{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CHE4U3NGLUBOKVAEGBSEGG2OKS","short_pith_number":"pith:CHE4U3NG","schema_version":"1.0","canonical_sha256":"11c9ca6da65d02e554043064431b4e54805102f9455957e2c4ab206715c9225b","source":{"kind":"arxiv","id":"2405.11637","version":1},"attestation_state":"computed","paper":{"title":"Zero-Shot Stance Detection using Contextual Data Generation with LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Babak Behkamkia, Ghazaleh Mahmoudi, Sauleh Eetemadi","submitted_at":"2024-05-19T17:58:26Z","abstract_excerpt":"Stance detection, the classification of attitudes expressed in a text towards a specific topic, is vital for applications like fake news detection and opinion mining. However, the scarcity of labeled data remains a challenge for this task. To address this problem, we propose Dynamic Model Adaptation with Contextual Data Generation (DyMoAdapt) that combines Few-Shot Learning and Large Language Models. In this approach, we aim to fine-tune an existing model at test time. We achieve this by generating new topic-specific data using GPT-3. This method could enhance performance by allowing the adapt"},"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":"2405.11637","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-19T17:58:26Z","cross_cats_sorted":[],"title_canon_sha256":"2ecd90768c12e9eb00ab9d7a5fb42626d3fa41d93752d2ccfeb397a9569dc214","abstract_canon_sha256":"a9a8e1b55082660c94bd6f5cb31d6b7da174f30d463ee92d47d10957db9ba906"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:42.456387Z","signature_b64":"Dj7qi0tm/LNmo8L9nOM8acUZgARlcZiWcjPXGU3lfJRlM/2wenuIw/eJEETBtTFR7Ej3Z0JPaYwD33nPvTCjAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11c9ca6da65d02e554043064431b4e54805102f9455957e2c4ab206715c9225b","last_reissued_at":"2026-07-05T08:20:42.455893Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:42.455893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Stance Detection using Contextual Data Generation with LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Babak Behkamkia, Ghazaleh Mahmoudi, Sauleh Eetemadi","submitted_at":"2024-05-19T17:58:26Z","abstract_excerpt":"Stance detection, the classification of attitudes expressed in a text towards a specific topic, is vital for applications like fake news detection and opinion mining. However, the scarcity of labeled data remains a challenge for this task. To address this problem, we propose Dynamic Model Adaptation with Contextual Data Generation (DyMoAdapt) that combines Few-Shot Learning and Large Language Models. In this approach, we aim to fine-tune an existing model at test time. We achieve this by generating new topic-specific data using GPT-3. This method could enhance performance by allowing the adapt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.11637","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/2405.11637/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":"2405.11637","created_at":"2026-07-05T08:20:42.455953+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.11637v1","created_at":"2026-07-05T08:20:42.455953+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.11637","created_at":"2026-07-05T08:20:42.455953+00:00"},{"alias_kind":"pith_short_12","alias_value":"CHE4U3NGLUBO","created_at":"2026-07-05T08:20:42.455953+00:00"},{"alias_kind":"pith_short_16","alias_value":"CHE4U3NGLUBOKVAE","created_at":"2026-07-05T08:20:42.455953+00:00"},{"alias_kind":"pith_short_8","alias_value":"CHE4U3NG","created_at":"2026-07-05T08:20:42.455953+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.08512","citing_title":"Measuring Diversity in Synthetic Datasets","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CHE4U3NGLUBOKVAEGBSEGG2OKS","json":"https://pith.science/pith/CHE4U3NGLUBOKVAEGBSEGG2OKS.json","graph_json":"https://pith.science/api/pith-number/CHE4U3NGLUBOKVAEGBSEGG2OKS/graph.json","events_json":"https://pith.science/api/pith-number/CHE4U3NGLUBOKVAEGBSEGG2OKS/events.json","paper":"https://pith.science/paper/CHE4U3NG"},"agent_actions":{"view_html":"https://pith.science/pith/CHE4U3NGLUBOKVAEGBSEGG2OKS","download_json":"https://pith.science/pith/CHE4U3NGLUBOKVAEGBSEGG2OKS.json","view_paper":"https://pith.science/paper/CHE4U3NG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.11637&json=true","fetch_graph":"https://pith.science/api/pith-number/CHE4U3NGLUBOKVAEGBSEGG2OKS/graph.json","fetch_events":"https://pith.science/api/pith-number/CHE4U3NGLUBOKVAEGBSEGG2OKS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CHE4U3NGLUBOKVAEGBSEGG2OKS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CHE4U3NGLUBOKVAEGBSEGG2OKS/action/storage_attestation","attest_author":"https://pith.science/pith/CHE4U3NGLUBOKVAEGBSEGG2OKS/action/author_attestation","sign_citation":"https://pith.science/pith/CHE4U3NGLUBOKVAEGBSEGG2OKS/action/citation_signature","submit_replication":"https://pith.science/pith/CHE4U3NGLUBOKVAEGBSEGG2OKS/action/replication_record"}},"created_at":"2026-07-05T08:20:42.455953+00:00","updated_at":"2026-07-05T08:20:42.455953+00:00"}