{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FAIX6JRYJVGGGMVH6ZWJESYTPZ","short_pith_number":"pith:FAIX6JRY","schema_version":"1.0","canonical_sha256":"28117f26384d4c6332a7f66c924b137e442af9ce9af7a1357ae0e7831fbf8364","source":{"kind":"arxiv","id":"2412.05710","version":2},"attestation_state":"computed","paper":{"title":"PromptRefine: Enhancing Few-Shot Performance on Low-Resource Indic Languages with Example Selection from Related Example Banks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Dinesh Manocha, Koyel Mukherjee, Soumyabrata Pal, Soumya Suvra Ghosal","submitted_at":"2024-12-07T17:51:31Z","abstract_excerpt":"Large Language Models (LLMs) have recently demonstrated impressive few-shot learning capabilities through in-context learning (ICL). However, ICL performance is highly dependent on the choice of few-shot demonstrations, making the selection of the most optimal examples a persistent research challenge. This issue is further amplified in low-resource Indic languages, where the scarcity of ground-truth data complicates the selection process. In this work, we propose PromptRefine, a novel Alternating Minimization approach for example selection that improves ICL performance on low-resource Indic la"},"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":"2412.05710","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-07T17:51:31Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"15af371fee0ca5ce5ab91dc98af93b62e0ec0eef3f96979126ba0ae5ae71202f","abstract_canon_sha256":"0d761908a520fc78ee1b8c883f320777351c35a53b2872c369921130cc436243"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:16.522982Z","signature_b64":"LX/5EO8ji8qUAyIEUUMWdQSzGv3JgbR/Tm7YpMaqkDKsjj9YLIWNuEOaZzQ4nFQ8eWUur/t4rpUFrCwmP2xlBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28117f26384d4c6332a7f66c924b137e442af9ce9af7a1357ae0e7831fbf8364","last_reissued_at":"2026-07-05T11:13:16.522507Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:16.522507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PromptRefine: Enhancing Few-Shot Performance on Low-Resource Indic Languages with Example Selection from Related Example Banks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Dinesh Manocha, Koyel Mukherjee, Soumyabrata Pal, Soumya Suvra Ghosal","submitted_at":"2024-12-07T17:51:31Z","abstract_excerpt":"Large Language Models (LLMs) have recently demonstrated impressive few-shot learning capabilities through in-context learning (ICL). However, ICL performance is highly dependent on the choice of few-shot demonstrations, making the selection of the most optimal examples a persistent research challenge. This issue is further amplified in low-resource Indic languages, where the scarcity of ground-truth data complicates the selection process. In this work, we propose PromptRefine, a novel Alternating Minimization approach for example selection that improves ICL performance on low-resource Indic la"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05710","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/2412.05710/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":"2412.05710","created_at":"2026-07-05T11:13:16.522565+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05710v2","created_at":"2026-07-05T11:13:16.522565+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05710","created_at":"2026-07-05T11:13:16.522565+00:00"},{"alias_kind":"pith_short_12","alias_value":"FAIX6JRYJVGG","created_at":"2026-07-05T11:13:16.522565+00:00"},{"alias_kind":"pith_short_16","alias_value":"FAIX6JRYJVGGGMVH","created_at":"2026-07-05T11:13:16.522565+00:00"},{"alias_kind":"pith_short_8","alias_value":"FAIX6JRY","created_at":"2026-07-05T11:13:16.522565+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FAIX6JRYJVGGGMVH6ZWJESYTPZ","json":"https://pith.science/pith/FAIX6JRYJVGGGMVH6ZWJESYTPZ.json","graph_json":"https://pith.science/api/pith-number/FAIX6JRYJVGGGMVH6ZWJESYTPZ/graph.json","events_json":"https://pith.science/api/pith-number/FAIX6JRYJVGGGMVH6ZWJESYTPZ/events.json","paper":"https://pith.science/paper/FAIX6JRY"},"agent_actions":{"view_html":"https://pith.science/pith/FAIX6JRYJVGGGMVH6ZWJESYTPZ","download_json":"https://pith.science/pith/FAIX6JRYJVGGGMVH6ZWJESYTPZ.json","view_paper":"https://pith.science/paper/FAIX6JRY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05710&json=true","fetch_graph":"https://pith.science/api/pith-number/FAIX6JRYJVGGGMVH6ZWJESYTPZ/graph.json","fetch_events":"https://pith.science/api/pith-number/FAIX6JRYJVGGGMVH6ZWJESYTPZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FAIX6JRYJVGGGMVH6ZWJESYTPZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FAIX6JRYJVGGGMVH6ZWJESYTPZ/action/storage_attestation","attest_author":"https://pith.science/pith/FAIX6JRYJVGGGMVH6ZWJESYTPZ/action/author_attestation","sign_citation":"https://pith.science/pith/FAIX6JRYJVGGGMVH6ZWJESYTPZ/action/citation_signature","submit_replication":"https://pith.science/pith/FAIX6JRYJVGGGMVH6ZWJESYTPZ/action/replication_record"}},"created_at":"2026-07-05T11:13:16.522565+00:00","updated_at":"2026-07-05T11:13:16.522565+00:00"}