{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6NTWXY6IO7AMGC62V3XNVDAQZZ","short_pith_number":"pith:6NTWXY6I","schema_version":"1.0","canonical_sha256":"f3676be3c877c0c30bdaaeeeda8c10ce482c111d7142f990c0f05e77325f275d","source":{"kind":"arxiv","id":"2501.05952","version":3},"attestation_state":"computed","paper":{"title":"Scalable Vision Language Model Training via High Quality Data Curation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chao Feng, Hongyuan Dong, Jiao Ran, Weijie Yin, Xiao Liang, Zijian Kang","submitted_at":"2025-01-10T13:27:04Z","abstract_excerpt":"In this paper, we introduce SAIL-VL (ScAlable Vision Language Model TraIning via High QuaLity Data Curation), an open-source vision language model (VLM) series achieving state-of-the-art (SOTA) performance in 2B and 8B parameters. The following three key improvements contribute to SAIL-VL's leading performance: (1) Scalable high-quality visual understanding data construction: We implement a data construction pipeline to enable hundred-million-scale high-quality recaption data annotation. The resulted dataset SAIL-Caption is validated to be of the highest data quality compared with opensource d"},"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":"2501.05952","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-10T13:27:04Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"978148afe866e59fcf188ca6fb7ded784baf2740c0050a7f4754af35580f846d","abstract_canon_sha256":"6d66b8527c5d6f70e5185daae3c9c8a4f5f7e0189908c6846077c60692af3fee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:16.928511Z","signature_b64":"kP5+UHacefNnTpUWuQwpCK0LXy8rD7i+tpYUfj3hL8KBE6UO5Z1XELtsIYzVlW601DFQB1Rgu5MUbmgDGbWxAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3676be3c877c0c30bdaaeeeda8c10ce482c111d7142f990c0f05e77325f275d","last_reissued_at":"2026-07-05T11:18:16.928006Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:16.928006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable Vision Language Model Training via High Quality Data Curation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Chao Feng, Hongyuan Dong, Jiao Ran, Weijie Yin, Xiao Liang, Zijian Kang","submitted_at":"2025-01-10T13:27:04Z","abstract_excerpt":"In this paper, we introduce SAIL-VL (ScAlable Vision Language Model TraIning via High QuaLity Data Curation), an open-source vision language model (VLM) series achieving state-of-the-art (SOTA) performance in 2B and 8B parameters. The following three key improvements contribute to SAIL-VL's leading performance: (1) Scalable high-quality visual understanding data construction: We implement a data construction pipeline to enable hundred-million-scale high-quality recaption data annotation. The resulted dataset SAIL-Caption is validated to be of the highest data quality compared with opensource d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05952","kind":"arxiv","version":3},"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/2501.05952/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":"2501.05952","created_at":"2026-07-05T11:18:16.928067+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.05952v3","created_at":"2026-07-05T11:18:16.928067+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05952","created_at":"2026-07-05T11:18:16.928067+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NTWXY6IO7AM","created_at":"2026-07-05T11:18:16.928067+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NTWXY6IO7AMGC62","created_at":"2026-07-05T11:18:16.928067+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NTWXY6I","created_at":"2026-07-05T11:18:16.928067+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26196","citing_title":"From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models","ref_index":231,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20280","citing_title":"ELVA: Exploring Ranking-Driven Universal Multimodal Retrieval","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2503.02597","citing_title":"Seeing is Understanding: Unlocking Causal Attention into Modality-Mutual Attention for Multimodal LLMs","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2505.16416","citing_title":"Circle-RoPE: Cone-like Decoupled Rotary Positional Embedding for Large Vision-Language Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2511.14159","citing_title":"MVI-Bench: A Comprehensive Benchmark for Evaluating Robustness to Misleading Visual Inputs in LVLMs","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2506.11991","citing_title":"VGR: Visual Grounded Reasoning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2506.20670","citing_title":"MMSearch-R1: Incentivizing LMMs to Search","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09271","citing_title":"Shaping Schema via Language Representation as the Next Frontier for LLM Intelligence Expanding","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03547","citing_title":"Erase Persona, Forget Lore: Benchmarking Multimodal Copyright Unlearning in Large Vision Language Models","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16557","citing_title":"S-GRPO: Unified Post-Training for Large Vision-Language Models","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6NTWXY6IO7AMGC62V3XNVDAQZZ","json":"https://pith.science/pith/6NTWXY6IO7AMGC62V3XNVDAQZZ.json","graph_json":"https://pith.science/api/pith-number/6NTWXY6IO7AMGC62V3XNVDAQZZ/graph.json","events_json":"https://pith.science/api/pith-number/6NTWXY6IO7AMGC62V3XNVDAQZZ/events.json","paper":"https://pith.science/paper/6NTWXY6I"},"agent_actions":{"view_html":"https://pith.science/pith/6NTWXY6IO7AMGC62V3XNVDAQZZ","download_json":"https://pith.science/pith/6NTWXY6IO7AMGC62V3XNVDAQZZ.json","view_paper":"https://pith.science/paper/6NTWXY6I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.05952&json=true","fetch_graph":"https://pith.science/api/pith-number/6NTWXY6IO7AMGC62V3XNVDAQZZ/graph.json","fetch_events":"https://pith.science/api/pith-number/6NTWXY6IO7AMGC62V3XNVDAQZZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NTWXY6IO7AMGC62V3XNVDAQZZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NTWXY6IO7AMGC62V3XNVDAQZZ/action/storage_attestation","attest_author":"https://pith.science/pith/6NTWXY6IO7AMGC62V3XNVDAQZZ/action/author_attestation","sign_citation":"https://pith.science/pith/6NTWXY6IO7AMGC62V3XNVDAQZZ/action/citation_signature","submit_replication":"https://pith.science/pith/6NTWXY6IO7AMGC62V3XNVDAQZZ/action/replication_record"}},"created_at":"2026-07-05T11:18:16.928067+00:00","updated_at":"2026-07-05T11:18:16.928067+00:00"}