{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Y2NTYWIEV5LQD4TKQNDCE6IEHU","short_pith_number":"pith:Y2NTYWIE","schema_version":"1.0","canonical_sha256":"c69b3c5904af5701f26a83462279043d0f7444db26c608b4d9915761c9ea7875","source":{"kind":"arxiv","id":"2607.27421","version":1},"attestation_state":"computed","paper":{"title":"Selecting Open-Weight Language Models for Zero-Shot Intent Classification: A Systematic Evaluation of 41 Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Cheryl Seals, Gerry Dozier, Parishruthi Ganesh","submitted_at":"2026-07-29T19:42:33Z","abstract_excerpt":"Intent classification is a core component of task-oriented dialogue systems, yet practitioners have limited systematic guidance for selecting deployable open-weight language models under compute, latency, and robustness constraints. We present a systematic zero-shot evaluation of 41 open-weight language models spanning 15 families and the 135M--9B parameter range across eight English single-label intent-classification datasets. A ninth dataset, ATIS, uses five labeled demonstrations and is reported as an auxiliary five-shot result. The evaluation includes standard benchmarks, a large-scale voi"},"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":"2607.27421","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-29T19:42:33Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5f56c3b479ef055713bc02efc66c9424e51a99bdaa8fb4e26fcbea6bd8884dbb","abstract_canon_sha256":"3ff229f17d2e4787e0a8bc034c394ee9bc7f78d827eef78db1fa08d2065cbf65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c69b3c5904af5701f26a83462279043d0f7444db26c608b4d9915761c9ea7875","last_reissued_at":"2026-07-31T00:11:59.602390Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T00:11:59.602390Z"},"graph_snapshot":{"paper":{"title":"Selecting Open-Weight Language Models for Zero-Shot Intent Classification: A Systematic Evaluation of 41 Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Cheryl Seals, Gerry Dozier, Parishruthi Ganesh","submitted_at":"2026-07-29T19:42:33Z","abstract_excerpt":"Intent classification is a core component of task-oriented dialogue systems, yet practitioners have limited systematic guidance for selecting deployable open-weight language models under compute, latency, and robustness constraints. We present a systematic zero-shot evaluation of 41 open-weight language models spanning 15 families and the 135M--9B parameter range across eight English single-label intent-classification datasets. A ninth dataset, ATIS, uses five labeled demonstrations and is reported as an auxiliary five-shot result. The evaluation includes standard benchmarks, a large-scale voi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27421","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/2607.27421/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":"2607.27421","created_at":"2026-07-31T00:11:59.604721+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.27421v1","created_at":"2026-07-31T00:11:59.604721+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27421","created_at":"2026-07-31T00:11:59.604721+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y2NTYWIEV5LQ","created_at":"2026-07-31T00:11:59.604721+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y2NTYWIEV5LQD4TK","created_at":"2026-07-31T00:11:59.604721+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y2NTYWIE","created_at":"2026-07-31T00:11:59.604721+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/Y2NTYWIEV5LQD4TKQNDCE6IEHU","json":"https://pith.science/pith/Y2NTYWIEV5LQD4TKQNDCE6IEHU.json","graph_json":"https://pith.science/api/pith-number/Y2NTYWIEV5LQD4TKQNDCE6IEHU/graph.json","events_json":"https://pith.science/api/pith-number/Y2NTYWIEV5LQD4TKQNDCE6IEHU/events.json","paper":"https://pith.science/paper/Y2NTYWIE"},"agent_actions":{"view_html":"https://pith.science/pith/Y2NTYWIEV5LQD4TKQNDCE6IEHU","download_json":"https://pith.science/pith/Y2NTYWIEV5LQD4TKQNDCE6IEHU.json","view_paper":"https://pith.science/paper/Y2NTYWIE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.27421&json=true","fetch_graph":"https://pith.science/api/pith-number/Y2NTYWIEV5LQD4TKQNDCE6IEHU/graph.json","fetch_events":"https://pith.science/api/pith-number/Y2NTYWIEV5LQD4TKQNDCE6IEHU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y2NTYWIEV5LQD4TKQNDCE6IEHU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y2NTYWIEV5LQD4TKQNDCE6IEHU/action/storage_attestation","attest_author":"https://pith.science/pith/Y2NTYWIEV5LQD4TKQNDCE6IEHU/action/author_attestation","sign_citation":"https://pith.science/pith/Y2NTYWIEV5LQD4TKQNDCE6IEHU/action/citation_signature","submit_replication":"https://pith.science/pith/Y2NTYWIEV5LQD4TKQNDCE6IEHU/action/replication_record"}},"created_at":"2026-07-31T00:11:59.604721+00:00","updated_at":"2026-07-31T00:11:59.604721+00:00"}