{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:J3APOBG7JG4FOSCRLFTYANPSLA","short_pith_number":"pith:J3APOBG7","schema_version":"1.0","canonical_sha256":"4ec0f704df49b857485159678035f25802777ca4c860e3adb9ba00943dec4093","source":{"kind":"arxiv","id":"2311.00686","version":1},"attestation_state":"computed","paper":{"title":"Little Giants: Exploring the Potential of Small LLMs as Evaluation Metrics in Summarization in the Eval4NLP 2023 Shared Task","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alejandro Jaimes, Joel Tetreault, Neema Kotonya, Saran Krishnasamy","submitted_at":"2023-11-01T17:44:35Z","abstract_excerpt":"This paper describes and analyzes our participation in the 2023 Eval4NLP shared task, which focuses on assessing the effectiveness of prompt-based techniques to empower Large Language Models to handle the task of quality estimation, particularly in the context of evaluating machine translations and summaries. We conducted systematic experiments with various prompting techniques, including standard prompting, prompts informed by annotator instructions, and innovative chain-of-thought prompting. In addition, we integrated these approaches with zero-shot and one-shot learning methods to maximize "},"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":"2311.00686","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-01T17:44:35Z","cross_cats_sorted":[],"title_canon_sha256":"5d08f861b1ee938f807371fc2b55324b93fd885c79a6e79320bf4bbd8dc6d742","abstract_canon_sha256":"0fe2f7efcd0cc95dbaadca873f69a776d20c84e17091e591c86424947536bb27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:01.698482Z","signature_b64":"FdLjsp1fVuF9OrQPQ3ifOLdGY+lHMYJClo4iIXGg80Q0IMEBVt0E/lekb7AwkcCkF8Wigog4zicixX/6CLZ4AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ec0f704df49b857485159678035f25802777ca4c860e3adb9ba00943dec4093","last_reissued_at":"2026-07-05T07:08:01.697995Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:01.697995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Little Giants: Exploring the Potential of Small LLMs as Evaluation Metrics in Summarization in the Eval4NLP 2023 Shared Task","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alejandro Jaimes, Joel Tetreault, Neema Kotonya, Saran Krishnasamy","submitted_at":"2023-11-01T17:44:35Z","abstract_excerpt":"This paper describes and analyzes our participation in the 2023 Eval4NLP shared task, which focuses on assessing the effectiveness of prompt-based techniques to empower Large Language Models to handle the task of quality estimation, particularly in the context of evaluating machine translations and summaries. We conducted systematic experiments with various prompting techniques, including standard prompting, prompts informed by annotator instructions, and innovative chain-of-thought prompting. In addition, we integrated these approaches with zero-shot and one-shot learning methods to maximize "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00686","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/2311.00686/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":"2311.00686","created_at":"2026-07-05T07:08:01.698051+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.00686v1","created_at":"2026-07-05T07:08:01.698051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00686","created_at":"2026-07-05T07:08:01.698051+00:00"},{"alias_kind":"pith_short_12","alias_value":"J3APOBG7JG4F","created_at":"2026-07-05T07:08:01.698051+00:00"},{"alias_kind":"pith_short_16","alias_value":"J3APOBG7JG4FOSCR","created_at":"2026-07-05T07:08:01.698051+00:00"},{"alias_kind":"pith_short_8","alias_value":"J3APOBG7","created_at":"2026-07-05T07:08:01.698051+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.23213","citing_title":"Scoring, Reasoning, and Selecting the Best! Ensembling Large Language Models via a Peer-Review Process","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05579","citing_title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","ref_index":117,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J3APOBG7JG4FOSCRLFTYANPSLA","json":"https://pith.science/pith/J3APOBG7JG4FOSCRLFTYANPSLA.json","graph_json":"https://pith.science/api/pith-number/J3APOBG7JG4FOSCRLFTYANPSLA/graph.json","events_json":"https://pith.science/api/pith-number/J3APOBG7JG4FOSCRLFTYANPSLA/events.json","paper":"https://pith.science/paper/J3APOBG7"},"agent_actions":{"view_html":"https://pith.science/pith/J3APOBG7JG4FOSCRLFTYANPSLA","download_json":"https://pith.science/pith/J3APOBG7JG4FOSCRLFTYANPSLA.json","view_paper":"https://pith.science/paper/J3APOBG7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.00686&json=true","fetch_graph":"https://pith.science/api/pith-number/J3APOBG7JG4FOSCRLFTYANPSLA/graph.json","fetch_events":"https://pith.science/api/pith-number/J3APOBG7JG4FOSCRLFTYANPSLA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J3APOBG7JG4FOSCRLFTYANPSLA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J3APOBG7JG4FOSCRLFTYANPSLA/action/storage_attestation","attest_author":"https://pith.science/pith/J3APOBG7JG4FOSCRLFTYANPSLA/action/author_attestation","sign_citation":"https://pith.science/pith/J3APOBG7JG4FOSCRLFTYANPSLA/action/citation_signature","submit_replication":"https://pith.science/pith/J3APOBG7JG4FOSCRLFTYANPSLA/action/replication_record"}},"created_at":"2026-07-05T07:08:01.698051+00:00","updated_at":"2026-07-05T07:08:01.698051+00:00"}