{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TQI3PBMQRZROMEZC7KF5FGFSCF","short_pith_number":"pith:TQI3PBMQ","schema_version":"1.0","canonical_sha256":"9c11b785908e62e61322fa8bd298b21156201d4c21bf34dddb613eff32f28021","source":{"kind":"arxiv","id":"2507.00330","version":1},"attestation_state":"computed","paper":{"title":"Modeling Data Diversity for Joint Instance and Verbalizer Selection in Cold-Start Scenarios","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Adithya Kulkarni, Mohna Chakraborty, Qi Li","submitted_at":"2025-07-01T00:01:50Z","abstract_excerpt":"Prompt-based methods leverage the knowledge of pre-trained language models (PLMs) trained with a masked language modeling (MLM) objective; however, these methods are sensitive to template, verbalizer, and few-shot instance selection, particularly in cold-start settings with no labeled data. Existing studies overlook the dependency between instances and verbalizers, where instance-label probabilities depend on verbalizer token proximity in the embedding space. To address this, we propose COLDSELECT, a joint verbalizer and instance selection approach that models data diversity. COLDSELECT maps P"},"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":"2507.00330","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-01T00:01:50Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"38b01f7369a338ad82347beb0a6b2235d01ce884159d077f9a374866b00ad332","abstract_canon_sha256":"73e4dfac00af81e1e5690f5ceaf6700a14df49138cea1bf157fd4637339f7fdc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:06.349873Z","signature_b64":"S0w9sa4/CogMgjZ9H5ynkpvFXEUBH9iUPwvQwOEE2qYkMsZJHIaiN47fmy3Og6sW5AjewXvGa4BKYJok9ev1BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c11b785908e62e61322fa8bd298b21156201d4c21bf34dddb613eff32f28021","last_reissued_at":"2026-07-05T11:30:06.349437Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:06.349437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modeling Data Diversity for Joint Instance and Verbalizer Selection in Cold-Start Scenarios","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Adithya Kulkarni, Mohna Chakraborty, Qi Li","submitted_at":"2025-07-01T00:01:50Z","abstract_excerpt":"Prompt-based methods leverage the knowledge of pre-trained language models (PLMs) trained with a masked language modeling (MLM) objective; however, these methods are sensitive to template, verbalizer, and few-shot instance selection, particularly in cold-start settings with no labeled data. Existing studies overlook the dependency between instances and verbalizers, where instance-label probabilities depend on verbalizer token proximity in the embedding space. To address this, we propose COLDSELECT, a joint verbalizer and instance selection approach that models data diversity. COLDSELECT maps P"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00330","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/2507.00330/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":"2507.00330","created_at":"2026-07-05T11:30:06.349499+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00330v1","created_at":"2026-07-05T11:30:06.349499+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00330","created_at":"2026-07-05T11:30:06.349499+00:00"},{"alias_kind":"pith_short_12","alias_value":"TQI3PBMQRZRO","created_at":"2026-07-05T11:30:06.349499+00:00"},{"alias_kind":"pith_short_16","alias_value":"TQI3PBMQRZROMEZC","created_at":"2026-07-05T11:30:06.349499+00:00"},{"alias_kind":"pith_short_8","alias_value":"TQI3PBMQ","created_at":"2026-07-05T11:30:06.349499+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/TQI3PBMQRZROMEZC7KF5FGFSCF","json":"https://pith.science/pith/TQI3PBMQRZROMEZC7KF5FGFSCF.json","graph_json":"https://pith.science/api/pith-number/TQI3PBMQRZROMEZC7KF5FGFSCF/graph.json","events_json":"https://pith.science/api/pith-number/TQI3PBMQRZROMEZC7KF5FGFSCF/events.json","paper":"https://pith.science/paper/TQI3PBMQ"},"agent_actions":{"view_html":"https://pith.science/pith/TQI3PBMQRZROMEZC7KF5FGFSCF","download_json":"https://pith.science/pith/TQI3PBMQRZROMEZC7KF5FGFSCF.json","view_paper":"https://pith.science/paper/TQI3PBMQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00330&json=true","fetch_graph":"https://pith.science/api/pith-number/TQI3PBMQRZROMEZC7KF5FGFSCF/graph.json","fetch_events":"https://pith.science/api/pith-number/TQI3PBMQRZROMEZC7KF5FGFSCF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TQI3PBMQRZROMEZC7KF5FGFSCF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TQI3PBMQRZROMEZC7KF5FGFSCF/action/storage_attestation","attest_author":"https://pith.science/pith/TQI3PBMQRZROMEZC7KF5FGFSCF/action/author_attestation","sign_citation":"https://pith.science/pith/TQI3PBMQRZROMEZC7KF5FGFSCF/action/citation_signature","submit_replication":"https://pith.science/pith/TQI3PBMQRZROMEZC7KF5FGFSCF/action/replication_record"}},"created_at":"2026-07-05T11:30:06.349499+00:00","updated_at":"2026-07-05T11:30:06.349499+00:00"}