{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Q3PWNCHK42TM77DZP46WUH6U4T","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":"0f17897ce7da2b85278a6c9e0f99401ebb130dd9625d090a50b5a9b7c5d70597","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-10T18:59:58Z","title_canon_sha256":"85a38fb4801ae555617b4b8237dc79632b269c0039831d7415f5f61f879338cf"},"schema_version":"1.0","source":{"id":"2502.06788","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.06788","created_at":"2026-07-05T11:42:25Z"},{"alias_kind":"arxiv_version","alias_value":"2502.06788v2","created_at":"2026-07-05T11:42:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06788","created_at":"2026-07-05T11:42:25Z"},{"alias_kind":"pith_short_12","alias_value":"Q3PWNCHK42TM","created_at":"2026-07-05T11:42:25Z"},{"alias_kind":"pith_short_16","alias_value":"Q3PWNCHK42TM77DZ","created_at":"2026-07-05T11:42:25Z"},{"alias_kind":"pith_short_8","alias_value":"Q3PWNCHK","created_at":"2026-07-05T11:42:25Z"}],"graph_snapshots":[{"event_id":"sha256:9da6c8b49f03f4b37fc2883194a27a1ae3ccc18082a12273d2a71e7e9365b594","target":"graph","created_at":"2026-07-05T11:42:25Z","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/2502.06788/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing encoder-free vision-language models (VLMs) are rapidly narrowing the performance gap with their encoder-based counterparts, highlighting the promising potential for unified multimodal systems with structural simplicity and efficient deployment. We systematically clarify the performance gap between VLMs using pre-trained vision encoders, discrete tokenizers, and minimalist visual layers from scratch, deeply excavating the under-examined characteristics of encoder-free VLMs. We develop efficient strategies for encoder-free VLMs that rival mainstream encoder-based ones. After an in-depth","authors_text":"Haiwen Diao, Haoge Deng, Huchuan Lu, Ting Pan, Wenxuan Wang, Xiaotong Li, Xinlong Wang, Yueze Wang, Yufeng Cui","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-10T18:59:58Z","title":"EVEv2: Improved Baselines for Encoder-Free Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06788","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:d9b059966ddceeb3b0090aa028cb208f07792604e6e47633feab10086ed0b35b","target":"record","created_at":"2026-07-05T11:42:25Z","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":"0f17897ce7da2b85278a6c9e0f99401ebb130dd9625d090a50b5a9b7c5d70597","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-10T18:59:58Z","title_canon_sha256":"85a38fb4801ae555617b4b8237dc79632b269c0039831d7415f5f61f879338cf"},"schema_version":"1.0","source":{"id":"2502.06788","kind":"arxiv","version":2}},"canonical_sha256":"86df6688eae6a6cffc797f3d6a1fd4e4e7fd5d7849365f121303d9be8e01b160","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86df6688eae6a6cffc797f3d6a1fd4e4e7fd5d7849365f121303d9be8e01b160","first_computed_at":"2026-07-05T11:42:25.792942Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:25.792942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fxhXKhqwhNrpfffkyzG9iSBd8jnGBeSyHixCipabN4wGwb+L9lYD/G+Ayj7DlRnVHOplGyFrBtcyRxdBgwq9Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:25.793520Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.06788","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9b059966ddceeb3b0090aa028cb208f07792604e6e47633feab10086ed0b35b","sha256:9da6c8b49f03f4b37fc2883194a27a1ae3ccc18082a12273d2a71e7e9365b594"],"state_sha256":"923c5e90e9130304df139566d5b5be0926a460ff0bfed2102152df8330478530"}