{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:XMZVLXKTHMNHGPMEX7K6UBQWLA","short_pith_number":"pith:XMZVLXKT","canonical_record":{"source":{"id":"2108.08810","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-19T17:27:03Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"7f0f50e2be6644a0a9fee99546427ed12bd93f06232dc5894a53da95a84a3968","abstract_canon_sha256":"d8386dc13ff99ffa0c89b5229b712155d1e16ccf02bd34367c101eabe8f321b7"},"schema_version":"1.0"},"canonical_sha256":"bb3355dd533b1a733d84bfd5ea061658020702365ed9c37737a3609182849017","source":{"kind":"arxiv","id":"2108.08810","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.08810","created_at":"2026-07-05T04:01:56Z"},{"alias_kind":"arxiv_version","alias_value":"2108.08810v2","created_at":"2026-07-05T04:01:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.08810","created_at":"2026-07-05T04:01:56Z"},{"alias_kind":"pith_short_12","alias_value":"XMZVLXKTHMNH","created_at":"2026-07-05T04:01:56Z"},{"alias_kind":"pith_short_16","alias_value":"XMZVLXKTHMNHGPME","created_at":"2026-07-05T04:01:56Z"},{"alias_kind":"pith_short_8","alias_value":"XMZVLXKT","created_at":"2026-07-05T04:01:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:XMZVLXKTHMNHGPMEX7K6UBQWLA","target":"record","payload":{"canonical_record":{"source":{"id":"2108.08810","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-19T17:27:03Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"7f0f50e2be6644a0a9fee99546427ed12bd93f06232dc5894a53da95a84a3968","abstract_canon_sha256":"d8386dc13ff99ffa0c89b5229b712155d1e16ccf02bd34367c101eabe8f321b7"},"schema_version":"1.0"},"canonical_sha256":"bb3355dd533b1a733d84bfd5ea061658020702365ed9c37737a3609182849017","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:01:56.538535Z","signature_b64":"+xZoXE9fdrYJPP6OCAk4N24tQQFmGAJc3IKcT0uZmtdegnfXgcanSFsdIEKYmSN4KHcnF6cVo1Mkl722gbvDCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb3355dd533b1a733d84bfd5ea061658020702365ed9c37737a3609182849017","last_reissued_at":"2026-07-05T04:01:56.538040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:01:56.538040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.08810","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":"2026-07-05T04:01:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8CMod70NPNHZVgMrn3F1+A6HGai9lgkXlLDpB5WIiITNPhWoblLA8IBbdF+36VJQS/gXh6hUk2v2mGPhHeODDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:14:00.141089Z"},"content_sha256":"63ca6fbc39fa9308a2517bfbdde41f253e115267a437e5b34a92462de09c015f","schema_version":"1.0","event_id":"sha256:63ca6fbc39fa9308a2517bfbdde41f253e115267a437e5b34a92462de09c015f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:XMZVLXKTHMNHGPMEX7K6UBQWLA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do Vision Transformers See Like Convolutional Neural Networks?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Alexey Dosovitskiy, Chiyuan Zhang, Maithra Raghu, Simon Kornblith, Thomas Unterthiner","submitted_at":"2021-08-19T17:27:03Z","abstract_excerpt":"Convolutional neural networks (CNNs) have so far been the de-facto model for visual data. Recent work has shown that (Vision) Transformer models (ViT) can achieve comparable or even superior performance on image classification tasks. This raises a central question: how are Vision Transformers solving these tasks? Are they acting like convolutional networks, or learning entirely different visual representations? Analyzing the internal representation structure of ViTs and CNNs on image classification benchmarks, we find striking differences between the two architectures, such as ViT having more "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.08810","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/2108.08810/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":"2026-07-05T04:01:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EuMnfGqU3zxiuENvBmwLo6Ln8WZhUrIbcJoa5Epx8aL+T1yGUyolXpsIcpgRBEIpxbXAsKsaTZYlz4QgP4L4BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:14:00.141485Z"},"content_sha256":"9dae99e698c27daa0aafdd38008b1d2a9b32e42ef5519fe363c40fd8396b3e0f","schema_version":"1.0","event_id":"sha256:9dae99e698c27daa0aafdd38008b1d2a9b32e42ef5519fe363c40fd8396b3e0f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XMZVLXKTHMNHGPMEX7K6UBQWLA/bundle.json","state_url":"https://pith.science/pith