{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5U7HEH3W4R64XPEYYQ3S7B7ICB","short_pith_number":"pith:5U7HEH3W","schema_version":"1.0","canonical_sha256":"ed3e721f76e47dcbbc98c4372f87e810618b4b5c68052fda839b7c2ccdb31d99","source":{"kind":"arxiv","id":"2211.17142","version":2},"attestation_state":"computed","paper":{"title":"Learning Label Modular Prompts for Text Classification in the Wild","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amrita Saha, Hailin Chen, Shafiq Joty, Steven C.H. Hoi","submitted_at":"2022-11-30T16:26:38Z","abstract_excerpt":"Machine learning models usually assume i.i.d data during training and testing, but data and tasks in real world often change over time. To emulate the transient nature of real world, we propose a challenging but practical task: text classification in-the-wild, which introduces different non-stationary training/testing stages. Decomposing a complex task into modular components can enable robust generalisation under such non-stationary environment. However, current modular approaches in NLP do not take advantage of recent advances in parameter efficient tuning of pretrained language models. To c"},"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":"2211.17142","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-30T16:26:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"08d151194b70e61882c5ea72cb57e0121261954c6bffb5f75247c672b73b92d6","abstract_canon_sha256":"3dc0f766344031e9aa7f7b94eb08990f88b22e7e90235dd53bc82a979a811db1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:22:13.112716Z","signature_b64":"ghqQcX3qSq8Bh2vfDi4r3jfyMcjQCGv/7WDcougZw4HtKQf0douFMNc56tE3KOTwzy2Xa3Xqn1a41tj8+sNZAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed3e721f76e47dcbbc98c4372f87e810618b4b5c68052fda839b7c2ccdb31d99","last_reissued_at":"2026-07-05T05:22:13.112377Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:22:13.112377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Label Modular Prompts for Text Classification in the Wild","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amrita Saha, Hailin Chen, Shafiq Joty, Steven C.H. Hoi","submitted_at":"2022-11-30T16:26:38Z","abstract_excerpt":"Machine learning models usually assume i.i.d data during training and testing, but data and tasks in real world often change over time. To emulate the transient nature of real world, we propose a challenging but practical task: text classification in-the-wild, which introduces different non-stationary training/testing stages. Decomposing a complex task into modular components can enable robust generalisation under such non-stationary environment. However, current modular approaches in NLP do not take advantage of recent advances in parameter efficient tuning of pretrained language models. To c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.17142","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/2211.17142/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":"2211.17142","created_at":"2026-07-05T05:22:13.112435+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.17142v2","created_at":"2026-07-05T05:22:13.112435+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.17142","created_at":"2026-07-05T05:22:13.112435+00:00"},{"alias_kind":"pith_short_12","alias_value":"5U7HEH3W4R64","created_at":"2026-07-05T05:22:13.112435+00:00"},{"alias_kind":"pith_short_16","alias_value":"5U7HEH3W4R64XPEY","created_at":"2026-07-05T05:22:13.112435+00:00"},{"alias_kind":"pith_short_8","alias_value":"5U7HEH3W","created_at":"2026-07-05T05:22:13.112435+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/5U7HEH3W4R64XPEYYQ3S7B7ICB","json":"https://pith.science/pith/5U7HEH3W4R64XPEYYQ3S7B7ICB.json","graph_json":"https://pith.science/api/pith-number/5U7HEH3W4R64XPEYYQ3S7B7ICB/graph.json","events_json":"https://pith.science/api/pith-number/5U7HEH3W4R64XPEYYQ3S7B7ICB/events.json","paper":"https://pith.science/paper/5U7HEH3W"},"agent_actions":{"view_html":"https://pith.science/pith/5U7HEH3W4R64XPEYYQ3S7B7ICB","download_json":"https://pith.science/pith/5U7HEH3W4R64XPEYYQ3S7B7ICB.json","view_paper":"https://pith.science/paper/5U7HEH3W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.17142&json=true","fetch_graph":"https://pith.science/api/pith-number/5U7HEH3W4R64XPEYYQ3S7B7ICB/graph.json","fetch_events":"https://pith.science/api/pith-number/5U7HEH3W4R64XPEYYQ3S7B7ICB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5U7HEH3W4R64XPEYYQ3S7B7ICB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5U7HEH3W4R64XPEYYQ3S7B7ICB/action/storage_attestation","attest_author":"https://pith.science/pith/5U7HEH3W4R64XPEYYQ3S7B7ICB/action/author_attestation","sign_citation":"https://pith.science/pith/5U7HEH3W4R64XPEYYQ3S7B7ICB/action/citation_signature","submit_replication":"https://pith.science/pith/5U7HEH3W4R64XPEYYQ3S7B7ICB/action/replication_record"}},"created_at":"2026-07-05T05:22:13.112435+00:00","updated_at":"2026-07-05T05:22:13.112435+00:00"}