{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:2LIHOWJIBCM2PZNJGMAGGZAO44","short_pith_number":"pith:2LIHOWJI","canonical_record":{"source":{"id":"2210.09221","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-13T19:53:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ae76ba0600472b39ff898a90afcd6cd013b19d73202aa939f1e1d84d202845e3","abstract_canon_sha256":"813347e97c9dcf5dfaac3695450ef83f0e48612bc17624713af5b952a00b8fd8"},"schema_version":"1.0"},"canonical_sha256":"d2d07759280899a7e5a9330063640ee7117606cb9558567988d306dcbde49450","source":{"kind":"arxiv","id":"2210.09221","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.09221","created_at":"2026-07-05T05:07:20Z"},{"alias_kind":"arxiv_version","alias_value":"2210.09221v1","created_at":"2026-07-05T05:07:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09221","created_at":"2026-07-05T05:07:20Z"},{"alias_kind":"pith_short_12","alias_value":"2LIHOWJIBCM2","created_at":"2026-07-05T05:07:20Z"},{"alias_kind":"pith_short_16","alias_value":"2LIHOWJIBCM2PZNJ","created_at":"2026-07-05T05:07:20Z"},{"alias_kind":"pith_short_8","alias_value":"2LIHOWJI","created_at":"2026-07-05T05:07:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:2LIHOWJIBCM2PZNJGMAGGZAO44","target":"record","payload":{"canonical_record":{"source":{"id":"2210.09221","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-13T19:53:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ae76ba0600472b39ff898a90afcd6cd013b19d73202aa939f1e1d84d202845e3","abstract_canon_sha256":"813347e97c9dcf5dfaac3695450ef83f0e48612bc17624713af5b952a00b8fd8"},"schema_version":"1.0"},"canonical_sha256":"d2d07759280899a7e5a9330063640ee7117606cb9558567988d306dcbde49450","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:07:20.250273Z","signature_b64":"rQ44q6mWQrHOthMMz4HnBmDfbmLZ1sJ7lfA6x/gAnGHd+9ilkSbWpDFgTvFcq2TM9jUZ8tRFKldg7J6nQPy5Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2d07759280899a7e5a9330063640ee7117606cb9558567988d306dcbde49450","last_reissued_at":"2026-07-05T05:07:20.249909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:07:20.249909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.09221","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":"2026-07-05T05:07:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kUh4N8v6Srf3MlF1f1wjZ0SRs+iMk3Jot1GZC379fGAyiBHN6Q7YZ0VR4TsOl8HGwSxvZgT5U3NnUE1SEdZKDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:41:02.337853Z"},"content_sha256":"101d597739f1134f3f831c83801344c25d45324b43fc74fa146b00b4f71de170","schema_version":"1.0","event_id":"sha256:101d597739f1134f3f831c83801344c25d45324b43fc74fa146b00b4f71de170"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:2LIHOWJIBCM2PZNJGMAGGZAO44","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vision Transformers provably learn spatial structure","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Michael E. Sander, Samy Jelassi, Yuanzhi Li","submitted_at":"2022-10-13T19:53:56Z","abstract_excerpt":"Vision Transformers (ViTs) have achieved comparable or superior performance than Convolutional Neural Networks (CNNs) in computer vision. This empirical breakthrough is even more remarkable since, in contrast to CNNs, ViTs do not embed any visual inductive bias of spatial locality. Yet, recent works have shown that while minimizing their training loss, ViTs specifically learn spatially localized patterns. This raises a central question: how do ViTs learn these patterns by solely minimizing their training loss using gradient-based methods from random initialization? In this paper, we provide so"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09221","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/2210.09221/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":"2026-07-05T05:07:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z3prquUCaXuFLugzfWL8k5OEM1Q4NFFL/aAg5hgpw475OjXrEJXh1SbUkfqyaObOB+d/ecJTl2u2Ch45PQL6AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:41:02.338364Z"},"content_sha256":"67f4072b1326230e88198041d8201c888fb7027fcb022c095521fe238e3cd430","schema_version":"1.0","event_id":"sha256:67f4072b1326230e88198041d8201c888fb7027fcb022c095521fe238e3cd430"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2LIHOWJIBCM2PZNJGMAGGZAO44/bundle.json","state_url":"https://pith.science/pith/2LIHOWJIBCM2PZNJGMAGGZAO44/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2LIHOWJIBCM2PZNJGMAGGZAO44/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":"2026-08-08T19:41:02Z","links":{"resolver":"https://pith.science/pith/2LIHOWJIBCM2PZNJGMAGGZAO44","bundle":"https://pith.science/pith/2LIHOWJIBCM2PZNJGMAGGZAO44/bundle.json","state":"https://pith.science/pith/2LIHOWJIBCM2PZNJGMAGGZAO44/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2LIHOWJIBCM2PZNJGMAGGZAO44/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2LIHOWJIBCM2PZNJGMAGGZAO44","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":"813347e97c9dcf5dfaac3695450ef83f0e48612bc17624713af5b952a00b8fd8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-13T19:53:56Z","title_canon_sha256":"ae76ba0600472b39ff898a90afcd6cd013b19d73202aa939f1e1d84d202845e3"},"schema_version":"1.0","source":{"id":"2210.09221","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.09221","created_at":"2026-07-05T05:07:20Z"},{"alias_kind":"arxiv_version","alias_value":"2210.09221v1","created_at":"2026-07-05T05:07:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09221","created_at":"2026-07-05T05:07:20Z"},{"alias_kind":"pith_short_12","alias_value":"2LIHOWJIBCM2","created_at":"2026-07-05T05:07:20Z"},{"alias_kind":"pith_short_16","alias_value":"2LIHOWJIBCM2PZNJ","created_at":"2026-07-05T05:07:20Z"},{"alias_kind":"pith_short_8","alias_value":"2LIHOWJI","created_at":"2026-07-05T05:07:20Z"}],"graph_snapshots":[{"event_id":"sha256:67f4072b1326230e88198041d8201c888fb7027fcb022c095521fe238e3cd430","target":"graph","created_at":"2026-07-05T05:07:20Z","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/2210.09221/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision Transformers (ViTs) have achieved comparable or superior performance than Convolutional Neural Networks (CNNs) in computer vision. This empirical breakthrough is even more remarkable since, in contrast to CNNs, ViTs do not embed any visual inductive bias of spatial locality. Yet, recent works have shown that while minimizing their training loss, ViTs specifically learn spatially localized patterns. This raises a central question: how do ViTs learn these patterns by solely minimizing their training loss using gradient-based methods from random initialization? In this paper, we provide so","authors_text":"Michael E. Sander, Samy Jelassi, Yuanzhi Li","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-13T19:53:56Z","title":"Vision Transformers provably learn spatial structure"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09221","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":"sha256:101d597739f1134f3f831c83801344c25d45324b43fc74fa146b00b4f71de170","target":"record","created_at":"2026-07-05T05:07:20Z","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":"813347e97c9dcf5dfaac3695450ef83f0e48612bc17624713af5b952a00b8fd8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-13T19:53:56Z","title_canon_sha256":"ae76ba0600472b39ff898a90afcd6cd013b19d73202aa939f1e1d84d202845e3"},"schema_version":"1.0","source":{"id":"2210.09221","kind":"arxiv","version":1}},"canonical_sha256":"d2d07759280899a7e5a9330063640ee7117606cb9558567988d306dcbde49450","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2d07759280899a7e5a9330063640ee7117606cb9558567988d306dcbde49450","first_computed_at":"2026-07-05T05:07:20.249909Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:07:20.249909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rQ44q6mWQrHOthMMz4HnBmDfbmLZ1sJ7lfA6x/gAnGHd+9ilkSbWpDFgTvFcq2TM9jUZ8tRFKldg7J6nQPy5Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:07:20.250273Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.09221","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:101d597739f1134f3f831c83801344c25d45324b43fc74fa146b00b4f71de170","sha256:67f4072b1326230e88198041d8201c888fb7027fcb022c095521fe238e3cd430"],"state_sha256":"67caf4e5b2d02b5b3a2aa06ce0ae16859be4e2a933c6c85ac7f2a5c7cf150021"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BxpjYZkFOhvUdcm2YjOhscWN1i3a9hfePGfA+cRZVncZ3JO82FUBIWrFXIWEtBqKPGdXR9bJ2mPFYDlJn6WJAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:41:02.342472Z","bundle_sha256":"ea07b7dd26bf023178481f8d370f84cd623c610256c61edbaf9075c2d25f54e0"}}