7a646714c65c7c12ff606ddbc0218f41eb58da9063","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-25T16:15:44Z","title_canon_sha256":"2738a19eb7fcf4335e29cd16beac96be5ab4d14f149d13976e3cff929fa76091"},"schema_version":"1.0","source":{"id":"2605.25998","kind":"arxiv","version":1}},"canonical_sha256":"48679aeb8d1177e8f9835581c46cc2979f65866752115be5530ce50abaed5871","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48679aeb8d1177e8f9835581c46cc2979f65866752115be5530ce50abaed5871","first_computed_at":"2026-05-26T02:05:22.496436Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:05:22.496436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wD5de4/11htZh7jxNFTrur5h0P7LVivSkswA5oYao+r0UXzNju4ek5dIZqxtk1ZzdOs/DR+EOr2cIJy9EsetBQ==","signature_status":"signed_v1","signed_at":"2026-05-26T02:05:22.497197Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.25998","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8fb30174e5c57e1da80d6c394500668dec1f32b5fcadaf817592c2aa5d93de98","sha256:7e48a98250963f149623d1b750625829857f86248bb038dd658f8ca004474a0c"],"state_sha256":"8c86c87472d1ebf9b716af85670226594c9a24386300298c8485b08c43400773"}