{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZDDG5YSWKEYOD2KSIP6G634S4I","short_pith_number":"pith:ZDDG5YSW","schema_version":"1.0","canonical_sha256":"c8c66ee2565130e1e95243fc6f6f92e23d20a7c8098350f8deee6ac1fe581694","source":{"kind":"arxiv","id":"2409.12293","version":3},"attestation_state":"computed","paper":{"title":"In-Context Learning of Linear Systems: Generalization Theory and Applications to Operator Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Frank Cole, Tianhao Zhang, Wuzhe Xu, Yulong Lu","submitted_at":"2024-09-18T19:59:50Z","abstract_excerpt":"We study theoretical guarantees for solving linear systems in-context using a linear transformer architecture. For in-domain generalization, we provide neural scaling laws that bound the generalization error in terms of the number of tasks and sizes of samples used in training and inference. For out-of-domain generalization, we find that the behavior of trained transformers under task distribution shifts depends crucially on the distribution of the tasks seen during training. We introduce a novel notion of task diversity and show that it defines a necessary and sufficient condition for pre-tra"},"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":"2409.12293","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-18T19:59:50Z","cross_cats_sorted":["cs.NA","math.NA","stat.ML"],"title_canon_sha256":"0cb6cacff7055c6d41604dce9b9cb40b1a9d0ecb12589420d98fc84c8acd840a","abstract_canon_sha256":"511bf2c63cfaa1552ec9008044cd7467abeeefefa217cd8637d3fe1bd9a39a64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:38.673295Z","signature_b64":"g+2GAaxXhT0AaVNpYGwsrd4Hq0gB5D3Jz9e+gojje52Xx2ZDlBW0kC04bjyjd/ptn+3tUW0B+9pql2CSU6k/Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8c66ee2565130e1e95243fc6f6f92e23d20a7c8098350f8deee6ac1fe581694","last_reissued_at":"2026-07-05T11:08:38.672821Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:38.672821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In-Context Learning of Linear Systems: Generalization Theory and Applications to Operator Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Frank Cole, Tianhao Zhang, Wuzhe Xu, Yulong Lu","submitted_at":"2024-09-18T19:59:50Z","abstract_excerpt":"We study theoretical guarantees for solving linear systems in-context using a linear transformer architecture. For in-domain generalization, we provide neural scaling laws that bound the generalization error in terms of the number of tasks and sizes of samples used in training and inference. For out-of-domain generalization, we find that the behavior of trained transformers under task distribution shifts depends crucially on the distribution of the tasks seen during training. We introduce a novel notion of task diversity and show that it defines a necessary and sufficient condition for pre-tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12293","kind":"arxiv","version":3},"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/2409.12293/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":"2409.12293","created_at":"2026-07-05T11:08:38.672873+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.12293v3","created_at":"2026-07-05T11:08:38.672873+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12293","created_at":"2026-07-05T11:08:38.672873+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZDDG5YSWKEYO","created_at":"2026-07-05T11:08:38.672873+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZDDG5YSWKEYOD2KS","created_at":"2026-07-05T11:08:38.672873+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZDDG5YSW","created_at":"2026-07-05T11:08:38.672873+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12318","citing_title":"Harness In-Context Operator Learning with Chain of Operators","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2506.10959","citing_title":"Understanding In-Context Learning on Structured Manifolds: Bridging Attention to Kernel Methods","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05176","citing_title":"Understanding In-Context Learning for Nonlinear Regression with Transformers: Attention as Featurizer","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZDDG5YSWKEYOD2KSIP6G634S4I","json":"https://pith.science/pith/ZDDG5YSWKEYOD2KSIP6G634S4I.json","graph_json":"https://pith.science/api/pith-number/ZDDG5YSWKEYOD2KSIP6G634S4I/graph.json","events_json":"https://pith.science/api/pith-number/ZDDG5YSWKEYOD2KSIP6G634S4I/events.json","paper":"https://pith.science/paper/ZDDG5YSW"},"agent_actions":{"view_html":"https://pith.science/pith/ZDDG5YSWKEYOD2KSIP6G634S4I","download_json":"https://pith.science/pith/ZDDG5YSWKEYOD2KSIP6G634S4I.json","view_paper":"https://pith.science/paper/ZDDG5YSW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.12293&json=true","fetch_graph":"https://pith.science/api/pith-number/ZDDG5YSWKEYOD2KSIP6G634S4I/graph.json","fetch_events":"https://pith.science/api/pith-number/ZDDG5YSWKEYOD2KSIP6G634S4I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZDDG5YSWKEYOD2KSIP6G634S4I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZDDG5YSWKEYOD2KSIP6G634S4I/action/storage_attestation","attest_author":"https://pith.science/pith/ZDDG5YSWKEYOD2KSIP6G634S4I/action/author_attestation","sign_citation":"https://pith.science/pith/ZDDG5YSWKEYOD2KSIP6G634S4I/action/citation_signature","submit_replication":"https://pith.science/pith/ZDDG5YSWKEYOD2KSIP6G634S4I/action/replication_record"}},"created_at":"2026-07-05T11:08:38.672873+00:00","updated_at":"2026-07-05T11:08:38.672873+00:00"}