{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IZGP5YLNZUJ74DTAMOPRZJDGPG","short_pith_number":"pith:IZGP5YLN","canonical_record":{"source":{"id":"2502.10120","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-14T12:40:37Z","cross_cats_sorted":[],"title_canon_sha256":"ed0af3f025f696666d4cdbb520520b751f8a4833e28953d791170f6046bdc590","abstract_canon_sha256":"111de1e260493b2fb0e3d1f8e5f68377bc8548746e8c1b6a45e595ed0f97bb11"},"schema_version":"1.0"},"canonical_sha256":"464cfee16dcd13fe0e60639f1ca46679a3beb3cab30baa81b18a50035f6a133f","source":{"kind":"arxiv","id":"2502.10120","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10120","created_at":"2026-07-05T10:15:26Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10120v2","created_at":"2026-07-05T10:15:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10120","created_at":"2026-07-05T10:15:26Z"},{"alias_kind":"pith_short_12","alias_value":"IZGP5YLNZUJ7","created_at":"2026-07-05T10:15:26Z"},{"alias_kind":"pith_short_16","alias_value":"IZGP5YLNZUJ74DTA","created_at":"2026-07-05T10:15:26Z"},{"alias_kind":"pith_short_8","alias_value":"IZGP5YLN","created_at":"2026-07-05T10:15:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IZGP5YLNZUJ74DTAMOPRZJDGPG","target":"record","payload":{"canonical_record":{"source":{"id":"2502.10120","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-14T12:40:37Z","cross_cats_sorted":[],"title_canon_sha256":"ed0af3f025f696666d4cdbb520520b751f8a4833e28953d791170f6046bdc590","abstract_canon_sha256":"111de1e260493b2fb0e3d1f8e5f68377bc8548746e8c1b6a45e595ed0f97bb11"},"schema_version":"1.0"},"canonical_sha256":"464cfee16dcd13fe0e60639f1ca46679a3beb3cab30baa81b18a50035f6a133f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:26.778939Z","signature_b64":"lPdlMajYtlqYU5vmkuLI3Hog9Tq2GCUQtCoIad/vTG8/MAvT8LblDsGA/VL2eUb0BfAETmVTd0X0OopquKVpAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"464cfee16dcd13fe0e60639f1ca46679a3beb3cab30baa81b18a50035f6a133f","last_reissued_at":"2026-07-05T10:15:26.778450Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:26.778450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.10120","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":"2026-07-05T10:15:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CJc8jE36wI/8ZmOxQXDTMFS7tKep8E1hYTj+Q1eP5hamIj1zwI9HFavEeGTx7NqpkggH1DGkUDJO+40tEQDwDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:11:24.681068Z"},"content_sha256":"63a3a2c9874242f12dc2ccd67f54c79f77b84b2e630f4920c8a6d11e3b232862","schema_version":"1.0","event_id":"sha256:63a3a2c9874242f12dc2ccd67f54c79f77b84b2e630f4920c8a6d11e3b232862"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IZGP5YLNZUJ74DTAMOPRZJDGPG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Compress image to patches for Vision Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Xinfeng Zhao, Yaoru Sun","submitted_at":"2025-02-14T12:40:37Z","abstract_excerpt":"The Vision Transformer (ViT) has made significant strides in the field of computer vision. However, as the depth of the model and the resolution of the input images increase, the computational cost associated with training and running ViT models has surged dramatically. This paper proposes a hybrid model based on CNN and Vision Transformer, named CI2P-ViT. The model incorporates a module called CI2P, which utilizes the CompressAI encoder to compress images and subsequently generates a sequence of patches through a series of convolutions. CI2P can replace the Patch Embedding component in the Vi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10120","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/2502.10120/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":"2026-07-05T10:15:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8OQ6BLu5zhN/pYmfx3HC4As3hzSwrMVDJqz7KB1usq1VS7ZIs7zRcfvLYmCstvKrUWdMWvhk+FV7cJ79ryXrAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:11:24.682624Z"},"content_sha256":"1e96718e637536f59c283151a82c86fcfd5e64ce61f4eb18f88812f872c88871","schema_version":"1.0","event_id":"sha256:1e96718e637536f59c283151a82c86fcfd5e64ce61f4eb18f88812f872c88871"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IZGP5YLNZUJ74DTAMOPRZJDGPG/bundle.json","state_url":"https://pith.science