{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:URGVIDG4PHFG5PBAK6M3UNRPWP","short_pith_number":"pith:URGVIDG4","schema_version":"1.0","canonical_sha256":"a44d540cdc79ca6ebc205799ba362fb3ef66224238cdb07fddf3b1ec2c4b0891","source":{"kind":"arxiv","id":"2412.08443","version":1},"attestation_state":"computed","paper":{"title":"POINTS1.5: Building a Vision-Language Model towards Real World Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Jie Zhou, Kavio Yu, Le Tian, Xiao Zhou, Xinyu Gao, Yang Yu, Yuan Liu","submitted_at":"2024-12-11T15:08:25Z","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"},"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":"2412.08443","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T15:08:25Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"715b17601e942d3af7669c96b819ff601f93c1b9a8370d65aa9d1d03f05504b1","abstract_canon_sha256":"adb03c4b0f74aaf326574c600287a7c3184b0d3498d8aa73b26c7aaf6c5b7a69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:50.241812Z","signature_b64":"aiSMr0fZPTFwzSV87JIM0mU+VSgre1rTv7PUIwNCHzhP3lL04jyH6FR68fMIX9A8haWmTYXluHCAgdVKN3ZcBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a44d540cdc79ca6ebc205799ba362fb3ef66224238cdb07fddf3b1ec2c4b0891","last_reissued_at":"2026-07-05T09:47:50.241363Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:50.241363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"POINTS1.5: Building a Vision-Language Model towards Real World Applications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Jie Zhou, Kavio Yu, Le Tian, Xiao Zhou, Xinyu Gao, Yang Yu, Yuan Liu","submitted_at":"2024-12-11T15:08:25Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08443","kind":"arxiv","version":1},"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/2412.08443/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":"2412.08443","created_at":"2026-07-05T09:47:50.241417+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.08443v1","created_at":"2026-07-05T09:47:50.241417+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08443","created_at":"2026-07-05T09:47:50.241417+00:00"},{"alias_kind":"pith_short_12","alias_value":"URGVIDG4PHFG","created_at":"2026-07-05T09:47:50.241417+00:00"},{"alias_kind":"pith_short_16","alias_value":"URGVIDG4PHFG5PBA","created_at":"2026-07-05T09:47:50.241417+00:00"},{"alias_kind":"pith_short_8","alias_value":"URGVIDG4","created_at":"2026-07-05T09:47:50.241417+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.11627","citing_title":"POINTS-Long: Adaptive Dual-Mode Visual Reasoning in MLLMs","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14029","citing_title":"POINTS-Seeker: An Open Recipe for Multimodal Search Agents with Visual Memory Management","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/URGVIDG4PHFG5PBAK6M3UNRPWP","json":"https://pith.science/pith/URGVIDG4PHFG5PBAK6M3UNRPWP.json","graph_json":"https://pith.science/api/pith-number/URGVIDG4PHFG5PBAK6M3UNRPWP/graph.json","events_json":"https://pith.science/api/pith-number/URGVIDG4PHFG5PBAK6M3UNRPWP/events.json","paper":"https://pith.science/paper/URGVIDG4"},"agent_actions":{"view_html":"https://pith.science/pith/URGVIDG4PHFG5PBAK6M3UNRPWP","download_json":"https://pith.science/pith/URGVIDG4PHFG5PBAK6M3UNRPWP.json","view_paper":"https://pith.science/paper/URGVIDG4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.08443&json=true","fetch_graph":"https://pith.science/api/pith-number/URGVIDG4PHFG5PBAK6M3UNRPWP/graph.json","fetch_events":"https://pith.science/api/pith-number/URGVIDG4PHFG5PBAK6M3UNRPWP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/URGVIDG4PHFG5PBAK6M3UNRPWP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/URGVIDG4PHFG5PBAK6M3UNRPWP/action/storage_attestation","attest_author":"https://pith.science/pith/URGVIDG4PHFG5PBAK6M3UNRPWP/action/author_attestation","sign_citation":"https://pith.science/pith/URGVIDG4PHFG5PBAK6M3UNRPWP/action/citation_signature","submit_replication":"https://pith.science/pith/URGVIDG4PHFG5PBAK6M3UNRPWP/action/replication_record"}},"created_at":"2026-07-05T09:47:50.241417+00:00","updated_at":"2026-07-05T09:47:50.241417+00:00"}