{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JKAGFNVOXQYDMJ34TVSYBZUZCZ","short_pith_number":"pith:JKAGFNVO","canonical_record":{"source":{"id":"2406.09415","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8e1612a2449dadcf17cabe62e5bf8a6d00674c5a8d735a0a7ed1d4f46459f9b1","abstract_canon_sha256":"ec821e9cfab4aed0a030b30c0551fabd5143539b4e7d9ddd020907413798bda4"},"schema_version":"1.0"},"canonical_sha256":"4a8062b6aebc3036277c9d6580e699166d8ac8c8685e4cc70b55384bb05fed86","source":{"kind":"arxiv","id":"2406.09415","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09415","created_at":"2026-07-05T10:30:54Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09415v2","created_at":"2026-07-05T10:30:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09415","created_at":"2026-07-05T10:30:54Z"},{"alias_kind":"pith_short_12","alias_value":"JKAGFNVOXQYD","created_at":"2026-07-05T10:30:54Z"},{"alias_kind":"pith_short_16","alias_value":"JKAGFNVOXQYDMJ34","created_at":"2026-07-05T10:30:54Z"},{"alias_kind":"pith_short_8","alias_value":"JKAGFNVO","created_at":"2026-07-05T10:30:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JKAGFNVOXQYDMJ34TVSYBZUZCZ","target":"record","payload":{"canonical_record":{"source":{"id":"2406.09415","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8e1612a2449dadcf17cabe62e5bf8a6d00674c5a8d735a0a7ed1d4f46459f9b1","abstract_canon_sha256":"ec821e9cfab4aed0a030b30c0551fabd5143539b4e7d9ddd020907413798bda4"},"schema_version":"1.0"},"canonical_sha256":"4a8062b6aebc3036277c9d6580e699166d8ac8c8685e4cc70b55384bb05fed86","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:54.076713Z","signature_b64":"BNni2/OL+3jGpcTB/3YoO8XVdYVQ8OHSQd7yI8rh1lO2/FLJLU45WlA68fHWE8UjMDnbYF0WSnjPFCABEshbDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a8062b6aebc3036277c9d6580e699166d8ac8c8685e4cc70b55384bb05fed86","last_reissued_at":"2026-07-05T10:30:54.076014Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:54.076014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.09415","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:30:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l+OhlIrj6wz5rnT5sta9fEpwXYmCVqPrHdAvxWXLmV8FlJ1DWMO61/gZsoURMhH0CvYNSfpalza/xTSlqVLKDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:43:43.764606Z"},"content_sha256":"b180d41b7b81eaa2a076d53fe0ee718f03a7bb2a14772ab6832870aad01cd970","schema_version":"1.0","event_id":"sha256:b180d41b7b81eaa2a076d53fe0ee718f03a7bb2a14772ab6832870aad01cd970"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JKAGFNVOXQYDMJ34TVSYBZUZCZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Cees G. M. Snoek, Duy-Kien Nguyen, Mahmoud Assran, Martin R. Oswald, Unnat Jain, Xinlei Chen","submitted_at":"2024-06-13T17:59:58Z","abstract_excerpt":"This work does not introduce a new method. Instead, we present an interesting finding that questions the necessity of the inductive bias of locality in modern computer vision architectures. Concretely, we find that vanilla Transformers can operate by directly treating each individual pixel as a token and achieve highly performant results. This is substantially different from the popular design in Vision Transformer, which maintains the inductive bias from ConvNets towards local neighborhoods (e.g. by treating each 16x16 patch as a token). We showcase the effectiveness of pixels-as-tokens acros"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09415","kind":"arxiv","version":2},"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/2406.09415/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":"2026-07-05T10:30:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ermc7nv0e4axcajGkyAsrDadpujsFk4uZoIEZpLFv2dgY/auKN97qVBzzuTrqoh6nKCzjwRp1I9E33JodIe8DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T18:43:43.765183Z"},"content_sha256":"62530870ec3298dc4530b0635b94b46d9acbce22e2dea788a50d28177156a2a7","schema_version":"1.0","event_id":"sha256:62530870ec3298dc4530b0635b94b46d9acbce22e2dea788a50d28177156a2a7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JKAGFNVOXQYDMJ34TVSYBZUZCZ/bundle.json","state_url":"https://pith.science/pith/JKAGFNVOXQYDMJ34TVSYBZUZCZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