{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IE6MDMGP7T5GNLD5P6NDTHKPHJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1d4e77b2d1a5c1ec63c5ea4dc6c473e295327edebda2b3875a2206fe27e84042","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-02T21:05:31Z","title_canon_sha256":"f371ae815454680911ab3f4f0ac61d7d5e7ba6ea04c90daaffe72eacb0e8a8b2"},"schema_version":"1.0","source":{"id":"2409.01466","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.01466","created_at":"2026-07-05T10:45:11Z"},{"alias_kind":"arxiv_version","alias_value":"2409.01466v2","created_at":"2026-07-05T10:45:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01466","created_at":"2026-07-05T10:45:11Z"},{"alias_kind":"pith_short_12","alias_value":"IE6MDMGP7T5G","created_at":"2026-07-05T10:45:11Z"},{"alias_kind":"pith_short_16","alias_value":"IE6MDMGP7T5GNLD5","created_at":"2026-07-05T10:45:11Z"},{"alias_kind":"pith_short_8","alias_value":"IE6MDMGP","created_at":"2026-07-05T10:45:11Z"}],"graph_snapshots":[{"event_id":"sha256:cc9190071772a8bd6d5890cf7798b200c6772882d222bacc0e4acf62bdf0bcb6","target":"graph","created_at":"2026-07-05T10:45:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2409.01466/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) offer substantial promise for text classification in political science, yet their effectiveness often depends on high-quality prompts and exemplars. To address this, we introduce a three-stage framework that enhances LLM performance through automatic prompt optimization, dynamic exemplar selection, and a consensus mechanism. Our approach automates prompt refinement using task-specific exemplars, eliminating speculative trial-and-error adjustments and producing structured prompts aligned with human-defined criteria. In the second stage, we dynamically select the mos","authors_text":"Ge Shi, Menglin Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-02T21:05:31Z","title":"Enhancing LLM-Based Text Classification in Political Science: Automatic Prompt Optimization and Dynamic Exemplar Selection for Few-Shot Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01466","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3123451c5969300a4e98ce2ec6ef05de3effd466fb355b20a8d9937fb5dc29a5","target":"record","created_at":"2026-07-05T10:45:11Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1d4e77b2d1a5c1ec63c5ea4dc6c473e295327edebda2b3875a2206fe27e84042","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-02T21:05:31Z","title_canon_sha256":"f371ae815454680911ab3f4f0ac61d7d5e7ba6ea04c90daaffe72eacb0e8a8b2"},"schema_version":"1.0","source":{"id":"2409.01466","kind":"arxiv","version":2}},"canonical_sha256":"413cc1b0cffcfa66ac7d7f9a399d4f3a4ad7a32757fec8f92d489b23db364029","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"413cc1b0cffcfa66ac7d7f9a399d4f3a4ad7a32757fec8f92d489b23db364029","first_computed_at":"2026-07-05T10:45:11.246065Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:45:11.246065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EipF3K4Iiryzg3JlTgmH4299SiR1rZHb+30MaxFQOJ1+CBB9f1p3WmLwzrzBbUdd9v/WTHAZthB4BhuPOl3gBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:45:11.246623Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.01466","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3123451c5969300a4e98ce2ec6ef05de3effd466fb355b20a8d9937fb5dc29a5","sha256:cc9190071772a8bd6d5890cf7798b200c6772882d222bacc0e4acf62bdf0bcb6"],"state_sha256":"cee979a5ec14570b47d7f965ffd89ca6490ead2499cb100600a96c3922dd7a90"}