{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NHX6IBFWUNH2MN6L2PMDDMXX2B","short_pith_number":"pith:NHX6IBFW","schema_version":"1.0","canonical_sha256":"69efe404b6a34fa637cbd3d831b2f7d048d4b7668c30c525b3afb621e3d778db","source":{"kind":"arxiv","id":"2210.00185","version":2},"attestation_state":"computed","paper":{"title":"Zemi: Learning Zero-Shot Semi-Parametric Language Models from Multiple Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dian Yu, Dong Yu, Heng Ji, Jianshu Chen, Xiaoman Pan, Zhenhailong Wang","submitted_at":"2022-10-01T04:08:50Z","abstract_excerpt":"Although large language models have achieved impressive zero-shot ability, the huge model size generally incurs high cost. Recently, semi-parametric language models, which augment a smaller language model with an external retriever, have demonstrated promising language modeling capabilities. However, it remains unclear whether such semi-parametric language models can perform competitively well as their fully-parametric counterparts on zero-shot generalization to downstream tasks. In this work, we introduce $\\text{Zemi}$, a zero-shot semi-parametric language model. To our best knowledge, this i"},"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":"2210.00185","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-01T04:08:50Z","cross_cats_sorted":[],"title_canon_sha256":"7dfd1bab251eb0f28fba2c5ba78c53099d5dca26e8c10f77ad609b3a7eb653d2","abstract_canon_sha256":"da672d57efeb37bc844bb3027f82b5dfe61e918192ae2671a62a3d866d0678f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:37.044736Z","signature_b64":"279b+apRXUEJxugXF29S4bWM/Bdzm0+ytgZyWC2rTrXW77wTVP2hTOqRjucNLTZnohPcpdwXKFd0RsOzP43HCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69efe404b6a34fa637cbd3d831b2f7d048d4b7668c30c525b3afb621e3d778db","last_reissued_at":"2026-07-05T06:12:37.044217Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:37.044217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zemi: Learning Zero-Shot Semi-Parametric Language Models from Multiple Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dian Yu, Dong Yu, Heng Ji, Jianshu Chen, Xiaoman Pan, Zhenhailong Wang","submitted_at":"2022-10-01T04:08:50Z","abstract_excerpt":"Although large language models have achieved impressive zero-shot ability, the huge model size generally incurs high cost. Recently, semi-parametric language models, which augment a smaller language model with an external retriever, have demonstrated promising language modeling capabilities. However, it remains unclear whether such semi-parametric language models can perform competitively well as their fully-parametric counterparts on zero-shot generalization to downstream tasks. In this work, we introduce $\\text{Zemi}$, a zero-shot semi-parametric language model. To our best knowledge, this i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.00185","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/2210.00185/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":"2210.00185","created_at":"2026-07-05T06:12:37.044280+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.00185v2","created_at":"2026-07-05T06:12:37.044280+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.00185","created_at":"2026-07-05T06:12:37.044280+00:00"},{"alias_kind":"pith_short_12","alias_value":"NHX6IBFWUNH2","created_at":"2026-07-05T06:12:37.044280+00:00"},{"alias_kind":"pith_short_16","alias_value":"NHX6IBFWUNH2MN6L","created_at":"2026-07-05T06:12:37.044280+00:00"},{"alias_kind":"pith_short_8","alias_value":"NHX6IBFW","created_at":"2026-07-05T06:12:37.044280+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2312.10997","citing_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2310.11511","citing_title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","ref_index":111,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NHX6IBFWUNH2MN6L2PMDDMXX2B","json":"https://pith.science/pith/NHX6IBFWUNH2MN6L2PMDDMXX2B.json","graph_json":"https://pith.science/api/pith-number/NHX6IBFWUNH2MN6L2PMDDMXX2B/graph.json","events_json":"https://pith.science/api/pith-number/NHX6IBFWUNH2MN6L2PMDDMXX2B/events.json","paper":"https://pith.science/paper/NHX6IBFW"},"agent_actions":{"view_html":"https://pith.science/pith/NHX6IBFWUNH2MN6L2PMDDMXX2B","download_json":"https://pith.science/pith/NHX6IBFWUNH2MN6L2PMDDMXX2B.json","view_paper":"https://pith.science/paper/NHX6IBFW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.00185&json=true","fetch_graph":"https://pith.science/api/pith-number/NHX6IBFWUNH2MN6L2PMDDMXX2B/graph.json","fetch_events":"https://pith.science/api/pith-number/NHX6IBFWUNH2MN6L2PMDDMXX2B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NHX6IBFWUNH2MN6L2PMDDMXX2B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NHX6IBFWUNH2MN6L2PMDDMXX2B/action/storage_attestation","attest_author":"https://pith.science/pith/NHX6IBFWUNH2MN6L2PMDDMXX2B/action/author_attestation","sign_citation":"https://pith.science/pith/NHX6IBFWUNH2MN6L2PMDDMXX2B/action/citation_signature","submit_replication":"https://pith.science/pith/NHX6IBFWUNH2MN6L2PMDDMXX2B/action/replication_record"}},"created_at":"2026-07-05T06:12:37.044280+00:00","updated_at":"2026-07-05T06:12:37.044280+00:00"}