{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AQZLYLHOLDHJDQ73OE5MWIIPTS","short_pith_number":"pith:AQZLYLHO","schema_version":"1.0","canonical_sha256":"0432bc2cee58ce91c3fb713acb210f9ca7d72e08153d7d8f965a45970ec64d5a","source":{"kind":"arxiv","id":"2510.20477","version":3},"attestation_state":"computed","paper":{"title":"Bi-CoG: Bi-Consistency-Guided Self-Training for Vision-Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Bi-CoG produces higher-quality pseudo-labels for vision-language models by checking consistency both across models and inside a single model.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lan-Zhe Guo, Rui Zhu, Song-Lin Lv, Zi-Kang Wang","submitted_at":"2025-10-23T12:16:41Z","abstract_excerpt":"Exploiting unlabeled data through semi-supervised learning (SSL) or leveraging pre-trained models via fine-tuning are two prevailing paradigms for addressing label-scarce scenarios. Recently, growing attention has been given to combining fine-tuning of pre-trained vision-language models (VLMs) with SSL, forming the emerging paradigm of semi-supervised fine-tuning. However, existing methods often suffer from model bias and hyperparameter sensitivity, due to reliance on prediction consistency or pre-defined confidence thresholds. To address these limitations, we propose a simple yet effective pl"},"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":true},"canonical_record":{"source":{"id":"2510.20477","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-23T12:16:41Z","cross_cats_sorted":[],"title_canon_sha256":"4df7e32150b77cd9747f6830b14f5e201a60620f782f396b9495efd6d9fb6f5a","abstract_canon_sha256":"676828eb599c82787e70d879d5be1b9078b18f36b3bebe32ce9e00128b2cb323"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:17.165117Z","signature_b64":"XL88kdvMxRZtcAl2Gto7nLfN1Us1LJUPJkLJaSomjZUHAmpJOT8hgGDVdyPN+RG44gZN3/b2sZzfZ+b4lVCjDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0432bc2cee58ce91c3fb713acb210f9ca7d72e08153d7d8f965a45970ec64d5a","last_reissued_at":"2026-05-26T01:03:17.164579Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:17.164579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bi-CoG: Bi-Consistency-Guided Self-Training for Vision-Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Bi-CoG produces higher-quality pseudo-labels for vision-language models by checking consistency both across models and inside a single model.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lan-Zhe Guo, Rui Zhu, Song-Lin Lv, Zi-Kang Wang","submitted_at":"2025-10-23T12:16:41Z","abstract_excerpt":"Exploiting unlabeled data through semi-supervised learning (SSL) or leveraging pre-trained models via fine-tuning are two prevailing paradigms for addressing label-scarce scenarios. Recently, growing attention has been given to combining fine-tuning of pre-trained vision-language models (VLMs) with SSL, forming the emerging paradigm of semi-supervised fine-tuning. However, existing methods often suffer from model bias and hyperparameter sensitivity, due to reliance on prediction consistency or pre-defined confidence thresholds. To address these limitations, we propose a simple yet effective pl"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Bi-CoG assigns high-quality and low-bias pseudo-labels by simultaneously exploiting inter-model and intra-model consistency, along with an error-aware dynamic pseudo-label assignment strategy, and consistently and significantly improves the performance of existing methods over 14 datasets.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that simultaneous inter-model and intra-model consistency, together with the error-aware dynamic strategy, reliably produces pseudo-labels that are both high-quality and low-bias without introducing new forms of confirmation bias or hyperparameter sensitivity, as implied by the claim that this addresses the limitations of prior consistency or threshold-based methods.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Bi-CoG improves semi-supervised fine-tuning of vision-language models by assigning higher-quality pseudo-labels through simultaneous inter-model and intra-model consistency checks combined with dynamic error-aware selection.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Bi-CoG produces higher-quality pseudo-labels for vision-language models by checking consistency both across models and inside a single model.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"af0952d0e81abc451dc05103234a78c1ed22fa1ee32fbc54fa43aecedce86449"},"source":{"id":"2510.20477","kind":"arxiv","version":3},"verdict":{"id":"1437b69b-781e-422f-b556-67a3d56d6ac4","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-18T04:55:53.717476Z","strongest_claim":"Bi-CoG assigns high-quality and low-bias pseudo-labels by simultaneously exploiting inter-model and intra-model consistency, along with an error-aware dynamic pseudo-label assignment strategy, and consistently and significantly improves the performance of existing methods over 14 datasets.","one_line_summary":"Bi-CoG improves semi-supervised fine-tuning of vision-language models by assigning higher-quality pseudo-labels through simultaneous inter-model and intra-model consistency checks combined with dynamic error-aware selection.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that simultaneous inter-model and intra-model consistency, together with the error-aware dynamic strategy, reliably produces pseudo-labels that are both high-quality and low-bias without introducing new forms of confirmation bias or hyperparameter sensitivity, as implied by the claim that this addresses the limitations of prior consistency or threshold-based methods.","pith_extraction_headline":"Bi-CoG produces higher-quality pseudo-labels for vision-language models by checking consistency both across models and inside a single model."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2510.20477/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":1,"snapshot_sha256":"b6e8e26d98dca957144a0d4a831dc88a15e618dd0030369dddf3665f8a92456f"},"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":"2510.20477","created_at":"2026-05-26T01:03:17.164643+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.20477v3","created_at":"2026-05-26T01:03:17.164643+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.20477","created_at":"2026-05-26T01:03:17.164643+00:00"},{"alias_kind":"pith_short_12","alias_value":"AQZLYLHOLDHJ","created_at":"2026-05-26T01:03:17.164643+00:00"},{"alias_kind":"pith_short_16","alias_value":"AQZLYLHOLDHJDQ73","created_at":"2026-05-26T01:03:17.164643+00:00"},{"alias_kind":"pith_short_8","alias_value":"AQZLYLHO","created_at":"2026-05-26T01:03:17.164643+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":1,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AQZLYLHOLDHJDQ73OE5MWIIPTS","json":"https://pith.science/pith/AQZLYLHOLDHJDQ73OE5MWIIPTS.json","graph_json":"https://pith.science/api/pith-number/AQZLYLHOLDHJDQ73OE5MWIIPTS/graph.json","events_json":"https://pith.science/api/pith-number/AQZLYLHOLDHJDQ73OE5MWIIPTS/events.json","paper":"https://pith.science/paper/AQZLYLHO"},"agent_actions":{"view_html":"https://pith.science/pith/AQZLYLHOLDHJDQ73OE5MWIIPTS","download_json":"https://pith.science/pith/AQZLYLHOLDHJDQ73OE5MWIIPTS.json","view_paper":"https://pith.science/paper/AQZLYLHO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.20477&json=true","fetch_graph":"https://pith.science/api/pith-number/AQZLYLHOLDHJDQ73OE5MWIIPTS/graph.json","fetch_events":"https://pith.science/api/pith-number/AQZLYLHOLDHJDQ73OE5MWIIPTS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AQZLYLHOLDHJDQ73OE5MWIIPTS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AQZLYLHOLDHJDQ73OE5MWIIPTS/action/storage_attestation","attest_author":"https://pith.science/pith/AQZLYLHOLDHJDQ73OE5MWIIPTS/action/author_attestation","sign_citation":"https://pith.science/pith/AQZLYLHOLDHJDQ73OE5MWIIPTS/action/citation_signature","submit_replication":"https://pith.science/pith/AQZLYLHOLDHJDQ73OE5MWIIPTS/action/replication_record"}},"created_at":"2026-05-26T01:03:17.164643+00:00","updated_at":"2026-05-26T01:03:17.164643+00:00"}