{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:655HUOMXKHCVQVJFVNEQHTDWXL","short_pith_number":"pith:655HUOMX","schema_version":"1.0","canonical_sha256":"f77a7a399751c5585525ab4903cc76baf4066d7b30300005d00ff1118f7b4b03","source":{"kind":"arxiv","id":"2307.02419","version":1},"attestation_state":"computed","paper":{"title":"In-Context Learning for Attention Scheme: from Single Softmax Regression to Multiple Softmax Regression via a Tensor Trick","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Shenghao Xie, Yeqi Gao, Zhao Song","submitted_at":"2023-07-05T16:41:01Z","abstract_excerpt":"Large language models (LLMs) have brought significant and transformative changes in human society. These models have demonstrated remarkable capabilities in natural language understanding and generation, leading to various advancements and impacts across several domains.\n  We consider the in-context learning under two formulation for attention related regression in this work. Given matrices $A_1 \\in \\mathbb{R}^{n \\times d}$, and $A_2 \\in \\mathbb{R}^{n \\times d}$ and $B \\in \\mathbb{R}^{n \\times n}$, the purpose is to solve some certain optimization problems: Normalized version $\\min_{X} \\| D(X)"},"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":"2307.02419","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-07-05T16:41:01Z","cross_cats_sorted":[],"title_canon_sha256":"d9f21550d81285b74e66a0dff1b40acc513b566c5d85993166b2b28e51b7f46c","abstract_canon_sha256":"9bc77391ca8c04d768f4f377884aa0b11e3545f5b597de18a37729c94372445a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:08.919052Z","signature_b64":"iZNkK4jqnGVHVo2niA/f+XoVFxdZYwHkuSNTO0XBa4yiYWUqSF3GMdBBOxoQYWXUqaP43g7nwS4JO/tdnGKrCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f77a7a399751c5585525ab4903cc76baf4066d7b30300005d00ff1118f7b4b03","last_reissued_at":"2026-07-05T06:28:08.918631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:08.918631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In-Context Learning for Attention Scheme: from Single Softmax Regression to Multiple Softmax Regression via a Tensor Trick","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Shenghao Xie, Yeqi Gao, Zhao Song","submitted_at":"2023-07-05T16:41:01Z","abstract_excerpt":"Large language models (LLMs) have brought significant and transformative changes in human society. These models have demonstrated remarkable capabilities in natural language understanding and generation, leading to various advancements and impacts across several domains.\n  We consider the in-context learning under two formulation for attention related regression in this work. Given matrices $A_1 \\in \\mathbb{R}^{n \\times d}$, and $A_2 \\in \\mathbb{R}^{n \\times d}$ and $B \\in \\mathbb{R}^{n \\times n}$, the purpose is to solve some certain optimization problems: Normalized version $\\min_{X} \\| D(X)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.02419","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2307.02419/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":"2307.02419","created_at":"2026-07-05T06:28:08.918694+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.02419v1","created_at":"2026-07-05T06:28:08.918694+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.02419","created_at":"2026-07-05T06:28:08.918694+00:00"},{"alias_kind":"pith_short_12","alias_value":"655HUOMXKHCV","created_at":"2026-07-05T06:28:08.918694+00:00"},{"alias_kind":"pith_short_16","alias_value":"655HUOMXKHCVQVJF","created_at":"2026-07-05T06:28:08.918694+00:00"},{"alias_kind":"pith_short_8","alias_value":"655HUOMX","created_at":"2026-07-05T06:28:08.918694+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06167","citing_title":"Universal Approximation of Visual Autoregressive Transformers","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/655HUOMXKHCVQVJFVNEQHTDWXL","json":"https://pith.science/pith/655HUOMXKHCVQVJFVNEQHTDWXL.json","graph_json":"https://pith.science/api/pith-number/655HUOMXKHCVQVJFVNEQHTDWXL/graph.json","events_json":"https://pith.science/api/pith-number/655HUOMXKHCVQVJFVNEQHTDWXL/events.json","paper":"https://pith.science/paper/655HUOMX"},"agent_actions":{"view_html":"https://pith.science/pith/655HUOMXKHCVQVJFVNEQHTDWXL","download_json":"https://pith.science/pith/655HUOMXKHCVQVJFVNEQHTDWXL.json","view_paper":"https://pith.science/paper/655HUOMX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.02419&json=true","fetch_graph":"https://pith.science/api/pith-number/655HUOMXKHCVQVJFVNEQHTDWXL/graph.json","fetch_events":"https://pith.science/api/pith-number/655HUOMXKHCVQVJFVNEQHTDWXL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/655HUOMXKHCVQVJFVNEQHTDWXL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/655HUOMXKHCVQVJFVNEQHTDWXL/action/storage_attestation","attest_author":"https://pith.science/pith/655HUOMXKHCVQVJFVNEQHTDWXL/action/author_attestation","sign_citation":"https://pith.science/pith/655HUOMXKHCVQVJFVNEQHTDWXL/action/citation_signature","submit_replication":"https://pith.science/pith/655HUOMXKHCVQVJFVNEQHTDWXL/action/replication_record"}},"created_at":"2026-07-05T06:28:08.918694+00:00","updated_at":"2026-07-05T06:28:08.918694+00:00"}