{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JSLABZJZXHYRITUA574DYDZK3G","short_pith_number":"pith:JSLABZJZ","schema_version":"1.0","canonical_sha256":"4c9600e539b9f1144e80eff83c0f2ad9982f85416c4b3f4b6cc2d371cf9fead9","source":{"kind":"arxiv","id":"2507.22075","version":1},"attestation_state":"computed","paper":{"title":"Prototype-Guided Pseudo-Labeling with Neighborhood-Aware Consistency for Unsupervised Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chetan Arora, Eman Ali, Muhammad Haris Khan","submitted_at":"2025-07-22T19:08:24Z","abstract_excerpt":"In unsupervised adaptation for vision-language models such as CLIP, pseudo-labels derived from zero-shot predictions often exhibit significant noise, particularly under domain shifts or in visually complex scenarios. Conventional pseudo-label filtering approaches, which rely on fixed confidence thresholds, tend to be unreliable in fully unsupervised settings. In this work, we propose a novel adaptive pseudo-labeling framework that enhances CLIP's adaptation performance by integrating prototype consistency and neighborhood-based consistency. The proposed method comprises two key components: PIC"},"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":"2507.22075","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-22T19:08:24Z","cross_cats_sorted":[],"title_canon_sha256":"3752dbae88dcd58283bbad51fc82de3942c5bded78cca1ebeffd41a3dd863a45","abstract_canon_sha256":"0486f81ab3328798f6049e74a6eab3182fb7626d52b1ad1ea72bc41451714a2c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:15.998512Z","signature_b64":"UParYmNSTCOyBypJa/PxGVxq3zkJy+gFbVR0R8yzZUTaz9eyB2FfqCAl0fPEa9bMXKgGueBzjLE4puEeqo1PDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c9600e539b9f1144e80eff83c0f2ad9982f85416c4b3f4b6cc2d371cf9fead9","last_reissued_at":"2026-07-05T11:45:15.998106Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:15.998106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prototype-Guided Pseudo-Labeling with Neighborhood-Aware Consistency for Unsupervised Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chetan Arora, Eman Ali, Muhammad Haris Khan","submitted_at":"2025-07-22T19:08:24Z","abstract_excerpt":"In unsupervised adaptation for vision-language models such as CLIP, pseudo-labels derived from zero-shot predictions often exhibit significant noise, particularly under domain shifts or in visually complex scenarios. Conventional pseudo-label filtering approaches, which rely on fixed confidence thresholds, tend to be unreliable in fully unsupervised settings. In this work, we propose a novel adaptive pseudo-labeling framework that enhances CLIP's adaptation performance by integrating prototype consistency and neighborhood-based consistency. The proposed method comprises two key components: PIC"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22075","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/2507.22075/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":"2507.22075","created_at":"2026-07-05T11:45:15.998160+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.22075v1","created_at":"2026-07-05T11:45:15.998160+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22075","created_at":"2026-07-05T11:45:15.998160+00:00"},{"alias_kind":"pith_short_12","alias_value":"JSLABZJZXHYR","created_at":"2026-07-05T11:45:15.998160+00:00"},{"alias_kind":"pith_short_16","alias_value":"JSLABZJZXHYRITUA","created_at":"2026-07-05T11:45:15.998160+00:00"},{"alias_kind":"pith_short_8","alias_value":"JSLABZJZ","created_at":"2026-07-05T11:45:15.998160+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/JSLABZJZXHYRITUA574DYDZK3G","json":"https://pith.science/pith/JSLABZJZXHYRITUA574DYDZK3G.json","graph_json":"https://pith.science/api/pith-number/JSLABZJZXHYRITUA574DYDZK3G/graph.json","events_json":"https://pith.science/api/pith-number/JSLABZJZXHYRITUA574DYDZK3G/events.json","paper":"https://pith.science/paper/JSLABZJZ"},"agent_actions":{"view_html":"https://pith.science/pith/JSLABZJZXHYRITUA574DYDZK3G","download_json":"https://pith.science/pith/JSLABZJZXHYRITUA574DYDZK3G.json","view_paper":"https://pith.science/paper/JSLABZJZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.22075&json=true","fetch_graph":"https://pith.science/api/pith-number/JSLABZJZXHYRITUA574DYDZK3G/graph.json","fetch_events":"https://pith.science/api/pith-number/JSLABZJZXHYRITUA574DYDZK3G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JSLABZJZXHYRITUA574DYDZK3G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JSLABZJZXHYRITUA574DYDZK3G/action/storage_attestation","attest_author":"https://pith.science/pith/JSLABZJZXHYRITUA574DYDZK3G/action/author_attestation","sign_citation":"https://pith.science/pith/JSLABZJZXHYRITUA574DYDZK3G/action/citation_signature","submit_replication":"https://pith.science/pith/JSLABZJZXHYRITUA574DYDZK3G/action/replication_record"}},"created_at":"2026-07-05T11:45:15.998160+00:00","updated_at":"2026-07-05T11:45:15.998160+00:00"}