{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5LWKC6JDLQLM5YNPHRX4CJYCW4","short_pith_number":"pith:5LWKC6JD","schema_version":"1.0","canonical_sha256":"eaeca179235c16cee1af3c6fc12702b73bb99e9b516a14dfda4b2d67c01571fb","source":{"kind":"arxiv","id":"2304.13276","version":1},"attestation_state":"computed","paper":{"title":"The Closeness of In-Context Learning and Weight Shifting for Softmax Regression","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Shuai Li, Tianyi Zhou, Tong Yu, Yu Xia, Zhao Song","submitted_at":"2023-04-26T04:33:41Z","abstract_excerpt":"Large language models (LLMs) are known for their exceptional performance in natural language processing, making them highly effective in many human life-related or even job-related tasks. The attention mechanism in the Transformer architecture is a critical component of LLMs, as it allows the model to selectively focus on specific input parts. The softmax unit, which is a key part of the attention mechanism, normalizes the attention scores. Hence, the performance of LLMs in various NLP tasks depends significantly on the crucial role played by the attention mechanism with the softmax unit.\n  In"},"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":"2304.13276","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-26T04:33:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ac7f31a647314c9a840bb1cab4306648c82119a3b8af110b13c9c286e7bbaba4","abstract_canon_sha256":"c213d5524915103732c30aa3f3c88e604edd0727e84e6fb1e423fcc79cf6d44c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:04:42.202444Z","signature_b64":"5fuSMGydoONZAz8VcYdScchTHEkPtj4QN0a7nV6QTyXnorfQ99Ovw38djeY9jWzfjkVbIHYv+tLf3hqebL2RBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eaeca179235c16cee1af3c6fc12702b73bb99e9b516a14dfda4b2d67c01571fb","last_reissued_at":"2026-07-05T06:04:42.202044Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:04:42.202044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Closeness of In-Context Learning and Weight Shifting for Softmax Regression","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Shuai Li, Tianyi Zhou, Tong Yu, Yu Xia, Zhao Song","submitted_at":"2023-04-26T04:33:41Z","abstract_excerpt":"Large language models (LLMs) are known for their exceptional performance in natural language processing, making them highly effective in many human life-related or even job-related tasks. The attention mechanism in the Transformer architecture is a critical component of LLMs, as it allows the model to selectively focus on specific input parts. The softmax unit, which is a key part of the attention mechanism, normalizes the attention scores. Hence, the performance of LLMs in various NLP tasks depends significantly on the crucial role played by the attention mechanism with the softmax unit.\n  In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.13276","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/2304.13276/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":"2304.13276","created_at":"2026-07-05T06:04:42.202105+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.13276v1","created_at":"2026-07-05T06:04:42.202105+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.13276","created_at":"2026-07-05T06:04:42.202105+00:00"},{"alias_kind":"pith_short_12","alias_value":"5LWKC6JDLQLM","created_at":"2026-07-05T06:04:42.202105+00:00"},{"alias_kind":"pith_short_16","alias_value":"5LWKC6JDLQLM5YNP","created_at":"2026-07-05T06:04:42.202105+00:00"},{"alias_kind":"pith_short_8","alias_value":"5LWKC6JD","created_at":"2026-07-05T06:04:42.202105+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.01321","citing_title":"ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5LWKC6JDLQLM5YNPHRX4CJYCW4","json":"https://pith.science/pith/5LWKC6JDLQLM5YNPHRX4CJYCW4.json","graph_json":"https://pith.science/api/pith-number/5LWKC6JDLQLM5YNPHRX4CJYCW4/graph.json","events_json":"https://pith.science/api/pith-number/5LWKC6JDLQLM5YNPHRX4CJYCW4/events.json","paper":"https://pith.science/paper/5LWKC6JD"},"agent_actions":{"view_html":"https://pith.science/pith/5LWKC6JDLQLM5YNPHRX4CJYCW4","download_json":"https://pith.science/pith/5LWKC6JDLQLM5YNPHRX4CJYCW4.json","view_paper":"https://pith.science/paper/5LWKC6JD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.13276&json=true","fetch_graph":"https://pith.science/api/pith-number/5LWKC6JDLQLM5YNPHRX4CJYCW4/graph.json","fetch_events":"https://pith.science/api/pith-number/5LWKC6JDLQLM5YNPHRX4CJYCW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5LWKC6JDLQLM5YNPHRX4CJYCW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5LWKC6JDLQLM5YNPHRX4CJYCW4/action/storage_attestation","attest_author":"https://pith.science/pith/5LWKC6JDLQLM5YNPHRX4CJYCW4/action/author_attestation","sign_citation":"https://pith.science/pith/5LWKC6JDLQLM5YNPHRX4CJYCW4/action/citation_signature","submit_replication":"https://pith.science/pith/5LWKC6JDLQLM5YNPHRX4CJYCW4/action/replication_record"}},"created_at":"2026-07-05T06:04:42.202105+00:00","updated_at":"2026-07-05T06:04:42.202105+00:00"}