{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GKGPZKCPFAYTYVHC4JUB4VVIQD","short_pith_number":"pith:GKGPZKCP","schema_version":"1.0","canonical_sha256":"328cfca84f28313c54e2e2681e56a880e91c46b2d6b4e439c72e5d82c51980ed","source":{"kind":"arxiv","id":"2404.11225","version":2},"attestation_state":"computed","paper":{"title":"In-Context Learning State Vector with Inner and Momentum Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Baotian Hu, Dongfang Li, Min Zhang, Xinshuo Hu, Zetian Sun, Zhenyu Liu","submitted_at":"2024-04-17T10:19:15Z","abstract_excerpt":"Large Language Models (LLMs) have exhibited an impressive ability to perform In-Context Learning (ICL) from only a few examples. Recent works have indicated that the functions learned by ICL can be represented through compressed vectors derived from the transformer. However, the working mechanisms and optimization of these vectors are yet to be thoroughly explored. In this paper, we address this gap by presenting a comprehensive analysis of these compressed vectors, drawing parallels to the parameters trained with gradient descent, and introduce the concept of state vector. Inspired by the wor"},"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":"2404.11225","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-17T10:19:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"be9375722460b7e9c6c2ce2212e3fe8e2ca9a82467ba393f4e5681c891b68481","abstract_canon_sha256":"e1d46838f85c79bf7d8f25fac0242c79f0390f79faf7cb029de6d593c186fbb3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:40:16.678918Z","signature_b64":"uugVaNpbNGdFI6IYPliXaHdd0x7IWp4Lv1T6d7nXLrgvTSfpj63Cs3wRM18YcbHIEmQT4NiGt34JBhrlqWqQAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"328cfca84f28313c54e2e2681e56a880e91c46b2d6b4e439c72e5d82c51980ed","last_reissued_at":"2026-07-05T08:40:16.678461Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:40:16.678461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In-Context Learning State Vector with Inner and Momentum Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Baotian Hu, Dongfang Li, Min Zhang, Xinshuo Hu, Zetian Sun, Zhenyu Liu","submitted_at":"2024-04-17T10:19:15Z","abstract_excerpt":"Large Language Models (LLMs) have exhibited an impressive ability to perform In-Context Learning (ICL) from only a few examples. Recent works have indicated that the functions learned by ICL can be represented through compressed vectors derived from the transformer. However, the working mechanisms and optimization of these vectors are yet to be thoroughly explored. In this paper, we address this gap by presenting a comprehensive analysis of these compressed vectors, drawing parallels to the parameters trained with gradient descent, and introduce the concept of state vector. Inspired by the wor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.11225","kind":"arxiv","version":2},"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/2404.11225/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":"2404.11225","created_at":"2026-07-05T08:40:16.678515+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.11225v2","created_at":"2026-07-05T08:40:16.678515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.11225","created_at":"2026-07-05T08:40:16.678515+00:00"},{"alias_kind":"pith_short_12","alias_value":"GKGPZKCPFAYT","created_at":"2026-07-05T08:40:16.678515+00:00"},{"alias_kind":"pith_short_16","alias_value":"GKGPZKCPFAYTYVHC","created_at":"2026-07-05T08:40:16.678515+00:00"},{"alias_kind":"pith_short_8","alias_value":"GKGPZKCP","created_at":"2026-07-05T08:40:16.678515+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.24164","citing_title":"Localizing Task Recognition and Task Learning in In-Context Learning via Attention Head Analysis","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GKGPZKCPFAYTYVHC4JUB4VVIQD","json":"https://pith.science/pith/GKGPZKCPFAYTYVHC4JUB4VVIQD.json","graph_json":"https://pith.science/api/pith-number/GKGPZKCPFAYTYVHC4JUB4VVIQD/graph.json","events_json":"https://pith.science/api/pith-number/GKGPZKCPFAYTYVHC4JUB4VVIQD/events.json","paper":"https://pith.science/paper/GKGPZKCP"},"agent_actions":{"view_html":"https://pith.science/pith/GKGPZKCPFAYTYVHC4JUB4VVIQD","download_json":"https://pith.science/pith/GKGPZKCPFAYTYVHC4JUB4VVIQD.json","view_paper":"https://pith.science/paper/GKGPZKCP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.11225&json=true","fetch_graph":"https://pith.science/api/pith-number/GKGPZKCPFAYTYVHC4JUB4VVIQD/graph.json","fetch_events":"https://pith.science/api/pith-number/GKGPZKCPFAYTYVHC4JUB4VVIQD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GKGPZKCPFAYTYVHC4JUB4VVIQD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GKGPZKCPFAYTYVHC4JUB4VVIQD/action/storage_attestation","attest_author":"https://pith.science/pith/GKGPZKCPFAYTYVHC4JUB4VVIQD/action/author_attestation","sign_citation":"https://pith.science/pith/GKGPZKCPFAYTYVHC4JUB4VVIQD/action/citation_signature","submit_replication":"https://pith.science/pith/GKGPZKCPFAYTYVHC4JUB4VVIQD/action/replication_record"}},"created_at":"2026-07-05T08:40:16.678515+00:00","updated_at":"2026-07-05T08:40:16.678515+00:00"}