{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:O5U6WR22GCOGXXZLHTIOPUTMR4","short_pith_number":"pith:O5U6WR22","canonical_record":{"source":{"id":"2504.10462","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-14T17:50:20Z","cross_cats_sorted":[],"title_canon_sha256":"30adc8979bed256356a6b86c926dd1c3c7ade2ce12dd99f6e610020eb8e6974a","abstract_canon_sha256":"255859b11957126f10750d6b5974b419f7b48c949c5b978b935bee55428759be"},"schema_version":"1.0"},"canonical_sha256":"7769eb475a309c6bdf2b3cd0e7d26c8f087508e2812c7c56742264e85a109b77","source":{"kind":"arxiv","id":"2504.10462","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:O5U6WR22GCOGXXZLHTIOPUTMR4","target":"record","payload":{"canonical_record":{"source":{"id":"2504.10462","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-14T17:50:20Z","cross_cats_sorted":[],"title_canon_sha256":"30adc8979bed256356a6b86c926dd1c3c7ade2ce12dd99f6e610020eb8e6974a","abstract_canon_sha256":"255859b11957126f10750d6b5974b419f7b48c949c5b978b935bee55428759be"},"schema_version":"1.0"},"canonical_sha256":"7769eb475a309c6bdf2b3cd0e7d26c8f087508e2812c7c56742264e85a109b77","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:00.867204Z","signature_b64":"fAd5WoxzSdPGlImG2ZX/8pKme2RXkGnsLsPKAp943hRfXR7kBT6ENlvFSmZWxMaja81HFi16no0Kqm/VNHM7DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7769eb475a309c6bdf2b3cd0e7d26c8f087508e2812c7c56742264e85a109b77","last_reissued_at":"2026-07-05T10:49:00.866717Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:00.866717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.10462","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:49:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g4dTZ/Togk76Je6/MenPEdUYF6GWi8Icrjs4EhT5RN+kYnm8PnLKRXhBoCEWIajuty0PqxmNhDO0RPMUGzweCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:51:29.862098Z"},"content_sha256":"db87e5235a34f19ce5237a99ecd745a02ce39de63ab8a15b35f9d4913fb7ee5c","schema_version":"1.0","event_id":"sha256:db87e5235a34f19ce5237a99ecd745a02ce39de63ab8a15b35f9d4913fb7ee5c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:O5U6WR22GCOGXXZLHTIOPUTMR4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haochen Wang, Jiacong Wang, Jiashi Feng, Jun Hao Liew, Weixian Lei, Xiangtai Li, Zilong Huang","submitted_at":"2025-04-14T17:50:20Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.10462","kind":"arxiv","version":1},"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/2504.10462/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:49:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vPhjwdHQq24pw7eockUZ9fw9hNJuMEIqPJAd68JtYGuzeu/46GY79MDDBmbxXmPvGa2KpKfKrJo3Px5TVnXNAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:51:29.862815Z"},"content_sha256":"b0766c8c06beb493cab6e3f53adedc603b5bc70ac4a46434ee586a85034de5f7","schema_version":"1.0","event_id":"sha256:b0766c8c06beb493cab6e3f53adedc603b5bc70ac4a46434ee586a85034de5f7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O5U6WR22GCOGXXZLHTIOPUTMR4/bundle.json","state_url":"https://pith.science/pith/O5U6WR22GCOGXXZLHTIOPUTMR4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O5U6WR22GCOGXXZLHTIOPUTMR4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T21:51:29Z","links":{"resolver":"https://pith.science/pith/O5U6WR22GCOGXXZLHTIOPUTMR4","bundle":"https://pith.science/pith/O5U6WR22GCOGXXZLHTIOPUTMR4/bundle.json","state":"https://pith.science/pith/O5U6WR22GCOGXXZLHTIOPUTMR4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O5U6WR22GCOGXXZLHTIOPUTMR4/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0M3nCEDzyANCG0pqUzP5ScM6h2Tp5IY+mAUePx4WTtBduRNEd8Q11svtQzWmRdAfoJxsgCPlcOS2zQganfBiAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T21:51:29.868935Z","bundle_sha256":"a2238e4f0691c6b70392b201ae2a1ae052fa34d754d57bb4bcf86ceacfc20c7f"}}