JKAGFNVOXQYDMJ34TVSYBZUZCZ/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":"2026-08-10T18:43:43Z","links":{"resolver":"https://pith.science/pith/JKAGFNVOXQYDMJ34TVSYBZUZCZ","bundle":"https://pith.science/pith/JKAGFNVOXQYDMJ34TVSYBZUZCZ/bundle.json","state":"https://pith.science/pith/JKAGFNVOXQYDMJ34TVSYBZUZCZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JKAGFNVOXQYDMJ34TVSYBZUZCZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JKAGFNVOXQYDMJ34TVSYBZUZCZ","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":"ec821e9cfab4aed0a030b30c0551fabd5143539b4e7d9ddd020907413798bda4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:58Z","title_canon_sha256":"8e1612a2449dadcf17cabe62e5bf8a6d00674c5a8d735a0a7ed1d4f46459f9b1"},"schema_version":"1.0","source":{"id":"2406.09415","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.09415","created_at":"2026-07-05T10:30:54Z"},{"alias_kind":"arxiv_version","alias_value":"2406.09415v2","created_at":"2026-07-05T10:30:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09415","created_at":"2026-07-05T10:30:54Z"},{"alias_kind":"pith_short_12","alias_value":"JKAGFNVOXQYD","created_at":"2026-07-05T10:30:54Z"},{"alias_kind":"pith_short_16","alias_value":"JKAGFNVOXQYDMJ34","created_at":"2026-07-05T10:30:54Z"},{"alias_kind":"pith_short_8","alias_value":"JKAGFNVO","created_at":"2026-07-05T10:30:54Z"}],"graph_snapshots":[{"event_id":"sha256:62530870ec3298dc4530b0635b94b46d9acbce22e2dea788a50d28177156a2a7","target":"graph","created_at":"2026-07-05T10:30:54Z","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/2406.09415/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This work does not introduce a new method. Instead, we present an interesting finding that questions the necessity of the inductive bias of locality in modern computer vision architectures. Concretely, we find that vanilla Transformers can operate by directly treating each individual pixel as a token and achieve highly performant results. This is substantially different from the popular design in Vision Transformer, which maintains the inductive bias from ConvNets towards local neighborhoods (e.g. by treating each 16x16 patch as a token). We showcase the effectiveness of pixels-as-tokens acros","authors_text":"Cees G. M. Snoek, Duy-Kien Nguyen, Mahmoud Assran, Martin R. Oswald, Unnat Jain, Xinlei Chen","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:58Z","title":"An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09415","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:b180d41b7b81eaa2a076d53fe0ee718f03a7bb2a14772ab6832870aad01cd970","target":"record","created_at":"2026-07-05T10:30:54Z","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":"ec821e9cfab4aed0a030b30c0551fabd5143539b4e7d9ddd020907413798bda4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:58Z","title_canon_sha256":"8e1612a2449dadcf17cabe62e5bf8a6d00674c5a8d735a0a7ed1d4f46459f9b1"},"schema_version":"1.0","source":{"id":"2406.09415","kind":"arxiv","version":2}},"canonical_sha256":"4a8062b6aebc3036277c9d6580e699166d8ac8c8685e4cc70b55384bb05fed86","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a8062b6aebc3036277c9d6580e699166d8ac8c8685e4cc70b55384bb05fed86","first_computed_at":"2026-07-05T10:30:54.076014Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:30:54.076014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BNni2/OL+3jGpcTB/3YoO8XVdYVQ8OHSQd7yI8rh1lO2/FLJLU45WlA68fHWE8UjMDnbYF0WSnjPFCABEshbDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:30:54.076713Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.09415","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b180d41b7b81eaa2a076d53fe0ee718f03a7bb2a14772ab6832870aad01cd970","sha256:62530870ec3298dc4530b0635b94b46d9acbce22e2dea788a50d28177156a2a7"],"state_sha256":"856da489ae956fc04f165fc14fa26a9dd6529f931f1dc5d30fe1517496af3c98"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bmx8BgpheXFl/lsye4QdLgTvwvir62ExrvM8kCtWO9iDl6yh8JIT1p+JgYkwgBLLCQJbGgNr7S4jDrIQo24SCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T18:43:43.771258Z","bundle_sha256":"8fa663ce0de65b870e31378a813ee2dcf7fe35cb3c1355e4907f660abf865dda"}}