{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4DNVR5PKOXSMAG75I6FWVP2ATK","short_pith_number":"pith:4DNVR5PK","schema_version":"1.0","canonical_sha256":"e0db58f5ea75e4c01bfd478b6abf409a978a7981eabf42f100c78398a746d768","source":{"kind":"arxiv","id":"2409.04828","version":3},"attestation_state":"computed","paper":{"title":"POINTS: Improving Your Vision-language Model with Affordable Strategies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Jie Zhou, Le Tian, Xiao Zhou, Yuan Liu, Zhongyin Zhao, Ziyuan Zhuang","submitted_at":"2024-09-07T13:41:37Z","abstract_excerpt":"In recent years, vision-language models have made significant strides, excelling in tasks like optical character recognition and geometric problem-solving. However, several critical issues remain: 1) Proprietary models often lack transparency about their architectures, while open-source models need more detailed ablations of their training strategies. 2) Pre-training data in open-source works is under-explored, with datasets added empirically, making the process cumbersome. 3) Fine-tuning often focuses on adding datasets, leading to diminishing returns. To address these issues, we propose the "},"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":"2409.04828","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-07T13:41:37Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"59568ae7dce7d6cd2cbcd0a402ba3abac73c8f8c770479438f90a0a7b476851d","abstract_canon_sha256":"da499418522e494429f70cc7eed01ce79c973a4dc4497ebb4a673129a53932a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:07.861393Z","signature_b64":"sAFmxvxODZRYG6ofHe2rd9nkV43Y/8E+CCjiDa3Clr+3nEo71qrhX03tDyapQrVNryjTOYCQx95MbyJY96AjDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0db58f5ea75e4c01bfd478b6abf409a978a7981eabf42f100c78398a746d768","last_reissued_at":"2026-07-05T09:31:07.860893Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:07.860893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"POINTS: Improving Your Vision-language Model with Affordable Strategies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Jie Zhou, Le Tian, Xiao Zhou, Yuan Liu, Zhongyin Zhao, Ziyuan Zhuang","submitted_at":"2024-09-07T13:41:37Z","abstract_excerpt":"In recent years, vision-language models have made significant strides, excelling in tasks like optical character recognition and geometric problem-solving. However, several critical issues remain: 1) Proprietary models often lack transparency about their architectures, while open-source models need more detailed ablations of their training strategies. 2) Pre-training data in open-source works is under-explored, with datasets added empirically, making the process cumbersome. 3) Fine-tuning often focuses on adding datasets, leading to diminishing returns. To address these issues, we propose the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.04828","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/2409.04828/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":"2409.04828","created_at":"2026-07-05T09:31:07.860952+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.04828v3","created_at":"2026-07-05T09:31:07.860952+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.04828","created_at":"2026-07-05T09:31:07.860952+00:00"},{"alias_kind":"pith_short_12","alias_value":"4DNVR5PKOXSM","created_at":"2026-07-05T09:31:07.860952+00:00"},{"alias_kind":"pith_short_16","alias_value":"4DNVR5PKOXSMAG75","created_at":"2026-07-05T09:31:07.860952+00:00"},{"alias_kind":"pith_short_8","alias_value":"4DNVR5PK","created_at":"2026-07-05T09:31:07.860952+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"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":55,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11627","citing_title":"POINTS-Long: Adaptive Dual-Mode Visual Reasoning in MLLMs","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05271","citing_title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","ref_index":157,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4DNVR5PKOXSMAG75I6FWVP2ATK","json":"https://pith.science/pith/4DNVR5PKOXSMAG75I6FWVP2ATK.json","graph_json":"https://pith.science/api/pith-number/4DNVR5PKOXSMAG75I6FWVP2ATK/graph.json","events_json":"https://pith.science/api/pith-number/4DNVR5PKOXSMAG75I6FWVP2ATK/events.json","paper":"https://pith.science/paper/4DNVR5PK"},"agent_actions":{"view_html":"https://pith.science/pith/4DNVR5PKOXSMAG75I6FWVP2ATK","download_json":"https://pith.science/pith/4DNVR5PKOXSMAG75I6FWVP2ATK.json","view_paper":"https://pith.science/paper/4DNVR5PK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.04828&json=true","fetch_graph":"https://pith.science/api/pith-number/4DNVR5PKOXSMAG75I6FWVP2ATK/graph.json","fetch_events":"https://pith.science/api/pith-number/4DNVR5PKOXSMAG75I6FWVP2ATK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4DNVR5PKOXSMAG75I6FWVP2ATK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4DNVR5PKOXSMAG75I6FWVP2ATK/action/storage_attestation","attest_author":"https://pith.science/pith/4DNVR5PKOXSMAG75I6FWVP2ATK/action/author_attestation","sign_citation":"https://pith.science/pith/4DNVR5PKOXSMAG75I6FWVP2ATK/action/citation_signature","submit_replication":"https://pith.science/pith/4DNVR5PKOXSMAG75I6FWVP2ATK/action/replication_record"}},"created_at":"2026-07-05T09:31:07.860952+00:00","updated_at":"2026-07-05T09:31:07.860952+00:00"}