{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4GY6E7E5JZY7PWP5RF4EBD3XPJ","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":"362f2f1c000d3dad72daa1ea1f494f386579fec102e286a6d3d3ac1d253d3403","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-10T11:53:46Z","title_canon_sha256":"0c3243e48ce3f2d6ee74bbdda702c2e52b101a08a401c2951698b06ae6316935"},"schema_version":"1.0","source":{"id":"2501.05901","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.05901","created_at":"2026-07-05T09:59:59Z"},{"alias_kind":"arxiv_version","alias_value":"2501.05901v2","created_at":"2026-07-05T09:59:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05901","created_at":"2026-07-05T09:59:59Z"},{"alias_kind":"pith_short_12","alias_value":"4GY6E7E5JZY7","created_at":"2026-07-05T09:59:59Z"},{"alias_kind":"pith_short_16","alias_value":"4GY6E7E5JZY7PWP5","created_at":"2026-07-05T09:59:59Z"},{"alias_kind":"pith_short_8","alias_value":"4GY6E7E5","created_at":"2026-07-05T09:59:59Z"}],"graph_snapshots":[{"event_id":"sha256:d760ba2c491c69d5e84e4cfe2fc73db0e778fb24ed77edfaeee66cf8fb34ac04","target":"graph","created_at":"2026-07-05T09:59:59Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.05901/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Can Zhang, Haoran Lin, Minghui Qiu, Ruipu Luo, Xian Wang, Yuan Gao, Zhenghao Chen, Zhentao He, Ziheng Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-10T11:53:46Z","title":"Valley2: Exploring Multimodal Models with Scalable Vision-Language Design"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05901","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e912f6b42331112df79b17c898c5056ec34a553ef5b57d1ed00a14ee65579a45","target":"record","created_at":"2026-07-05T09:59:59Z","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":"362f2f1c000d3dad72daa1ea1f494f386579fec102e286a6d3d3ac1d253d3403","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-10T11:53:46Z","title_canon_sha256":"0c3243e48ce3f2d6ee74bbdda702c2e52b101a08a401c2951698b06ae6316935"},"schema_version":"1.0","source":{"id":"2501.05901","kind":"arxiv","version":2}},"canonical_sha256":"e1b1e27c9d4e71f7d9fd8978408f777a70df6727d9e43e7204e6459cafd2b24b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1b1e27c9d4e71f7d9fd8978408f777a70df6727d9e43e7204e6459cafd2b24b","first_computed_at":"2026-07-05T09:59:59.801856Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:59:59.801856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pBGNc6I15Zoh+3gPHb51swZhhRU0AfrReVMARJkS5AaV08cIMXSgEFOOQxyRZgINgblvb5b2kNBRdq8R4JNVBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:59:59.802263Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.05901","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e912f6b42331112df79b17c898c5056ec34a553ef5b57d1ed00a14ee65579a45","sha256:d760ba2c491c69d5e84e4cfe2fc73db0e778fb24ed77edfaeee66cf8fb34ac04"],"state_sha256":"986f018496f78961a2429a759cc019122658645ceff5e1efba62aa9074c4803b"}