{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4DNVR5PKOXSMAG75I6FWVP2ATK","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":"da499418522e494429f70cc7eed01ce79c973a4dc4497ebb4a673129a53932a4","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-07T13:41:37Z","title_canon_sha256":"59568ae7dce7d6cd2cbcd0a402ba3abac73c8f8c770479438f90a0a7b476851d"},"schema_version":"1.0","source":{"id":"2409.04828","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.04828","created_at":"2026-07-05T09:31:07Z"},{"alias_kind":"arxiv_version","alias_value":"2409.04828v3","created_at":"2026-07-05T09:31:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.04828","created_at":"2026-07-05T09:31:07Z"},{"alias_kind":"pith_short_12","alias_value":"4DNVR5PKOXSM","created_at":"2026-07-05T09:31:07Z"},{"alias_kind":"pith_short_16","alias_value":"4DNVR5PKOXSMAG75","created_at":"2026-07-05T09:31:07Z"},{"alias_kind":"pith_short_8","alias_value":"4DNVR5PK","created_at":"2026-07-05T09:31:07Z"}],"graph_snapshots":[{"event_id":"sha256:b3e7eb8a6e6e216817a1c968ab0e3f9067f1be8640930628edc6dd594f05a1b2","target":"graph","created_at":"2026-07-05T09:31:07Z","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/2409.04828/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Jie Zhou, Le Tian, Xiao Zhou, Yuan Liu, Zhongyin Zhao, Ziyuan Zhuang","cross_cats":["cs.AI","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-07T13:41:37Z","title":"POINTS: Improving Your Vision-language Model with Affordable Strategies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.04828","kind":"arxiv","version":3},"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":"sha256:3fb99231e3c0cb9f6ee8c7f87d8796446597a5f415c20cb91ff21a36750386b1","target":"record","created_at":"2026-07-05T09:31:07Z","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":"da499418522e494429f70cc7eed01ce79c973a4dc4497ebb4a673129a53932a4","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-07T13:41:37Z","title_canon_sha256":"59568ae7dce7d6cd2cbcd0a402ba3abac73c8f8c770479438f90a0a7b476851d"},"schema_version":"1.0","source":{"id":"2409.04828","kind":"arxiv","version":3}},"canonical_sha256":"e0db58f5ea75e4c01bfd478b6abf409a978a7981eabf42f100c78398a746d768","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e0db58f5ea75e4c01bfd478b6abf409a978a7981eabf42f100c78398a746d768","first_computed_at":"2026-07-05T09:31:07.860893Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:31:07.860893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sAFmxvxODZRYG6ofHe2rd9nkV43Y/8E+CCjiDa3Clr+3nEo71qrhX03tDyapQrVNryjTOYCQx95MbyJY96AjDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:31:07.861393Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.04828","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3fb99231e3c0cb9f6ee8c7f87d8796446597a5f415c20cb91ff21a36750386b1","sha256:b3e7eb8a6e6e216817a1c968ab0e3f9067f1be8640930628edc6dd594f05a1b2"],"state_sha256":"1a9810b9068c894415e87b3c471efe61dff19ad48b5094e3af1d9e22d0a55bee"}