{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YCROZPIJWJGB2SABPTZAMY5B62","short_pith_number":"pith:YCROZPIJ","schema_version":"1.0","canonical_sha256":"c0a2ecbd09b24c1d48017cf20663a1f6b6c90ebbcf14dd9daf9b49715360d982","source":{"kind":"arxiv","id":"2508.09263","version":1},"attestation_state":"computed","paper":{"title":"LLM Empowered Prototype Learning for Zero and Few-Shot Tasks on Tabular Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dandan Guo, Dongsheng Wang, Hangting Ye, He Zhao, Peng Wang, Yi Chang","submitted_at":"2025-08-12T18:07:11Z","abstract_excerpt":"Recent breakthroughs in large language models (LLMs) have opened the door to in-depth investigation of their potential in tabular data modeling. However, effectively utilizing advanced LLMs in few-shot and even zero-shot scenarios is still challenging. To this end, we propose a novel LLM-based prototype estimation framework for tabular learning. Our key idea is to query the LLM to generate feature values based example-free prompt, which solely relies on task and feature descriptions. With the feature values generated by LLM, we can build a zero-shot prototype in a training-free manner, which c"},"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":"2508.09263","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-12T18:07:11Z","cross_cats_sorted":[],"title_canon_sha256":"b69a7368edec0717f956f6cbc34a28e41139644941fb5d93622644dcaa87e321","abstract_canon_sha256":"dc5662e4a0c8f92ba2d8a89045376228188188affe72cda2c9467a1fd1f06e8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:11.505645Z","signature_b64":"oLpoT5pGQF6rO1asBm5th7FNSJOBJxJNB158u9CeHKlTHZBrYgEjrAcQuI3lIWjDIFGXvbwfOro10s4Esxl0Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0a2ecbd09b24c1d48017cf20663a1f6b6c90ebbcf14dd9daf9b49715360d982","last_reissued_at":"2026-07-05T11:53:11.505139Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:11.505139Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM Empowered Prototype Learning for Zero and Few-Shot Tasks on Tabular Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dandan Guo, Dongsheng Wang, Hangting Ye, He Zhao, Peng Wang, Yi Chang","submitted_at":"2025-08-12T18:07:11Z","abstract_excerpt":"Recent breakthroughs in large language models (LLMs) have opened the door to in-depth investigation of their potential in tabular data modeling. However, effectively utilizing advanced LLMs in few-shot and even zero-shot scenarios is still challenging. To this end, we propose a novel LLM-based prototype estimation framework for tabular learning. Our key idea is to query the LLM to generate feature values based example-free prompt, which solely relies on task and feature descriptions. With the feature values generated by LLM, we can build a zero-shot prototype in a training-free manner, which c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09263","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/2508.09263/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":"2508.09263","created_at":"2026-07-05T11:53:11.505201+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.09263v1","created_at":"2026-07-05T11:53:11.505201+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09263","created_at":"2026-07-05T11:53:11.505201+00:00"},{"alias_kind":"pith_short_12","alias_value":"YCROZPIJWJGB","created_at":"2026-07-05T11:53:11.505201+00:00"},{"alias_kind":"pith_short_16","alias_value":"YCROZPIJWJGB2SAB","created_at":"2026-07-05T11:53:11.505201+00:00"},{"alias_kind":"pith_short_8","alias_value":"YCROZPIJ","created_at":"2026-07-05T11:53:11.505201+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/YCROZPIJWJGB2SABPTZAMY5B62","json":"https://pith.science/pith/YCROZPIJWJGB2SABPTZAMY5B62.json","graph_json":"https://pith.science/api/pith-number/YCROZPIJWJGB2SABPTZAMY5B62/graph.json","events_json":"https://pith.science/api/pith-number/YCROZPIJWJGB2SABPTZAMY5B62/events.json","paper":"https://pith.science/paper/YCROZPIJ"},"agent_actions":{"view_html":"https://pith.science/pith/YCROZPIJWJGB2SABPTZAMY5B62","download_json":"https://pith.science/pith/YCROZPIJWJGB2SABPTZAMY5B62.json","view_paper":"https://pith.science/paper/YCROZPIJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.09263&json=true","fetch_graph":"https://pith.science/api/pith-number/YCROZPIJWJGB2SABPTZAMY5B62/graph.json","fetch_events":"https://pith.science/api/pith-number/YCROZPIJWJGB2SABPTZAMY5B62/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YCROZPIJWJGB2SABPTZAMY5B62/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YCROZPIJWJGB2SABPTZAMY5B62/action/storage_attestation","attest_author":"https://pith.science/pith/YCROZPIJWJGB2SABPTZAMY5B62/action/author_attestation","sign_citation":"https://pith.science/pith/YCROZPIJWJGB2SABPTZAMY5B62/action/citation_signature","submit_replication":"https://pith.science/pith/YCROZPIJWJGB2SABPTZAMY5B62/action/replication_record"}},"created_at":"2026-07-05T11:53:11.505201+00:00","updated_at":"2026-07-05T11:53:11.505201+00:00"}