{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:O5U6WR22GCOGXXZLHTIOPUTMR4","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":"255859b11957126f10750d6b5974b419f7b48c949c5b978b935bee55428759be","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-14T17:50:20Z","title_canon_sha256":"30adc8979bed256356a6b86c926dd1c3c7ade2ce12dd99f6e610020eb8e6974a"},"schema_version":"1.0","source":{"id":"2504.10462","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.10462","created_at":"2026-07-05T10:49:00Z"},{"alias_kind":"arxiv_version","alias_value":"2504.10462v1","created_at":"2026-07-05T10:49:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.10462","created_at":"2026-07-05T10:49:00Z"},{"alias_kind":"pith_short_12","alias_value":"O5U6WR22GCOG","created_at":"2026-07-05T10:49:00Z"},{"alias_kind":"pith_short_16","alias_value":"O5U6WR22GCOGXXZL","created_at":"2026-07-05T10:49:00Z"},{"alias_kind":"pith_short_8","alias_value":"O5U6WR22","created_at":"2026-07-05T10:49:00Z"}],"graph_snapshots":[{"event_id":"sha256:b0766c8c06beb493cab6e3f53adedc603b5bc70ac4a46434ee586a85034de5f7","target":"graph","created_at":"2026-07-05T10:49:00Z","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/2504.10462/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces SAIL, a single transformer unified multimodal large language model (MLLM) that integrates raw pixel encoding and language decoding within a singular architecture. Unlike existing modular MLLMs, which rely on a pre-trained vision transformer (ViT), SAIL eliminates the need for a separate vision encoder, presenting a more minimalist architecture design. Instead of introducing novel architectural components, SAIL adapts mix-attention mechanisms and multimodal positional encodings to better align with the distinct characteristics of visual and textual modalities. We systemati","authors_text":"Haochen Wang, Jiacong Wang, Jiashi Feng, Jun Hao Liew, Weixian Lei, Xiangtai Li, Zilong Huang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-14T17:50:20Z","title":"The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.10462","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:db87e5235a34f19ce5237a99ecd745a02ce39de63ab8a15b35f9d4913fb7ee5c","target":"record","created_at":"2026-07-05T10:49:00Z","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":"255859b11957126f10750d6b5974b419f7b48c949c5b978b935bee55428759be","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-14T17:50:20Z","title_canon_sha256":"30adc8979bed256356a6b86c926dd1c3c7ade2ce12dd99f6e610020eb8e6974a"},"schema_version":"1.0","source":{"id":"2504.10462","kind":"arxiv","version":1}},"canonical_sha256":"7769eb475a309c6bdf2b3cd0e7d26c8f087508e2812c7c56742264e85a109b77","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7769eb475a309c6bdf2b3cd0e7d26c8f087508e2812c7c56742264e85a109b77","first_computed_at":"2026-07-05T10:49:00.866717Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:49:00.866717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fAd5WoxzSdPGlImG2ZX/8pKme2RXkGnsLsPKAp943hRfXR7kBT6ENlvFSmZWxMaja81HFi16no0Kqm/VNHM7DA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:49:00.867204Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.10462","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db87e5235a34f19ce5237a99ecd745a02ce39de63ab8a15b35f9d4913fb7ee5c","sha256:b0766c8c06beb493cab6e3f53adedc603b5bc70ac4a46434ee586a85034de5f7"],"state_sha256":"68702dfe63b0856a92945334e77e0803db457bb0ae2182884ac494e4a5c3f92e"}