/pith/IZGP5YLNZUJ74DTAMOPRZJDGPG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IZGP5YLNZUJ74DTAMOPRZJDGPG/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":"2026-08-06T19:11:24Z","links":{"resolver":"https://pith.science/pith/IZGP5YLNZUJ74DTAMOPRZJDGPG","bundle":"https://pith.science/pith/IZGP5YLNZUJ74DTAMOPRZJDGPG/bundle.json","state":"https://pith.science/pith/IZGP5YLNZUJ74DTAMOPRZJDGPG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IZGP5YLNZUJ74DTAMOPRZJDGPG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IZGP5YLNZUJ74DTAMOPRZJDGPG","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":"111de1e260493b2fb0e3d1f8e5f68377bc8548746e8c1b6a45e595ed0f97bb11","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-14T12:40:37Z","title_canon_sha256":"ed0af3f025f696666d4cdbb520520b751f8a4833e28953d791170f6046bdc590"},"schema_version":"1.0","source":{"id":"2502.10120","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.10120","created_at":"2026-07-05T10:15:26Z"},{"alias_kind":"arxiv_version","alias_value":"2502.10120v2","created_at":"2026-07-05T10:15:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10120","created_at":"2026-07-05T10:15:26Z"},{"alias_kind":"pith_short_12","alias_value":"IZGP5YLNZUJ7","created_at":"2026-07-05T10:15:26Z"},{"alias_kind":"pith_short_16","alias_value":"IZGP5YLNZUJ74DTA","created_at":"2026-07-05T10:15:26Z"},{"alias_kind":"pith_short_8","alias_value":"IZGP5YLN","created_at":"2026-07-05T10:15:26Z"}],"graph_snapshots":[{"event_id":"sha256:1e96718e637536f59c283151a82c86fcfd5e64ce61f4eb18f88812f872c88871","target":"graph","created_at":"2026-07-05T10:15:26Z","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/2502.10120/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Vision Transformer (ViT) has made significant strides in the field of computer vision. However, as the depth of the model and the resolution of the input images increase, the computational cost associated with training and running ViT models has surged dramatically. This paper proposes a hybrid model based on CNN and Vision Transformer, named CI2P-ViT. The model incorporates a module called CI2P, which utilizes the CompressAI encoder to compress images and subsequently generates a sequence of patches through a series of convolutions. CI2P can replace the Patch Embedding component in the Vi","authors_text":"Xinfeng Zhao, Yaoru Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-14T12:40:37Z","title":"Compress image to patches for Vision Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10120","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":"sha256:63a3a2c9874242f12dc2ccd67f54c79f77b84b2e630f4920c8a6d11e3b232862","target":"record","created_at":"2026-07-05T10:15:26Z","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":"111de1e260493b2fb0e3d1f8e5f68377bc8548746e8c1b6a45e595ed0f97bb11","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-14T12:40:37Z","title_canon_sha256":"ed0af3f025f696666d4cdbb520520b751f8a4833e28953d791170f6046bdc590"},"schema_version":"1.0","source":{"id":"2502.10120","kind":"arxiv","version":2}},"canonical_sha256":"464cfee16dcd13fe0e60639f1ca46679a3beb3cab30baa81b18a50035f6a133f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"464cfee16dcd13fe0e60639f1ca46679a3beb3cab30baa81b18a50035f6a133f","first_computed_at":"2026-07-05T10:15:26.778450Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:15:26.778450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lPdlMajYtlqYU5vmkuLI3Hog9Tq2GCUQtCoIad/vTG8/MAvT8LblDsGA/VL2eUb0BfAETmVTd0X0OopquKVpAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:15:26.778939Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.10120","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63a3a2c9874242f12dc2ccd67f54c79f77b84b2e630f4920c8a6d11e3b232862","sha256:1e96718e637536f59c283151a82c86fcfd5e64ce61f4eb18f88812f872c88871"],"state_sha256":"674e2a0c36591b87fe18cb9a1004f073be6da92c5b05fbbc955d5b350a80bf14"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BcwlTbbpJonwFVtC6kWCHfbLJEzAdkEcRFvkAB/xAyH8hJnzoP7hDq2cSSnmCy12kKHJYnYDPZ7sYNOUAX/2Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T19:11:24.688689Z","bundle_sha256":"a2e2bc0d06f7d96fcc364d24a6a7fda6a2e0cd3d545ebaa2e6798af60ddd8131"}}