{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:A7WUKPZLVJRMYTSZWTPLHNFRSB","short_pith_number":"pith:A7WUKPZL","canonical_record":{"source":{"id":"2402.17863","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-27T19:54:42Z","cross_cats_sorted":[],"title_canon_sha256":"037583f3c7391b09522ada73fa12a32657774b8332004386c51d163002871c50","abstract_canon_sha256":"784e80dc2032ff53eac38cab862cf8747708cd0cf3d910f2349c1b0e02eefd32"},"schema_version":"1.0"},"canonical_sha256":"07ed453f2baa62cc4e59b4deb3b4b19049b6d37cc8dc588efc356f59170bc03d","source":{"kind":"arxiv","id":"2402.17863","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17863","created_at":"2026-07-05T07:50:09Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17863v1","created_at":"2026-07-05T07:50:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17863","created_at":"2026-07-05T07:50:09Z"},{"alias_kind":"pith_short_12","alias_value":"A7WUKPZLVJRM","created_at":"2026-07-05T07:50:09Z"},{"alias_kind":"pith_short_16","alias_value":"A7WUKPZLVJRMYTSZ","created_at":"2026-07-05T07:50:09Z"},{"alias_kind":"pith_short_8","alias_value":"A7WUKPZL","created_at":"2026-07-05T07:50:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:A7WUKPZLVJRMYTSZWTPLHNFRSB","target":"record","payload":{"canonical_record":{"source":{"id":"2402.17863","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-27T19:54:42Z","cross_cats_sorted":[],"title_canon_sha256":"037583f3c7391b09522ada73fa12a32657774b8332004386c51d163002871c50","abstract_canon_sha256":"784e80dc2032ff53eac38cab862cf8747708cd0cf3d910f2349c1b0e02eefd32"},"schema_version":"1.0"},"canonical_sha256":"07ed453f2baa62cc4e59b4deb3b4b19049b6d37cc8dc588efc356f59170bc03d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:50:09.193957Z","signature_b64":"AouWafOs45Dp+GnorfL8kTJyuvjwdsBcL+vijeFEd7tNMfvJNJEXcTvOQNAEtzrhLLjwXt3eHLYF06E9oM4SAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07ed453f2baa62cc4e59b4deb3b4b19049b6d37cc8dc588efc356f59170bc03d","last_reissued_at":"2026-07-05T07:50:09.193609Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:50:09.193609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.17863","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":"2026-07-05T07:50:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vDm8nqvhKf3IQmvDbMpnNWpxsXfDvE4vrPmFoak1m3OKv+c0WfJZqLu9c3huB1dPa2bZRfAYp2hfPtI/Pd3wBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T14:32:36.873513Z"},"content_sha256":"b0625f02c8898a370f5c89363747e1c23f950b7da6f8e480732b9614b150757b","schema_version":"1.0","event_id":"sha256:b0625f02c8898a370f5c89363747e1c23f950b7da6f8e480732b9614b150757b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:A7WUKPZLVJRMYTSZWTPLHNFRSB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vision Transformers with Natural Language Semantics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guillermo Sapiro, J. Mat\\'ias Di Martino, Young Kyung Kim","submitted_at":"2024-02-27T19:54:42Z","abstract_excerpt":"Tokens or patches within Vision Transformers (ViT) lack essential semantic information, unlike their counterparts in natural language processing (NLP). Typically, ViT tokens are associated with rectangular image patches that lack specific semantic context, making interpretation difficult and failing to effectively encapsulate information. We introduce a novel transformer model, Semantic Vision Transformers (sViT), which leverages recent progress on segmentation models to design novel tokenizer strategies. sViT effectively harnesses semantic information, creating an inductive bias reminiscent o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17863","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/2402.17863/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":"2026-07-05T07:50:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7ab2OqfFy+2rfpkG3hcmRfsnE5xc7e+RH0Hev96Xlu46docKmH/xiNgFGnmg7Uzp3e44sxjPwaHtb7oVVzoVDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T14:32:36.875175Z"},"content_sha256":"e57f07e02da3be8d5ede065d826568fc9fd86ca803f0398e2a82206cd0d4763c","schema_version":"1.0","event_id":"sha256:e57f07e02da3be8d5ede065d826568fc9fd86ca803f0398e2a82206cd0d4763c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A7WUKPZLVJRMYTSZWTPLHNFRSB/bundle.json","state_url":"https://pith