{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2FZXJF3I5P3ZEQB3CLWAFRLFV7","short_pith_number":"pith:2FZXJF3I","schema_version":"1.0","canonical_sha256":"d173749768ebf792403b12ec02c565afd7d5acf9d25bb244c1da1acc2bd3c529","source":{"kind":"arxiv","id":"2406.11243","version":1},"attestation_state":"computed","paper":{"title":"FamiCom: Further Demystifying Prompts for Language Models with Task-Agnostic Performance Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bangzheng Li, Ben Zhou, Dan Roth, Fei Wang, Muhao Chen, Xingyu Fu","submitted_at":"2024-06-17T06:14:55Z","abstract_excerpt":"Language models have shown impressive in-context-learning capabilities, which allow them to benefit from input prompts and perform better on downstream end tasks. Existing works investigate the mechanisms behind this observation, and propose label-agnostic prompt metrics that can better estimate end-task performances. One popular approach is using perplexity as a way to measure models' familiarity with the prompt. While showing consistent improvements on in-domain tasks, we found that familiarity metrics such as perplexity cannot accurately estimate performance in complicated situations such a"},"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":"2406.11243","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-17T06:14:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6356e00d0a5f4fee333d3eab2bf656e3c12268f09ceb8eeb908d47395dd9e4be","abstract_canon_sha256":"5908eaa42ddfc50d7959bf9e5fea1e60decdaed6576de3e62fac761bd2565153"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:50.723852Z","signature_b64":"H1XJKd2BmPIY7MQVaVHAnAWJJnMLEWQN+yigkyvj5KIubSyliiZR6L92gVlWcAsQQ1ywa+bIIpyROz6YSgs9Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d173749768ebf792403b12ec02c565afd7d5acf9d25bb244c1da1acc2bd3c529","last_reissued_at":"2026-07-05T08:32:50.723291Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:50.723291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FamiCom: Further Demystifying Prompts for Language Models with Task-Agnostic Performance Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bangzheng Li, Ben Zhou, Dan Roth, Fei Wang, Muhao Chen, Xingyu Fu","submitted_at":"2024-06-17T06:14:55Z","abstract_excerpt":"Language models have shown impressive in-context-learning capabilities, which allow them to benefit from input prompts and perform better on downstream end tasks. Existing works investigate the mechanisms behind this observation, and propose label-agnostic prompt metrics that can better estimate end-task performances. One popular approach is using perplexity as a way to measure models' familiarity with the prompt. While showing consistent improvements on in-domain tasks, we found that familiarity metrics such as perplexity cannot accurately estimate performance in complicated situations such a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11243","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/2406.11243/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":"2406.11243","created_at":"2026-07-05T08:32:50.723360+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.11243v1","created_at":"2026-07-05T08:32:50.723360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11243","created_at":"2026-07-05T08:32:50.723360+00:00"},{"alias_kind":"pith_short_12","alias_value":"2FZXJF3I5P3Z","created_at":"2026-07-05T08:32:50.723360+00:00"},{"alias_kind":"pith_short_16","alias_value":"2FZXJF3I5P3ZEQB3","created_at":"2026-07-05T08:32:50.723360+00:00"},{"alias_kind":"pith_short_8","alias_value":"2FZXJF3I","created_at":"2026-07-05T08:32:50.723360+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.00996","citing_title":"Self-supervised Analogical Learning using Language Models","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2FZXJF3I5P3ZEQB3CLWAFRLFV7","json":"https://pith.science/pith/2FZXJF3I5P3ZEQB3CLWAFRLFV7.json","graph_json":"https://pith.science/api/pith-number/2FZXJF3I5P3ZEQB3CLWAFRLFV7/graph.json","events_json":"https://pith.science/api/pith-number/2FZXJF3I5P3ZEQB3CLWAFRLFV7/events.json","paper":"https://pith.science/paper/2FZXJF3I"},"agent_actions":{"view_html":"https://pith.science/pith/2FZXJF3I5P3ZEQB3CLWAFRLFV7","download_json":"https://pith.science/pith/2FZXJF3I5P3ZEQB3CLWAFRLFV7.json","view_paper":"https://pith.science/paper/2FZXJF3I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.11243&json=true","fetch_graph":"https://pith.science/api/pith-number/2FZXJF3I5P3ZEQB3CLWAFRLFV7/graph.json","fetch_events":"https://pith.science/api/pith-number/2FZXJF3I5P3ZEQB3CLWAFRLFV7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2FZXJF3I5P3ZEQB3CLWAFRLFV7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2FZXJF3I5P3ZEQB3CLWAFRLFV7/action/storage_attestation","attest_author":"https://pith.science/pith/2FZXJF3I5P3ZEQB3CLWAFRLFV7/action/author_attestation","sign_citation":"https://pith.science/pith/2FZXJF3I5P3ZEQB3CLWAFRLFV7/action/citation_signature","submit_replication":"https://pith.science/pith/2FZXJF3I5P3ZEQB3CLWAFRLFV7/action/replication_record"}},"created_at":"2026-07-05T08:32:50.723360+00:00","updated_at":"2026-07-05T08:32:50.723360+00:00"}