{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QRFFMEEO5ZFDGLFH22PEHSTFUQ","short_pith_number":"pith:QRFFMEEO","schema_version":"1.0","canonical_sha256":"844a56108eee4a332ca7d69e43ca65a4246df696a88d5fdbfd4ba2d04522ebad","source":{"kind":"arxiv","id":"2502.12584","version":2},"attestation_state":"computed","paper":{"title":"Enhancing Semi-supervised Learning with Zero-shot Pseudolabels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Irene Y. Chen, Jichan Chung","submitted_at":"2025-02-18T06:41:53Z","abstract_excerpt":"The high cost of data labeling presents a major barrier to deploying machine learning systems at scale. Semi-supervised learning (SSL) mitigates this challenge by utilizing unlabeled data alongside limited labeled examples, while the emergence of foundation models (FMs) offers powerful zero-shot capabilities that can further reduce labeling cost. However, directly fine-tuning large FMs is often impractical in resource-constrained settings, and na\\\"ively using their pseudo-labels for unlabeled data can degrade performance due to its unreliablity or domain mismatch with target task. In this work"},"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":"2502.12584","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-18T06:41:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0e7dad2ada742d8b2df8978e269bf4f934338aa822d15130c9c7ab1a9f296a3d","abstract_canon_sha256":"8826237e3cd990c33969e6b2b7f0296c8275589e98ca8a64badc35898b1838f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:41.925520Z","signature_b64":"YOS41FJL3poMHNG8q2x92tKuN6f4facL4gImdOrWztmItuzWrXk7URlk4jZ8mIYJE/3ausabX/bbi5X1iMjmBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"844a56108eee4a332ca7d69e43ca65a4246df696a88d5fdbfd4ba2d04522ebad","last_reissued_at":"2026-07-05T11:11:41.924968Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:41.924968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Semi-supervised Learning with Zero-shot Pseudolabels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Irene Y. Chen, Jichan Chung","submitted_at":"2025-02-18T06:41:53Z","abstract_excerpt":"The high cost of data labeling presents a major barrier to deploying machine learning systems at scale. Semi-supervised learning (SSL) mitigates this challenge by utilizing unlabeled data alongside limited labeled examples, while the emergence of foundation models (FMs) offers powerful zero-shot capabilities that can further reduce labeling cost. However, directly fine-tuning large FMs is often impractical in resource-constrained settings, and na\\\"ively using their pseudo-labels for unlabeled data can degrade performance due to its unreliablity or domain mismatch with target task. In this work"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12584","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/2502.12584/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":"2502.12584","created_at":"2026-07-05T11:11:41.925023+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.12584v2","created_at":"2026-07-05T11:11:41.925023+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12584","created_at":"2026-07-05T11:11:41.925023+00:00"},{"alias_kind":"pith_short_12","alias_value":"QRFFMEEO5ZFD","created_at":"2026-07-05T11:11:41.925023+00:00"},{"alias_kind":"pith_short_16","alias_value":"QRFFMEEO5ZFDGLFH","created_at":"2026-07-05T11:11:41.925023+00:00"},{"alias_kind":"pith_short_8","alias_value":"QRFFMEEO","created_at":"2026-07-05T11:11:41.925023+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08448","citing_title":"LLM-guided Semi-Supervised Approaches for Social Media Crisis Data Classification","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QRFFMEEO5ZFDGLFH22PEHSTFUQ","json":"https://pith.science/pith/QRFFMEEO5ZFDGLFH22PEHSTFUQ.json","graph_json":"https://pith.science/api/pith-number/QRFFMEEO5ZFDGLFH22PEHSTFUQ/graph.json","events_json":"https://pith.science/api/pith-number/QRFFMEEO5ZFDGLFH22PEHSTFUQ/events.json","paper":"https://pith.science/paper/QRFFMEEO"},"agent_actions":{"view_html":"https://pith.science/pith/QRFFMEEO5ZFDGLFH22PEHSTFUQ","download_json":"https://pith.science/pith/QRFFMEEO5ZFDGLFH22PEHSTFUQ.json","view_paper":"https://pith.science/paper/QRFFMEEO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.12584&json=true","fetch_graph":"https://pith.science/api/pith-number/QRFFMEEO5ZFDGLFH22PEHSTFUQ/graph.json","fetch_events":"https://pith.science/api/pith-number/QRFFMEEO5ZFDGLFH22PEHSTFUQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QRFFMEEO5ZFDGLFH22PEHSTFUQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QRFFMEEO5ZFDGLFH22PEHSTFUQ/action/storage_attestation","attest_author":"https://pith.science/pith/QRFFMEEO5ZFDGLFH22PEHSTFUQ/action/author_attestation","sign_citation":"https://pith.science/pith/QRFFMEEO5ZFDGLFH22PEHSTFUQ/action/citation_signature","submit_replication":"https://pith.science/pith/QRFFMEEO5ZFDGLFH22PEHSTFUQ/action/replication_record"}},"created_at":"2026-07-05T11:11:41.925023+00:00","updated_at":"2026-07-05T11:11:41.925023+00:00"}