{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AO53LN4PRV5BTKBC5TTMWIA47E","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":"4f17bc510856a5d6916f25e05c8a0cc89d1b8a9735e634d0214ae42973ccc8bb","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-12T06:01:05Z","title_canon_sha256":"89c0de1c2072f1a77c5e26565f087207108ca37bcba87f2c6793ec8124a5c789"},"schema_version":"1.0","source":{"id":"2503.14694","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.14694","created_at":"2026-07-05T10:34:22Z"},{"alias_kind":"arxiv_version","alias_value":"2503.14694v1","created_at":"2026-07-05T10:34:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.14694","created_at":"2026-07-05T10:34:22Z"},{"alias_kind":"pith_short_12","alias_value":"AO53LN4PRV5B","created_at":"2026-07-05T10:34:22Z"},{"alias_kind":"pith_short_16","alias_value":"AO53LN4PRV5BTKBC","created_at":"2026-07-05T10:34:22Z"},{"alias_kind":"pith_short_8","alias_value":"AO53LN4P","created_at":"2026-07-05T10:34:22Z"}],"graph_snapshots":[{"event_id":"sha256:6ed57cf40916a2e97a6278a5d1828f3ceaa1a4f7e4a31b16a098665926fc5ab8","target":"graph","created_at":"2026-07-05T10:34:22Z","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/2503.14694/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in large language models (LLMs) have significantly propelled the development of large multi-modal models (LMMs), highlighting the potential for general and intelligent assistants. However, most LMMs model visual and textual modalities separately, leading to recent efforts to develop native LMMs using a single transformer. Despite the promise, these native models are resource-intensive and often exhibit performance gaps compared to their compositional counterparts. To alleviate this issue, we propose a simple yet efficient method to construct a baseline for the native and en","authors_text":"Hengshuang Zhao, Lin Song, Rui Yang, Runhui Huang, Yicheng Xiao, Ying Shan, Yixiao Ge","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-12T06:01:05Z","title":"HaploVL: A Single-Transformer Baseline for Multi-Modal Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.14694","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:cac7c5a9a4fde619397550d498ae5d4622605ceaa790abad64555b802e8c8192","target":"record","created_at":"2026-07-05T10:34:22Z","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":"4f17bc510856a5d6916f25e05c8a0cc89d1b8a9735e634d0214ae42973ccc8bb","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-12T06:01:05Z","title_canon_sha256":"89c0de1c2072f1a77c5e26565f087207108ca37bcba87f2c6793ec8124a5c789"},"schema_version":"1.0","source":{"id":"2503.14694","kind":"arxiv","version":1}},"canonical_sha256":"03bbb5b78f8d7a19a822ece6cb201cf936be0121d91f4055fd55953f1a060c84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03bbb5b78f8d7a19a822ece6cb201cf936be0121d91f4055fd55953f1a060c84","first_computed_at":"2026-07-05T10:34:22.556627Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:34:22.556627Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CjQSNWqxI9urEnxlqxgOoiWpTeWQ888RTPAw9bu0pc9yz7xP69TorztC2CQXnVYvUsnyMNHTxnhDBEelc2p9Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:34:22.557081Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.14694","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cac7c5a9a4fde619397550d498ae5d4622605ceaa790abad64555b802e8c8192","sha256:6ed57cf40916a2e97a6278a5d1828f3ceaa1a4f7e4a31b16a098665926fc5ab8"],"state_sha256":"9ed23cfa57dd36bde3ecdb40aa402f8afd1e717be440e75cb57b433a695fade6"}