{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Q3BPBDFKFBGRBLRDP7BJVFMIGF","short_pith_number":"pith:Q3BPBDFK","schema_version":"1.0","canonical_sha256":"86c2f08caa284d10ae237fc29a9588317aa0f8b6b46a657288abd41b812f9136","source":{"kind":"arxiv","id":"2607.04081","version":1},"attestation_state":"computed","paper":{"title":"A Unified Framework for In-Context Learning with Causal and Masked Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chenrui Liu, Chuanlong Xie, Falong Tan, Lixing Zhu, Yicheng Zeng","submitted_at":"2026-07-05T02:23:18Z","abstract_excerpt":"In-context learning (ICL) has emerged as a central capability of pretrained language models, yet its theoretical analysis has focused primarily on causal language models trained by left-to-right autoregressive prediction, such as GPT-style models. Masked language models instead recover masked tokens from bidirectional context, and their role in ICL remains less understood. We develop a statistical learning framework that represents the context examples by their empirical measure and models prediction as a function of the context and the query. This formulation places autoregressive and masked "},"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":"2607.04081","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-05T02:23:18Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"87b4b296f853361befae980090ecf3e0ed4dcde4f37b36ffc8800cac2ad8aa0b","abstract_canon_sha256":"8204162a4936bf9d1df0756aa7151fde3a34f71b48fb9d3ef3c23110d0b1a810"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:18:56.520761Z","signature_b64":"jtczn3QgAaKz7UZMVVi2PtfwqJnz4A7Nm13cS047uNRw+n8nG5bluKyjsNpliY1DPAT0J47lbPtv3q8dZ13zCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86c2f08caa284d10ae237fc29a9588317aa0f8b6b46a657288abd41b812f9136","last_reissued_at":"2026-07-07T02:18:56.519956Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:18:56.519956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Unified Framework for In-Context Learning with Causal and Masked Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chenrui Liu, Chuanlong Xie, Falong Tan, Lixing Zhu, Yicheng Zeng","submitted_at":"2026-07-05T02:23:18Z","abstract_excerpt":"In-context learning (ICL) has emerged as a central capability of pretrained language models, yet its theoretical analysis has focused primarily on causal language models trained by left-to-right autoregressive prediction, such as GPT-style models. Masked language models instead recover masked tokens from bidirectional context, and their role in ICL remains less understood. We develop a statistical learning framework that represents the context examples by their empirical measure and models prediction as a function of the context and the query. This formulation places autoregressive and masked "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04081","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/2607.04081/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":"2607.04081","created_at":"2026-07-07T02:18:56.520095+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.04081v1","created_at":"2026-07-07T02:18:56.520095+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04081","created_at":"2026-07-07T02:18:56.520095+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q3BPBDFKFBGR","created_at":"2026-07-07T02:18:56.520095+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q3BPBDFKFBGRBLRD","created_at":"2026-07-07T02:18:56.520095+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q3BPBDFK","created_at":"2026-07-07T02:18:56.520095+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q3BPBDFKFBGRBLRDP7BJVFMIGF","json":"https://pith.science/pith/Q3BPBDFKFBGRBLRDP7BJVFMIGF.json","graph_json":"https://pith.science/api/pith-number/Q3BPBDFKFBGRBLRDP7BJVFMIGF/graph.json","events_json":"https://pith.science/api/pith-number/Q3BPBDFKFBGRBLRDP7BJVFMIGF/events.json","paper":"https://pith.science/paper/Q3BPBDFK"},"agent_actions":{"view_html":"https://pith.science/pith/Q3BPBDFKFBGRBLRDP7BJVFMIGF","download_json":"https://pith.science/pith/Q3BPBDFKFBGRBLRDP7BJVFMIGF.json","view_paper":"https://pith.science/paper/Q3BPBDFK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.04081&json=true","fetch_graph":"https://pith.science/api/pith-number/Q3BPBDFKFBGRBLRDP7BJVFMIGF/graph.json","fetch_events":"https://pith.science/api/pith-number/Q3BPBDFKFBGRBLRDP7BJVFMIGF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q3BPBDFKFBGRBLRDP7BJVFMIGF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q3BPBDFKFBGRBLRDP7BJVFMIGF/action/storage_attestation","attest_author":"https://pith.science/pith/Q3BPBDFKFBGRBLRDP7BJVFMIGF/action/author_attestation","sign_citation":"https://pith.science/pith/Q3BPBDFKFBGRBLRDP7BJVFMIGF/action/citation_signature","submit_replication":"https://pith.science/pith/Q3BPBDFKFBGRBLRDP7BJVFMIGF/action/replication_record"}},"created_at":"2026-07-07T02:18:56.520095+00:00","updated_at":"2026-07-07T02:18:56.520095+00:00"}