{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GFROLO2UJINLKGH3SQIBY5UZDN","short_pith_number":"pith:GFROLO2U","schema_version":"1.0","canonical_sha256":"3162e5bb544a1ab518fb94101c76991b5ef5e750dfc3ef2fe23747b0f07e6d5f","source":{"kind":"arxiv","id":"2207.03037","version":1},"attestation_state":"computed","paper":{"title":"Sensitivity Analysis on Transferred Neural Architectures of BERT and GPT-2 for Financial Sentiment Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andy Xie, Camille Bruckmann, Tracy Qian","submitted_at":"2022-07-07T01:38:07Z","abstract_excerpt":"The explosion in novel NLP word embedding and deep learning techniques has induced significant endeavors into potential applications. One of these directions is in the financial sector. Although there is a lot of work done in state-of-the-art models like GPT and BERT, there are relatively few works on how well these methods perform through fine-tuning after being pre-trained, as well as info on how sensitive their parameters are. We investigate the performance and sensitivity of transferred neural architectures from pre-trained GPT-2 and BERT models. We test the fine-tuning performance based o"},"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":"2207.03037","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-07-07T01:38:07Z","cross_cats_sorted":[],"title_canon_sha256":"d81ee93b8aca7475f3ba4a265b8a0f8e6a23e6da6c64117cd81a1cb9bac51258","abstract_canon_sha256":"be25ba4e82bddb31ea5b0e2e4f469a363ea997ef6d88fec2e7f4ba2af859e6f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:38:18.295407Z","signature_b64":"dAx+jVvopfP2lAIM1xG6n2zznNiNRX/bbQBRrFo+izJJQ1Zv6ELgTATxmQA6rLGBefOkuR6niW4Y/4nDnTpVCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3162e5bb544a1ab518fb94101c76991b5ef5e750dfc3ef2fe23747b0f07e6d5f","last_reissued_at":"2026-07-05T04:38:18.294975Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:38:18.294975Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sensitivity Analysis on Transferred Neural Architectures of BERT and GPT-2 for Financial Sentiment Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andy Xie, Camille Bruckmann, Tracy Qian","submitted_at":"2022-07-07T01:38:07Z","abstract_excerpt":"The explosion in novel NLP word embedding and deep learning techniques has induced significant endeavors into potential applications. One of these directions is in the financial sector. Although there is a lot of work done in state-of-the-art models like GPT and BERT, there are relatively few works on how well these methods perform through fine-tuning after being pre-trained, as well as info on how sensitive their parameters are. We investigate the performance and sensitivity of transferred neural architectures from pre-trained GPT-2 and BERT models. We test the fine-tuning performance based o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.03037","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/2207.03037/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":"2207.03037","created_at":"2026-07-05T04:38:18.295035+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.03037v1","created_at":"2026-07-05T04:38:18.295035+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.03037","created_at":"2026-07-05T04:38:18.295035+00:00"},{"alias_kind":"pith_short_12","alias_value":"GFROLO2UJINL","created_at":"2026-07-05T04:38:18.295035+00:00"},{"alias_kind":"pith_short_16","alias_value":"GFROLO2UJINLKGH3","created_at":"2026-07-05T04:38:18.295035+00:00"},{"alias_kind":"pith_short_8","alias_value":"GFROLO2U","created_at":"2026-07-05T04:38:18.295035+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.01575","citing_title":"Asset Pricing in Pre-trained Transformer","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GFROLO2UJINLKGH3SQIBY5UZDN","json":"https://pith.science/pith/GFROLO2UJINLKGH3SQIBY5UZDN.json","graph_json":"https://pith.science/api/pith-number/GFROLO2UJINLKGH3SQIBY5UZDN/graph.json","events_json":"https://pith.science/api/pith-number/GFROLO2UJINLKGH3SQIBY5UZDN/events.json","paper":"https://pith.science/paper/GFROLO2U"},"agent_actions":{"view_html":"https://pith.science/pith/GFROLO2UJINLKGH3SQIBY5UZDN","download_json":"https://pith.science/pith/GFROLO2UJINLKGH3SQIBY5UZDN.json","view_paper":"https://pith.science/paper/GFROLO2U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.03037&json=true","fetch_graph":"https://pith.science/api/pith-number/GFROLO2UJINLKGH3SQIBY5UZDN/graph.json","fetch_events":"https://pith.science/api/pith-number/GFROLO2UJINLKGH3SQIBY5UZDN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GFROLO2UJINLKGH3SQIBY5UZDN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GFROLO2UJINLKGH3SQIBY5UZDN/action/storage_attestation","attest_author":"https://pith.science/pith/GFROLO2UJINLKGH3SQIBY5UZDN/action/author_attestation","sign_citation":"https://pith.science/pith/GFROLO2UJINLKGH3SQIBY5UZDN/action/citation_signature","submit_replication":"https://pith.science/pith/GFROLO2UJINLKGH3SQIBY5UZDN/action/replication_record"}},"created_at":"2026-07-05T04:38:18.295035+00:00","updated_at":"2026-07-05T04:38:18.295035+00:00"}