{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4GY6E7E5JZY7PWP5RF4EBD3XPJ","short_pith_number":"pith:4GY6E7E5","schema_version":"1.0","canonical_sha256":"e1b1e27c9d4e71f7d9fd8978408f777a70df6727d9e43e7204e6459cafd2b24b","source":{"kind":"arxiv","id":"2501.05901","version":2},"attestation_state":"computed","paper":{"title":"Valley2: Exploring Multimodal Models with Scalable Vision-Language Design","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Can Zhang, Haoran Lin, Minghui Qiu, Ruipu Luo, Xian Wang, Yuan Gao, Zhenghao Chen, Zhentao He, Ziheng Wu","submitted_at":"2025-01-10T11:53:46Z","abstract_excerpt":"Recently, vision-language models have made remarkable progress, demonstrating outstanding capabilities in various tasks such as image captioning and video understanding. We introduce Valley2, a novel multimodal large language model designed to enhance performance across all domains and extend the boundaries of practical applications in e-commerce and short video scenarios. Notably, Valley2 achieves state-of-the-art (SOTA) performance on e-commerce benchmarks, surpassing open-source models of similar size by a large margin (79.66 vs. 72.76). Additionally, Valley2 ranks second on the OpenCompass"},"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":"2501.05901","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-10T11:53:46Z","cross_cats_sorted":[],"title_canon_sha256":"0c3243e48ce3f2d6ee74bbdda702c2e52b101a08a401c2951698b06ae6316935","abstract_canon_sha256":"362f2f1c000d3dad72daa1ea1f494f386579fec102e286a6d3d3ac1d253d3403"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:59.802263Z","signature_b64":"pBGNc6I15Zoh+3gPHb51swZhhRU0AfrReVMARJkS5AaV08cIMXSgEFOOQxyRZgINgblvb5b2kNBRdq8R4JNVBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1b1e27c9d4e71f7d9fd8978408f777a70df6727d9e43e7204e6459cafd2b24b","last_reissued_at":"2026-07-05T09:59:59.801856Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:59.801856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Valley2: Exploring Multimodal Models with Scalable Vision-Language Design","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Can Zhang, Haoran Lin, Minghui Qiu, Ruipu Luo, Xian Wang, Yuan Gao, Zhenghao Chen, Zhentao He, Ziheng Wu","submitted_at":"2025-01-10T11:53:46Z","abstract_excerpt":"Recently, vision-language models have made remarkable progress, demonstrating outstanding capabilities in various tasks such as image captioning and video understanding. We introduce Valley2, a novel multimodal large language model designed to enhance performance across all domains and extend the boundaries of practical applications in e-commerce and short video scenarios. Notably, Valley2 achieves state-of-the-art (SOTA) performance on e-commerce benchmarks, surpassing open-source models of similar size by a large margin (79.66 vs. 72.76). Additionally, Valley2 ranks second on the OpenCompass"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05901","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/2501.05901/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":"2501.05901","created_at":"2026-07-05T09:59:59.801912+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.05901v2","created_at":"2026-07-05T09:59:59.801912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05901","created_at":"2026-07-05T09:59:59.801912+00:00"},{"alias_kind":"pith_short_12","alias_value":"4GY6E7E5JZY7","created_at":"2026-07-05T09:59:59.801912+00:00"},{"alias_kind":"pith_short_16","alias_value":"4GY6E7E5JZY7PWP5","created_at":"2026-07-05T09:59:59.801912+00:00"},{"alias_kind":"pith_short_8","alias_value":"4GY6E7E5","created_at":"2026-07-05T09:59:59.801912+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31187","citing_title":"Learning to Deny: Action Denial in Multimodal Large Language Models","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01278","citing_title":"Valley3: Scaling Omni Foundation Models for E-commerce","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2501.13106","citing_title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","ref_index":155,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4GY6E7E5JZY7PWP5RF4EBD3XPJ","json":"https://pith.science/pith/4GY6E7E5JZY7PWP5RF4EBD3XPJ.json","graph_json":"https://pith.science/api/pith-number/4GY6E7E5JZY7PWP5RF4EBD3XPJ/graph.json","events_json":"https://pith.science/api/pith-number/4GY6E7E5JZY7PWP5RF4EBD3XPJ/events.json","paper":"https://pith.science/paper/4GY6E7E5"},"agent_actions":{"view_html":"https://pith.science/pith/4GY6E7E5JZY7PWP5RF4EBD3XPJ","download_json":"https://pith.science/pith/4GY6E7E5JZY7PWP5RF4EBD3XPJ.json","view_paper":"https://pith.science/paper/4GY6E7E5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.05901&json=true","fetch_graph":"https://pith.science/api/pith-number/4GY6E7E5JZY7PWP5RF4EBD3XPJ/graph.json","fetch_events":"https://pith.science/api/pith-number/4GY6E7E5JZY7PWP5RF4EBD3XPJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4GY6E7E5JZY7PWP5RF4EBD3XPJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4GY6E7E5JZY7PWP5RF4EBD3XPJ/action/storage_attestation","attest_author":"https://pith.science/pith/4GY6E7E5JZY7PWP5RF4EBD3XPJ/action/author_attestation","sign_citation":"https://pith.science/pith/4GY6E7E5JZY7PWP5RF4EBD3XPJ/action/citation_signature","submit_replication":"https://pith.science/pith/4GY6E7E5JZY7PWP5RF4EBD3XPJ/action/replication_record"}},"created_at":"2026-07-05T09:59:59.801912+00:00","updated_at":"2026-07-05T09:59:59.801912+00:00"}