{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2NJVF7TYO5LVSDDIBMB6FZSHYN","short_pith_number":"pith:2NJVF7TY","schema_version":"1.0","canonical_sha256":"d35352fe787757590c680b03e2e647c3692397e1437363ac9dfcdfcbc1fd5afe","source":{"kind":"arxiv","id":"2501.00062","version":2},"attestation_state":"computed","paper":{"title":"ELECTRA and GPT-4o: Cost-Effective Partners for Sentiment Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"James P. Beno","submitted_at":"2024-12-29T05:29:52Z","abstract_excerpt":"Bidirectional transformers excel at sentiment analysis, and Large Language Models (LLM) are effective zero-shot learners. Might they perform better as a team? This paper explores collaborative approaches between ELECTRA and GPT-4o for three-way sentiment classification. We fine-tuned (FT) four models (ELECTRA Base/Large, GPT-4o/4o-mini) using a mix of reviews from Stanford Sentiment Treebank (SST) and DynaSent. We provided input from ELECTRA to GPT as: predicted label, probabilities, and retrieved examples. Sharing ELECTRA Base FT predictions with GPT-4o-mini significantly improved performance"},"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":"2501.00062","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-29T05:29:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dc4efc10796a6d60460a2b4bbc7a33d982e497626eab1068f86710b484ebdf18","abstract_canon_sha256":"47f29ca064717f31e0f9b7cbbf437f1cc7d5f030c47cd3b364d0c94c2538903c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:21.933299Z","signature_b64":"rMqytxsCEoCcmLVaewX3hZ2VrRJLYwZYPeedFmU5v5DD2NgeU1LrWIu2SyBzwMyeiwsXkQi969fgxtM6aVFaCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d35352fe787757590c680b03e2e647c3692397e1437363ac9dfcdfcbc1fd5afe","last_reissued_at":"2026-07-05T10:58:21.932798Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:21.932798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ELECTRA and GPT-4o: Cost-Effective Partners for Sentiment Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"James P. Beno","submitted_at":"2024-12-29T05:29:52Z","abstract_excerpt":"Bidirectional transformers excel at sentiment analysis, and Large Language Models (LLM) are effective zero-shot learners. Might they perform better as a team? This paper explores collaborative approaches between ELECTRA and GPT-4o for three-way sentiment classification. We fine-tuned (FT) four models (ELECTRA Base/Large, GPT-4o/4o-mini) using a mix of reviews from Stanford Sentiment Treebank (SST) and DynaSent. We provided input from ELECTRA to GPT as: predicted label, probabilities, and retrieved examples. Sharing ELECTRA Base FT predictions with GPT-4o-mini significantly improved performance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00062","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/2501.00062/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":"2501.00062","created_at":"2026-07-05T10:58:21.932862+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00062v2","created_at":"2026-07-05T10:58:21.932862+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00062","created_at":"2026-07-05T10:58:21.932862+00:00"},{"alias_kind":"pith_short_12","alias_value":"2NJVF7TYO5LV","created_at":"2026-07-05T10:58:21.932862+00:00"},{"alias_kind":"pith_short_16","alias_value":"2NJVF7TYO5LVSDDI","created_at":"2026-07-05T10:58:21.932862+00:00"},{"alias_kind":"pith_short_8","alias_value":"2NJVF7TY","created_at":"2026-07-05T10:58:21.932862+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17846","citing_title":"Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2NJVF7TYO5LVSDDIBMB6FZSHYN","json":"https://pith.science/pith/2NJVF7TYO5LVSDDIBMB6FZSHYN.json","graph_json":"https://pith.science/api/pith-number/2NJVF7TYO5LVSDDIBMB6FZSHYN/graph.json","events_json":"https://pith.science/api/pith-number/2NJVF7TYO5LVSDDIBMB6FZSHYN/events.json","paper":"https://pith.science/paper/2NJVF7TY"},"agent_actions":{"view_html":"https://pith.science/pith/2NJVF7TYO5LVSDDIBMB6FZSHYN","download_json":"https://pith.science/pith/2NJVF7TYO5LVSDDIBMB6FZSHYN.json","view_paper":"https://pith.science/paper/2NJVF7TY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00062&json=true","fetch_graph":"https://pith.science/api/pith-number/2NJVF7TYO5LVSDDIBMB6FZSHYN/graph.json","fetch_events":"https://pith.science/api/pith-number/2NJVF7TYO5LVSDDIBMB6FZSHYN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2NJVF7TYO5LVSDDIBMB6FZSHYN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2NJVF7TYO5LVSDDIBMB6FZSHYN/action/storage_attestation","attest_author":"https://pith.science/pith/2NJVF7TYO5LVSDDIBMB6FZSHYN/action/author_attestation","sign_citation":"https://pith.science/pith/2NJVF7TYO5LVSDDIBMB6FZSHYN/action/citation_signature","submit_replication":"https://pith.science/pith/2NJVF7TYO5LVSDDIBMB6FZSHYN/action/replication_record"}},"created_at":"2026-07-05T10:58:21.932862+00:00","updated_at":"2026-07-05T10:58:21.932862+00:00"}