/XMZVLXKTHMNHGPMEX7K6UBQWLA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XMZVLXKTHMNHGPMEX7K6UBQWLA/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":"2026-07-06T16:14:00Z","links":{"resolver":"https://pith.science/pith/XMZVLXKTHMNHGPMEX7K6UBQWLA","bundle":"https://pith.science/pith/XMZVLXKTHMNHGPMEX7K6UBQWLA/bundle.json","state":"https://pith.science/pith/XMZVLXKTHMNHGPMEX7K6UBQWLA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XMZVLXKTHMNHGPMEX7K6UBQWLA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:XMZVLXKTHMNHGPMEX7K6UBQWLA","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":"d8386dc13ff99ffa0c89b5229b712155d1e16ccf02bd34367c101eabe8f321b7","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-19T17:27:03Z","title_canon_sha256":"7f0f50e2be6644a0a9fee99546427ed12bd93f06232dc5894a53da95a84a3968"},"schema_version":"1.0","source":{"id":"2108.08810","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.08810","created_at":"2026-07-05T04:01:56Z"},{"alias_kind":"arxiv_version","alias_value":"2108.08810v2","created_at":"2026-07-05T04:01:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.08810","created_at":"2026-07-05T04:01:56Z"},{"alias_kind":"pith_short_12","alias_value":"XMZVLXKTHMNH","created_at":"2026-07-05T04:01:56Z"},{"alias_kind":"pith_short_16","alias_value":"XMZVLXKTHMNHGPME","created_at":"2026-07-05T04:01:56Z"},{"alias_kind":"pith_short_8","alias_value":"XMZVLXKT","created_at":"2026-07-05T04:01:56Z"}],"graph_snapshots":[{"event_id":"sha256:9dae99e698c27daa0aafdd38008b1d2a9b32e42ef5519fe363c40fd8396b3e0f","target":"graph","created_at":"2026-07-05T04:01:56Z","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/2108.08810/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Convolutional neural networks (CNNs) have so far been the de-facto model for visual data. Recent work has shown that (Vision) Transformer models (ViT) can achieve comparable or even superior performance on image classification tasks. This raises a central question: how are Vision Transformers solving these tasks? Are they acting like convolutional networks, or learning entirely different visual representations? Analyzing the internal representation structure of ViTs and CNNs on image classification benchmarks, we find striking differences between the two architectures, such as ViT having more ","authors_text":"Alexey Dosovitskiy, Chiyuan Zhang, Maithra Raghu, Simon Kornblith, Thomas Unterthiner","cross_cats":["cs.AI","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-19T17:27:03Z","title":"Do Vision Transformers See Like Convolutional Neural Networks?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.08810","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":"sha256:63ca6fbc39fa9308a2517bfbdde41f253e115267a437e5b34a92462de09c015f","target":"record","created_at":"2026-07-05T04:01:56Z","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":"d8386dc13ff99ffa0c89b5229b712155d1e16ccf02bd34367c101eabe8f321b7","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-19T17:27:03Z","title_canon_sha256":"7f0f50e2be6644a0a9fee99546427ed12bd93f06232dc5894a53da95a84a3968"},"schema_version":"1.0","source":{"id":"2108.08810","kind":"arxiv","version":2}},"canonical_sha256":"bb3355dd533b1a733d84bfd5ea061658020702365ed9c37737a3609182849017","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb3355dd533b1a733d84bfd5ea061658020702365ed9c37737a3609182849017","first_computed_at":"2026-07-05T04:01:56.538040Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:01:56.538040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+xZoXE9fdrYJPP6OCAk4N24tQQFmGAJc3IKcT0uZmtdegnfXgcanSFsdIEKYmSN4KHcnF6cVo1Mkl722gbvDCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:01:56.538535Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.08810","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63ca6fbc39fa9308a2517bfbdde41f253e115267a437e5b34a92462de09c015f","sha256:9dae99e698c27daa0aafdd38008b1d2a9b32e42ef5519fe363c40fd8396b3e0f"],"state_sha256":"7ad9eb7e42c8a42f4e8de14595ecccc6d184faf2c19ae5ba2531d8f6b5f74af5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TPa36NXzMYLfaWHlapyJjZrGnQCDmzKjJRoEk4EZo2J8ogBUUa+Xys1tKki/8cZxcj4pPosj1WcYLEGoffPiCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T16:14:00.143477Z","bundle_sha256":"6764cf3fbb7688995d2157dd4137374141720e6d7f048780b6c9d170e5fdfed9"}}