{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MDSDBLL7VQ7BXRMFUHLOFE4676","short_pith_number":"pith:MDSDBLL7","schema_version":"1.0","canonical_sha256":"60e430ad7fac3e1bc585a1d6e2939effaea36f1a16c41f0eb2b5361c5bbf753a","source":{"kind":"arxiv","id":"2305.14827","version":2},"attestation_state":"computed","paper":{"title":"Pre-training Intent-Aware Encoders for Zero- and Few-Shot Intent Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Elman Mansimov, James Gung, Mujeen Sung, Nikolaos Pappas, Raphael Shu, Salvatore Romeo, Vittorio Castelli, Yi Zhang","submitted_at":"2023-05-24T07:34:32Z","abstract_excerpt":"Intent classification (IC) plays an important role in task-oriented dialogue systems. However, IC models often generalize poorly when training without sufficient annotated examples for each user intent. We propose a novel pre-training method for text encoders that uses contrastive learning with intent psuedo-labels to produce embeddings that are well-suited for IC tasks, reducing the need for manual annotations. By applying this pre-training strategy, we also introduce Pre-trained Intent-aware Encoder (PIE), which is designed to align encodings of utterances with their intent names. Specifical"},"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":"2305.14827","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T07:34:32Z","cross_cats_sorted":[],"title_canon_sha256":"9477c95694a5cbc25be89b4ec27948a3c987e1ec85cf50d05e94ce302df083bd","abstract_canon_sha256":"972a2e56aed23aa6114ceb805785c64858675a9d5a0a66f686f256517171a5fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:16.831881Z","signature_b64":"Xi0tVmQcsRIsgFHptdqoeizl5BtVTugiK1qhkxt0rWgVJCPxVkbuiZyT3ifMA83AD6I1WdRVueaygV0VWgYlAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60e430ad7fac3e1bc585a1d6e2939effaea36f1a16c41f0eb2b5361c5bbf753a","last_reissued_at":"2026-07-05T07:12:16.831403Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:16.831403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pre-training Intent-Aware Encoders for Zero- and Few-Shot Intent Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Elman Mansimov, James Gung, Mujeen Sung, Nikolaos Pappas, Raphael Shu, Salvatore Romeo, Vittorio Castelli, Yi Zhang","submitted_at":"2023-05-24T07:34:32Z","abstract_excerpt":"Intent classification (IC) plays an important role in task-oriented dialogue systems. However, IC models often generalize poorly when training without sufficient annotated examples for each user intent. We propose a novel pre-training method for text encoders that uses contrastive learning with intent psuedo-labels to produce embeddings that are well-suited for IC tasks, reducing the need for manual annotations. By applying this pre-training strategy, we also introduce Pre-trained Intent-aware Encoder (PIE), which is designed to align encodings of utterances with their intent names. Specifical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14827","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/2305.14827/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":"2305.14827","created_at":"2026-07-05T07:12:16.831461+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14827v2","created_at":"2026-07-05T07:12:16.831461+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14827","created_at":"2026-07-05T07:12:16.831461+00:00"},{"alias_kind":"pith_short_12","alias_value":"MDSDBLL7VQ7B","created_at":"2026-07-05T07:12:16.831461+00:00"},{"alias_kind":"pith_short_16","alias_value":"MDSDBLL7VQ7BXRMF","created_at":"2026-07-05T07:12:16.831461+00:00"},{"alias_kind":"pith_short_8","alias_value":"MDSDBLL7","created_at":"2026-07-05T07:12:16.831461+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/MDSDBLL7VQ7BXRMFUHLOFE4676","json":"https://pith.science/pith/MDSDBLL7VQ7BXRMFUHLOFE4676.json","graph_json":"https://pith.science/api/pith-number/MDSDBLL7VQ7BXRMFUHLOFE4676/graph.json","events_json":"https://pith.science/api/pith-number/MDSDBLL7VQ7BXRMFUHLOFE4676/events.json","paper":"https://pith.science/paper/MDSDBLL7"},"agent_actions":{"view_html":"https://pith.science/pith/MDSDBLL7VQ7BXRMFUHLOFE4676","download_json":"https://pith.science/pith/MDSDBLL7VQ7BXRMFUHLOFE4676.json","view_paper":"https://pith.science/paper/MDSDBLL7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14827&json=true","fetch_graph":"https://pith.science/api/pith-number/MDSDBLL7VQ7BXRMFUHLOFE4676/graph.json","fetch_events":"https://pith.science/api/pith-number/MDSDBLL7VQ7BXRMFUHLOFE4676/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MDSDBLL7VQ7BXRMFUHLOFE4676/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MDSDBLL7VQ7BXRMFUHLOFE4676/action/storage_attestation","attest_author":"https://pith.science/pith/MDSDBLL7VQ7BXRMFUHLOFE4676/action/author_attestation","sign_citation":"https://pith.science/pith/MDSDBLL7VQ7BXRMFUHLOFE4676/action/citation_signature","submit_replication":"https://pith.science/pith/MDSDBLL7VQ7BXRMFUHLOFE4676/action/replication_record"}},"created_at":"2026-07-05T07:12:16.831461+00:00","updated_at":"2026-07-05T07:12:16.831461+00:00"}