{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DFW6JJNO5C3TQIRNRGQ5W7ROV6","short_pith_number":"pith:DFW6JJNO","canonical_record":{"source":{"id":"2402.14951","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-02-22T20:26:08Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"9b1d77a43dea4c528c09f85bb1266eb9b35f7a6540f2585cc0f6615fa17206f8","abstract_canon_sha256":"8861172f4211f2af8a4cbec1ccc5c1c71f881147dc9a5a910bb27a9b2b3d67ed"},"schema_version":"1.0"},"canonical_sha256":"196de4a5aee8b738222d89a1db7e2eafbe4a0aeb065118bc7947f994776043ff","source":{"kind":"arxiv","id":"2402.14951","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14951","created_at":"2026-07-05T07:48:20Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14951v1","created_at":"2026-07-05T07:48:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14951","created_at":"2026-07-05T07:48:20Z"},{"alias_kind":"pith_short_12","alias_value":"DFW6JJNO5C3T","created_at":"2026-07-05T07:48:20Z"},{"alias_kind":"pith_short_16","alias_value":"DFW6JJNO5C3TQIRN","created_at":"2026-07-05T07:48:20Z"},{"alias_kind":"pith_short_8","alias_value":"DFW6JJNO","created_at":"2026-07-05T07:48:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DFW6JJNO5C3TQIRNRGQ5W7ROV6","target":"record","payload":{"canonical_record":{"source":{"id":"2402.14951","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-02-22T20:26:08Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"9b1d77a43dea4c528c09f85bb1266eb9b35f7a6540f2585cc0f6615fa17206f8","abstract_canon_sha256":"8861172f4211f2af8a4cbec1ccc5c1c71f881147dc9a5a910bb27a9b2b3d67ed"},"schema_version":"1.0"},"canonical_sha256":"196de4a5aee8b738222d89a1db7e2eafbe4a0aeb065118bc7947f994776043ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:20.187521Z","signature_b64":"1ZqHERK37kzxigbTZk42rBZ4bYnfXWojjwnpx7lVMoiYPIJCYJs5k1lICNq1HjcL63AD+67Onrk/1N3NeJ8IAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"196de4a5aee8b738222d89a1db7e2eafbe4a0aeb065118bc7947f994776043ff","last_reissued_at":"2026-07-05T07:48:20.187015Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:20.187015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.14951","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:48:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UWdER2X6MamuvFQz52vRsypmc2HB6OiR4izXRSTBSKoPTbZkFV1dsX/Iq4ps1l0X31k8e7DpcnGxsCgYntp9Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:29:17.829946Z"},"content_sha256":"155df0d1234fa034960ea380fc26e22869f06db3682e6c5d2ec3d21a661ddc21","schema_version":"1.0","event_id":"sha256:155df0d1234fa034960ea380fc26e22869f06db3682e6c5d2ec3d21a661ddc21"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DFW6JJNO5C3TQIRNRGQ5W7ROV6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"stat.ML","authors_text":"Jingfeng Wu, Peter L. Bartlett, Ruiqi Zhang","submitted_at":"2024-02-22T20:26:08Z","abstract_excerpt":"We study the \\emph{in-context learning} (ICL) ability of a \\emph{Linear Transformer Block} (LTB) that combines a linear attention component and a linear multi-layer perceptron (MLP) component. For ICL of linear regression with a Gaussian prior and a \\emph{non-zero mean}, we show that LTB can achieve nearly Bayes optimal ICL risk. In contrast, using only linear attention must incur an irreducible additive approximation error. Furthermore, we establish a correspondence between LTB and one-step gradient descent estimators with learnable initialization ($\\mathsf{GD}\\text{-}\\mathbf{\\beta}$), in the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14951","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/2402.14951/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:48:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6ew9fQNlh2x2HtUeLj8g97fkW2lmxVwP3l4jVpwAraqHZGwgDSTsC6kEDag0kC134TsA7BQJhMNTkwyYEF87AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:29:17.830495Z"},"content_sha256":"bd30326f5e2cc6a39cecfdffed05e6113b1a8d912e96217a872dfc0313f741b2","schema_version":"1.0","event_id":"sha256:bd30326f5e2cc6a39cecfdffed05e6113b1a8d912e96217a872dfc0313f741b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DFW6JJNO5C3TQIRNRGQ5W7ROV6/bundle.json","state_url":"https://pith.science/pith/DFW6JJNO5C3TQIRNRGQ5W7ROV6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DFW6JJNO5C3TQIRNRGQ5W7ROV6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T11:29:17Z","links":{"resolver":"https://pith.science/pith/DFW6JJNO5C3TQIRNRGQ5W7ROV6","bundle":"https://pith.science/pith/DFW6JJNO5C3TQIRNRGQ5W7ROV6/bundle.json","state":"https://pith.science/pith/DFW6JJNO5C3TQIRNRGQ5W7ROV6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DFW6JJNO5C3TQIRNRGQ5W7ROV6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DFW6JJNO5C3TQIRNRGQ5W7ROV6","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":"8861172f4211f2af8a4cbec1ccc5c1c71f881147dc9a5a910bb27a9b2b3d67ed","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-02-22T20:26:08Z","title_canon_sha256":"9b1d77a43dea4c528c09f85bb1266eb9b35f7a6540f2585cc0f6615fa17206f8"},"schema_version":"1.0","source":{"id":"2402.14951","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14951","created_at":"2026-07-05T07:48:20Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14951v1","created_at":"2026-07-05T07:48:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14951","created_at":"2026-07-05T07:48:20Z"},{"alias_kind":"pith_short_12","alias_value":"DFW6JJNO5C3T","created_at":"2026-07-05T07:48:20Z"},{"alias_kind":"pith_short_16","alias_value":"DFW6JJNO5C3TQIRN","created_at":"2026-07-05T07:48:20Z"},{"alias_kind":"pith_short_8","alias_value":"DFW6JJNO","created_at":"2026-07-05T07:48:20Z"}],"graph_snapshots":[{"event_id":"sha256:bd30326f5e2cc6a39cecfdffed05e6113b1a8d912e96217a872dfc0313f741b2","target":"graph","created_at":"2026-07-05T07:48:20Z","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/2402.14951/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the \\emph{in-context learning} (ICL) ability of a \\emph{Linear Transformer Block} (LTB) that combines a linear attention component and a linear multi-layer perceptron (MLP) component. For ICL of linear regression with a Gaussian prior and a \\emph{non-zero mean}, we show that LTB can achieve nearly Bayes optimal ICL risk. In contrast, using only linear attention must incur an irreducible additive approximation error. Furthermore, we establish a correspondence between LTB and one-step gradient descent estimators with learnable initialization ($\\mathsf{GD}\\text{-}\\mathbf{\\beta}$), in the","authors_text":"Jingfeng Wu, Peter L. Bartlett, Ruiqi Zhang","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-02-22T20:26:08Z","title":"In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14951","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":"sha256:155df0d1234fa034960ea380fc26e22869f06db3682e6c5d2ec3d21a661ddc21","target":"record","created_at":"2026-07-05T07:48:20Z","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":"8861172f4211f2af8a4cbec1ccc5c1c71f881147dc9a5a910bb27a9b2b3d67ed","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-02-22T20:26:08Z","title_canon_sha256":"9b1d77a43dea4c528c09f85bb1266eb9b35f7a6540f2585cc0f6615fa17206f8"},"schema_version":"1.0","source":{"id":"2402.14951","kind":"arxiv","version":1}},"canonical_sha256":"196de4a5aee8b738222d89a1db7e2eafbe4a0aeb065118bc7947f994776043ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"196de4a5aee8b738222d89a1db7e2eafbe4a0aeb065118bc7947f994776043ff","first_computed_at":"2026-07-05T07:48:20.187015Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:48:20.187015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1ZqHERK37kzxigbTZk42rBZ4bYnfXWojjwnpx7lVMoiYPIJCYJs5k1lICNq1HjcL63AD+67Onrk/1N3NeJ8IAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:48:20.187521Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.14951","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:155df0d1234fa034960ea380fc26e22869f06db3682e6c5d2ec3d21a661ddc21","sha256:bd30326f5e2cc6a39cecfdffed05e6113b1a8d912e96217a872dfc0313f741b2"],"state_sha256":"c6304bdb8a6f07c05442adbcd74eff09293143f29b3490dd471e789743a7cb2a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zC0sZEL9JMNTnIASMSG+jQiC/XH7amwUkPNoE7lZXffoCXEnAUi959+K2voyU/n4w6YYluDUivG35ICexd0WAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T11:29:17.834126Z","bundle_sha256":"8cecb0e292efa91f1cd443834090e87321ea4e8424e0827c1d4085ff2a413774"}}