.science/pith/A7WUKPZLVJRMYTSZWTPLHNFRSB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A7WUKPZLVJRMYTSZWTPLHNFRSB/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":"2026-08-13T14:32:36Z","links":{"resolver":"https://pith.science/pith/A7WUKPZLVJRMYTSZWTPLHNFRSB","bundle":"https://pith.science/pith/A7WUKPZLVJRMYTSZWTPLHNFRSB/bundle.json","state":"https://pith.science/pith/A7WUKPZLVJRMYTSZWTPLHNFRSB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A7WUKPZLVJRMYTSZWTPLHNFRSB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:A7WUKPZLVJRMYTSZWTPLHNFRSB","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":"784e80dc2032ff53eac38cab862cf8747708cd0cf3d910f2349c1b0e02eefd32","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-27T19:54:42Z","title_canon_sha256":"037583f3c7391b09522ada73fa12a32657774b8332004386c51d163002871c50"},"schema_version":"1.0","source":{"id":"2402.17863","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17863","created_at":"2026-07-05T07:50:09Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17863v1","created_at":"2026-07-05T07:50:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17863","created_at":"2026-07-05T07:50:09Z"},{"alias_kind":"pith_short_12","alias_value":"A7WUKPZLVJRM","created_at":"2026-07-05T07:50:09Z"},{"alias_kind":"pith_short_16","alias_value":"A7WUKPZLVJRMYTSZ","created_at":"2026-07-05T07:50:09Z"},{"alias_kind":"pith_short_8","alias_value":"A7WUKPZL","created_at":"2026-07-05T07:50:09Z"}],"graph_snapshots":[{"event_id":"sha256:e57f07e02da3be8d5ede065d826568fc9fd86ca803f0398e2a82206cd0d4763c","target":"graph","created_at":"2026-07-05T07:50:09Z","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/2402.17863/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tokens or patches within Vision Transformers (ViT) lack essential semantic information, unlike their counterparts in natural language processing (NLP). Typically, ViT tokens are associated with rectangular image patches that lack specific semantic context, making interpretation difficult and failing to effectively encapsulate information. We introduce a novel transformer model, Semantic Vision Transformers (sViT), which leverages recent progress on segmentation models to design novel tokenizer strategies. sViT effectively harnesses semantic information, creating an inductive bias reminiscent o","authors_text":"Guillermo Sapiro, J. Mat\\'ias Di Martino, Young Kyung Kim","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-27T19:54:42Z","title":"Vision Transformers with Natural Language Semantics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17863","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:b0625f02c8898a370f5c89363747e1c23f950b7da6f8e480732b9614b150757b","target":"record","created_at":"2026-07-05T07:50:09Z","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":"784e80dc2032ff53eac38cab862cf8747708cd0cf3d910f2349c1b0e02eefd32","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-27T19:54:42Z","title_canon_sha256":"037583f3c7391b09522ada73fa12a32657774b8332004386c51d163002871c50"},"schema_version":"1.0","source":{"id":"2402.17863","kind":"arxiv","version":1}},"canonical_sha256":"07ed453f2baa62cc4e59b4deb3b4b19049b6d37cc8dc588efc356f59170bc03d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07ed453f2baa62cc4e59b4deb3b4b19049b6d37cc8dc588efc356f59170bc03d","first_computed_at":"2026-07-05T07:50:09.193609Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:50:09.193609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AouWafOs45Dp+GnorfL8kTJyuvjwdsBcL+vijeFEd7tNMfvJNJEXcTvOQNAEtzrhLLjwXt3eHLYF06E9oM4SAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:50:09.193957Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.17863","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0625f02c8898a370f5c89363747e1c23f950b7da6f8e480732b9614b150757b","sha256:e57f07e02da3be8d5ede065d826568fc9fd86ca803f0398e2a82206cd0d4763c"],"state_sha256":"44a26ae267e15d2f85d7e6e6b6409416bcd817e5d939040ea5dc076e2754b64c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zecxoTW7tUi9H0hnm4PjEzyS/8GWhfS+JLbq6x4hmZo1zLV+HLqQH6Txb5dMMnwRDlW8dNuQK+lIBLcv5IZdCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T14:32:36.887024Z","bundle_sha256":"72ea757507357742445ce7816a26bb9274e718329bbbdb9d92be301ed326a0ba"}}