{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:O7QSKCDIU5GUEY56KPQJORHLF3","short_pith_number":"pith:O7QSKCDI","schema_version":"1.0","canonical_sha256":"77e1250868a74d4263be53e09744eb2ed25f5e8aa0e1f9709216c6d96eee9ba9","source":{"kind":"arxiv","id":"2405.19716","version":2},"attestation_state":"computed","paper":{"title":"Enhancing Large Vision Language Models with Self-Training on Image Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Fan Yin, James Zou, Kai-Wei Chang, Pan Lu, Quanquan Gu, Sheng Shen, Wei Wang, Yihe Deng, Ziniu Hu","submitted_at":"2024-05-30T05:53:49Z","abstract_excerpt":"Large vision language models (LVLMs) integrate large language models (LLMs) with pre-trained vision encoders, thereby activating the perception capability of the model to understand image inputs for different queries and conduct subsequent reasoning. Improving this capability requires high-quality vision-language data, which is costly and labor-intensive to acquire. Self-training approaches have been effective in single-modal settings to alleviate the need for labeled data by leveraging model's own generation. However, effective self-training remains a challenge regarding the unique visual per"},"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":"2405.19716","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-30T05:53:49Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"889e9183b3720f237ff9205feafbe9c1e3b50c1720e129015e7254b861f7bfaa","abstract_canon_sha256":"3ee3435cfd812f082277ca2fbcad206419ed50b281f10276fdfc4486efc848f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:23.598810Z","signature_b64":"qdAkZ5TiqlV5H3Zhs19CT7jgxYeTniXhQmGwwdftlc8NrLIqTaHmewC2DqROVWJwbGYBLjSU6ymcZQ4dCUMgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77e1250868a74d4263be53e09744eb2ed25f5e8aa0e1f9709216c6d96eee9ba9","last_reissued_at":"2026-07-05T09:39:23.598308Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:23.598308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Large Vision Language Models with Self-Training on Image Comprehension","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Fan Yin, James Zou, Kai-Wei Chang, Pan Lu, Quanquan Gu, Sheng Shen, Wei Wang, Yihe Deng, Ziniu Hu","submitted_at":"2024-05-30T05:53:49Z","abstract_excerpt":"Large vision language models (LVLMs) integrate large language models (LLMs) with pre-trained vision encoders, thereby activating the perception capability of the model to understand image inputs for different queries and conduct subsequent reasoning. Improving this capability requires high-quality vision-language data, which is costly and labor-intensive to acquire. Self-training approaches have been effective in single-modal settings to alleviate the need for labeled data by leveraging model's own generation. However, effective self-training remains a challenge regarding the unique visual per"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19716","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/2405.19716/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":"2405.19716","created_at":"2026-07-05T09:39:23.598375+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.19716v2","created_at":"2026-07-05T09:39:23.598375+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19716","created_at":"2026-07-05T09:39:23.598375+00:00"},{"alias_kind":"pith_short_12","alias_value":"O7QSKCDIU5GU","created_at":"2026-07-05T09:39:23.598375+00:00"},{"alias_kind":"pith_short_16","alias_value":"O7QSKCDIU5GUEY56","created_at":"2026-07-05T09:39:23.598375+00:00"},{"alias_kind":"pith_short_8","alias_value":"O7QSKCDI","created_at":"2026-07-05T09:39:23.598375+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.10442","citing_title":"Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2502.17419","citing_title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","ref_index":195,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O7QSKCDIU5GUEY56KPQJORHLF3","json":"https://pith.science/pith/O7QSKCDIU5GUEY56KPQJORHLF3.json","graph_json":"https://pith.science/api/pith-number/O7QSKCDIU5GUEY56KPQJORHLF3/graph.json","events_json":"https://pith.science/api/pith-number/O7QSKCDIU5GUEY56KPQJORHLF3/events.json","paper":"https://pith.science/paper/O7QSKCDI"},"agent_actions":{"view_html":"https://pith.science/pith/O7QSKCDIU5GUEY56KPQJORHLF3","download_json":"https://pith.science/pith/O7QSKCDIU5GUEY56KPQJORHLF3.json","view_paper":"https://pith.science/paper/O7QSKCDI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.19716&json=true","fetch_graph":"https://pith.science/api/pith-number/O7QSKCDIU5GUEY56KPQJORHLF3/graph.json","fetch_events":"https://pith.science/api/pith-number/O7QSKCDIU5GUEY56KPQJORHLF3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O7QSKCDIU5GUEY56KPQJORHLF3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O7QSKCDIU5GUEY56KPQJORHLF3/action/storage_attestation","attest_author":"https://pith.science/pith/O7QSKCDIU5GUEY56KPQJORHLF3/action/author_attestation","sign_citation":"https://pith.science/pith/O7QSKCDIU5GUEY56KPQJORHLF3/action/citation_signature","submit_replication":"https://pith.science/pith/O7QSKCDIU5GUEY56KPQJORHLF3/action/replication_record"}},"created_at":"2026-07-05T09:39:23.598375+00:00","updated_at":"2026-07-05T09:39:23.598375+00:00"}