{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AQZLYLHOLDHJDQ73OE5MWIIPTS","short_pith_number":"pith:AQZLYLHO","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"},"canonical_sha256":"0432bc2cee58ce91c3fb713acb210f9ca7d72e08153d7d8f965a45970ec64d5a","source":{"kind":"arxiv","id":"2510.20477","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.20477","created_at":"2026-05-26T01:03:17Z"},{"alias_kind":"arxiv_version","alias_value":"2510.20477v3","created_at":"2026-05-26T01:03:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.20477","created_at":"2026-05-26T01:03:17Z"},{"alias_kind":"pith_short_12","alias_value":"AQZLYLHOLDHJ","created_at":"2026-05-26T01:03:17Z"},{"alias_kind":"pith_short_16","alias_value":"AQZLYLHOLDHJDQ73","created_at":"2026-05-26T01:03:17Z"},{"alias_kind":"pith_short_8","alias_value":"AQZLYLHO","created_at":"2026-05-26T01:03:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AQZLYLHOLDHJDQ73OE5MWIIPTS","target":"record","payload":{"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"},"canonical_sha256":"0432bc2cee58ce91c3fb713acb210f9ca7d72e08153d7d8f965a45970ec64d5a","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"},"source_kind":"arxiv","source_id":"2510.20477","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T01:03:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/u/Fz3mDDM2bLe4A1jJQsSgY4ptmKmlqPhmGTTjT/ChqfcrVFk7g+BDp4SVPljFcnXLkgjh92ULgdogq5LL8BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T23:58:33.381286Z"},"content_sha256":"4b9d95435555eb88a379f0eba4a323084dde0711c906a4dbc65790cbd2da76fc","schema_version":"1.0","event_id":"sha256:4b9d95435555eb88a379f0eba4a323084dde0711c906a4dbc65790cbd2da76fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AQZLYLHOLDHJDQ73OE5MWIIPTS","target":"graph","payload":{"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"},"verdict_id":"1437b69b-781e-422f-b556-67a3d56d6ac4"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T01:03:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pIpFoQF6av64fgI4jFxsCKMTVLoNpaoj9lXGIUaHaLqK0lNyiuQQSmDI+29cnsimdbby13JMGHDuvtQE7RD4Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T23:58:33.381766Z"},"content_sha256":"215b645af37dbe1aebc497286735a1969e879d52c71ca5305f43f6f3c93c4998","schema_version":"1.0","event_id":"sha256:215b645af37dbe1aebc497286735a1969e879d52c71ca5305f43f6f3c93c4998"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AQZLYLHOLDHJDQ73OE5MWIIPTS/bundle.json","state_url":"https://pith.science/pith/AQZLYLHOLDHJDQ73OE5MWIIPTS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AQZLYLHOLDHJDQ73OE5MWIIPTS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-02T23:58:33Z","links":{"resolver":"https://pith.science/pith/AQZLYLHOLDHJDQ73OE5MWIIPTS","bundle":"https://pith.science/pith/AQZLYLHOLDHJDQ73OE5MWIIPTS/bundle.json","state":"https://pith.science/pith/AQZLYLHOLDHJDQ73OE5MWIIPTS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AQZLYLHOLDHJDQ73OE5MWIIPTS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AQZLYLHOLDHJDQ73OE5MWIIPTS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"676828eb599c82787e70d879d5be1b9078b18f36b3bebe32ce9e00128b2cb323","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-23T12:16:41Z","title_canon_sha256":"4df7e32150b77cd9747f6830b14f5e201a60620f782f396b9495efd6d9fb6f5a"},"schema_version":"1.0","source":{"id":"2510.20477","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.20477","created_at":"2026-05-26T01:03:17Z"},{"alias_kind":"arxiv_version","alias_value":"2510.20477v3","created_at":"2026-05-26T01:03:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.20477","created_at":"2026-05-26T01:03:17Z"},{"alias_kind":"pith_short_12","alias_value":"AQZLYLHOLDHJ","created_at":"2026-05-26T01:03:17Z"},{"alias_kind":"pith_short_16","alias_value":"AQZLYLHOLDHJDQ73","created_at":"2026-05-26T01:03:17Z"},{"alias_kind":"pith_short_8","alias_value":"AQZLYLHO","created_at":"2026-05-26T01:03:17Z"}],"graph_snapshots":[{"event_id":"sha256:215b645af37dbe1aebc497286735a1969e879d52c71ca5305f43f6f3c93c4998","target":"graph","created_at":"2026-05-26T01:03:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Bi-CoG produces higher-quality pseudo-labels for vision-language models by checking consistency both across models and inside a single model."}],"snapshot_sha256":"af0952d0e81abc451dc05103234a78c1ed22fa1ee32fbc54fa43aecedce86449"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"b6e8e26d98dca957144a0d4a831dc88a15e618dd0030369dddf3665f8a92456f"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2510.20477/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Lan-Zhe Guo, Rui Zhu, Song-Lin Lv, Zi-Kang Wang","cross_cats":[],"headline":"Bi-CoG produces higher-quality pseudo-labels for vision-language models by checking consistency both across models and inside a single model.","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-23T12:16:41Z","title":"Bi-CoG: Bi-Consistency-Guided Self-Training for Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.20477","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-18T04:55:53.717476Z","id":"1437b69b-781e-422f-b556-67a3d56d6ac4","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"1437b69b-781e-422f-b556-67a3d56d6ac4"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4b9d95435555eb88a379f0eba4a323084dde0711c906a4dbc65790cbd2da76fc","target":"record","created_at":"2026-05-26T01:03:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"676828eb599c82787e70d879d5be1b9078b18f36b3bebe32ce9e00128b2cb323","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-23T12:16:41Z","title_canon_sha256":"4df7e32150b77cd9747f6830b14f5e201a60620f782f396b9495efd6d9fb6f5a"},"schema_version":"1.0","source":{"id":"2510.20477","kind":"arxiv","version":3}},"canonical_sha256":"0432bc2cee58ce91c3fb713acb210f9ca7d72e08153d7d8f965a45970ec64d5a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0432bc2cee58ce91c3fb713acb210f9ca7d72e08153d7d8f965a45970ec64d5a","first_computed_at":"2026-05-26T01:03:17.164579Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:17.164579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XL88kdvMxRZtcAl2Gto7nLfN1Us1LJUPJkLJaSomjZUHAmpJOT8hgGDVdyPN+RG44gZN3/b2sZzfZ+b4lVCjDw==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:17.165117Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.20477","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b9d95435555eb88a379f0eba4a323084dde0711c906a4dbc65790cbd2da76fc","sha256:215b645af37dbe1aebc497286735a1969e879d52c71ca5305f43f6f3c93c4998"],"state_sha256":"cd4fbb8e76d0f0932faa26042e2d3f04c3108ff2381e16b707d23590fd4df0c2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MjA4yjS5olDWZz5Mw7bTiTVMlEAl41/frOSJQduxGoxtd/lgdYunWogbVDnmFqdww2OnrwZvwh9uSJBFCpZHDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T23:58:33.384073Z","bundle_sha256":"4bd65b277cce29cf0bebe83e1d58d6c9d3a412bb4d640ad024213436e5b147b2"}}