{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:URGVIDG4PHFG5PBAK6M3UNRPWP","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":"adb03c4b0f74aaf326574c600287a7c3184b0d3498d8aa73b26c7aaf6c5b7a69","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T15:08:25Z","title_canon_sha256":"715b17601e942d3af7669c96b819ff601f93c1b9a8370d65aa9d1d03f05504b1"},"schema_version":"1.0","source":{"id":"2412.08443","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08443","created_at":"2026-07-05T09:47:50Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08443v1","created_at":"2026-07-05T09:47:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08443","created_at":"2026-07-05T09:47:50Z"},{"alias_kind":"pith_short_12","alias_value":"URGVIDG4PHFG","created_at":"2026-07-05T09:47:50Z"},{"alias_kind":"pith_short_16","alias_value":"URGVIDG4PHFG5PBA","created_at":"2026-07-05T09:47:50Z"},{"alias_kind":"pith_short_8","alias_value":"URGVIDG4","created_at":"2026-07-05T09:47:50Z"}],"graph_snapshots":[{"event_id":"sha256:e4b0bdda8ddc917332e72ea4c4b61651d97c9fcc386069c2d49b2632e88b5ec2","target":"graph","created_at":"2026-07-05T09:47:50Z","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/2412.08443/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models have made significant strides recently, demonstrating superior performance across a range of tasks, e.g. optical character recognition and complex diagram analysis. Building on this trend, we introduce a new vision-language model, POINTS1.5, designed to excel in various real-world applications. POINTS1.5 is an enhancement of POINTS1.0 and incorporates several key innovations: i) We replace the original CLIP vision encoder, which had a fixed image resolution, with a NaViT-style vision encoder that supports native dynamic high resolution. This allows POINTS1.5 to process i","authors_text":"Jie Zhou, Kavio Yu, Le Tian, Xiao Zhou, Xinyu Gao, Yang Yu, Yuan Liu","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T15:08:25Z","title":"POINTS1.5: Building a Vision-Language Model towards Real World Applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08443","kind":"arxiv","version":1},"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:e47e203b419e02d8187cc0569c20bddb0560504e74fdd57373a36d3d08dfca0c","target":"record","created_at":"2026-07-05T09:47:50Z","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":"adb03c4b0f74aaf326574c600287a7c3184b0d3498d8aa73b26c7aaf6c5b7a69","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T15:08:25Z","title_canon_sha256":"715b17601e942d3af7669c96b819ff601f93c1b9a8370d65aa9d1d03f05504b1"},"schema_version":"1.0","source":{"id":"2412.08443","kind":"arxiv","version":1}},"canonical_sha256":"a44d540cdc79ca6ebc205799ba362fb3ef66224238cdb07fddf3b1ec2c4b0891","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a44d540cdc79ca6ebc205799ba362fb3ef66224238cdb07fddf3b1ec2c4b0891","first_computed_at":"2026-07-05T09:47:50.241363Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:47:50.241363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aiSMr0fZPTFwzSV87JIM0mU+VSgre1rTv7PUIwNCHzhP3lL04jyH6FR68fMIX9A8haWmTYXluHCAgdVKN3ZcBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:47:50.241812Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.08443","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e47e203b419e02d8187cc0569c20bddb0560504e74fdd57373a36d3d08dfca0c","sha256:e4b0bdda8ddc917332e72ea4c4b61651d97c9fcc386069c2d49b2632e88b5ec2"],"state_sha256":"ab568feba730218f808c1b049b73367f9983ac70e4f8a1946b05e3e6ebfcf537"}