{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OZ67K5S3PVOXZYZVKUGRAJRMAT","short_pith_number":"pith:OZ67K5S3","schema_version":"1.0","canonical_sha256":"767df5765b7d5d7ce335550d10262c04ec721d3dd812625d12f8d6ccdd464381","source":{"kind":"arxiv","id":"2605.14754","version":1},"attestation_state":"computed","paper":{"title":"XDomainBench: Diagnosing Reasoning Collapse in High-Dimensional Scientific Knowledge Composition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chau Yuen, Che Wang, Fei Huang, Foo Ping, Fuyao Zhang, Gong Zhiren, Jiaming Zhang, Tiantong Wu, Wei Yang Bryan Lim, Yikun Hou, Yilei Zhao, Yurong Hao","submitted_at":"2026-05-14T12:19:19Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly deployed for knowledge synthesis, yet their capacity for compositional generalization in scientific knowledge remains under-characterized. Existing benchmarks primarily focus on single-turn restricted scenarios, failing to capture the capability boundaries exposed by real-world interactive scientific workflows. To address this, we introduce XDomainBench, a diagnostic benchmark for interactive interdisciplinary scientific reasoning. We formalize the composition order and mixture structure to enable systematic stress-testing from single-discipline to"},"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":"2605.14754","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-14T12:19:19Z","cross_cats_sorted":[],"title_canon_sha256":"f0617e25d504b1071bac740bf31dbb8613b44ebcf65c1f3cfce8511e1b346784","abstract_canon_sha256":"c9f3c556c6d08ef788a8e99b74c8078f848a70ed091dc41fc3505e895f27c896"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:58.810707Z","signature_b64":"YSGZWV7oLs+VSBb1KCQlEt0BDW+EJzUrn1+hWVkY0h4bO2PuHTnyQsXDk8maWGHzTExglp1+duHT/G8TWlFPCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"767df5765b7d5d7ce335550d10262c04ec721d3dd812625d12f8d6ccdd464381","last_reissued_at":"2026-05-17T23:38:58.809906Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:58.809906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XDomainBench: Diagnosing Reasoning Collapse in High-Dimensional Scientific Knowledge Composition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chau Yuen, Che Wang, Fei Huang, Foo Ping, Fuyao Zhang, Gong Zhiren, Jiaming Zhang, Tiantong Wu, Wei Yang Bryan Lim, Yikun Hou, Yilei Zhao, Yurong Hao","submitted_at":"2026-05-14T12:19:19Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly deployed for knowledge synthesis, yet their capacity for compositional generalization in scientific knowledge remains under-characterized. Existing benchmarks primarily focus on single-turn restricted scenarios, failing to capture the capability boundaries exposed by real-world interactive scientific workflows. To address this, we introduce XDomainBench, a diagnostic benchmark for interactive interdisciplinary scientific reasoning. We formalize the composition order and mixture structure to enable systematic stress-testing from single-discipline to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14754","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":""},"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":"2605.14754","created_at":"2026-05-17T23:38:58.810033+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14754v1","created_at":"2026-05-17T23:38:58.810033+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14754","created_at":"2026-05-17T23:38:58.810033+00:00"},{"alias_kind":"pith_short_12","alias_value":"OZ67K5S3PVOX","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"OZ67K5S3PVOXZYZV","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"OZ67K5S3","created_at":"2026-05-18T12:33:37.589309+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/OZ67K5S3PVOXZYZVKUGRAJRMAT","json":"https://pith.science/pith/OZ67K5S3PVOXZYZVKUGRAJRMAT.json","graph_json":"https://pith.science/api/pith-number/OZ67K5S3PVOXZYZVKUGRAJRMAT/graph.json","events_json":"https://pith.science/api/pith-number/OZ67K5S3PVOXZYZVKUGRAJRMAT/events.json","paper":"https://pith.science/paper/OZ67K5S3"},"agent_actions":{"view_html":"https://pith.science/pith/OZ67K5S3PVOXZYZVKUGRAJRMAT","download_json":"https://pith.science/pith/OZ67K5S3PVOXZYZVKUGRAJRMAT.json","view_paper":"https://pith.science/paper/OZ67K5S3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14754&json=true","fetch_graph":"https://pith.science/api/pith-number/OZ67K5S3PVOXZYZVKUGRAJRMAT/graph.json","fetch_events":"https://pith.science/api/pith-number/OZ67K5S3PVOXZYZVKUGRAJRMAT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OZ67K5S3PVOXZYZVKUGRAJRMAT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OZ67K5S3PVOXZYZVKUGRAJRMAT/action/storage_attestation","attest_author":"https://pith.science/pith/OZ67K5S3PVOXZYZVKUGRAJRMAT/action/author_attestation","sign_citation":"https://pith.science/pith/OZ67K5S3PVOXZYZVKUGRAJRMAT/action/citation_signature","submit_replication":"https://pith.science/pith/OZ67K5S3PVOXZYZVKUGRAJRMAT/action/replication_record"}},"created_at":"2026-05-17T23:38:58.810033+00:00","updated_at":"2026-05-17T23:38:58.810033+00:00"}