{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FRY23P3V2NZE5GNCF3WV3OUKA2","short_pith_number":"pith:FRY23P3V","canonical_record":{"source":{"id":"2404.01139","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T14:34:47Z","cross_cats_sorted":[],"title_canon_sha256":"c34b0f7e6be977acc9374140f919e5eb875aca93ba0fa01fc541f96972dd792f","abstract_canon_sha256":"28ee1977053aeeaa26569cff557a9aabecc1dd6c24e36bc8cdfcf21fea164598"},"schema_version":"1.0"},"canonical_sha256":"2c71adbf75d3724e99a22eed5dba8a06aeca9b620803f1ee6707a9df0fa184f2","source":{"kind":"arxiv","id":"2404.01139","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.01139","created_at":"2026-07-05T08:03:01Z"},{"alias_kind":"arxiv_version","alias_value":"2404.01139v1","created_at":"2026-07-05T08:03:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01139","created_at":"2026-07-05T08:03:01Z"},{"alias_kind":"pith_short_12","alias_value":"FRY23P3V2NZE","created_at":"2026-07-05T08:03:01Z"},{"alias_kind":"pith_short_16","alias_value":"FRY23P3V2NZE5GNC","created_at":"2026-07-05T08:03:01Z"},{"alias_kind":"pith_short_8","alias_value":"FRY23P3V","created_at":"2026-07-05T08:03:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FRY23P3V2NZE5GNCF3WV3OUKA2","target":"record","payload":{"canonical_record":{"source":{"id":"2404.01139","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T14:34:47Z","cross_cats_sorted":[],"title_canon_sha256":"c34b0f7e6be977acc9374140f919e5eb875aca93ba0fa01fc541f96972dd792f","abstract_canon_sha256":"28ee1977053aeeaa26569cff557a9aabecc1dd6c24e36bc8cdfcf21fea164598"},"schema_version":"1.0"},"canonical_sha256":"2c71adbf75d3724e99a22eed5dba8a06aeca9b620803f1ee6707a9df0fa184f2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:01.358910Z","signature_b64":"lW7CsTyCapVFmPE8orgN4R9V0k/ikEgP1mqaM4WYa1e9wZ483sBoiNK0+Yj7OHzoNZ7+ECKrgJtXIeiZZR5HDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c71adbf75d3724e99a22eed5dba8a06aeca9b620803f1ee6707a9df0fa184f2","last_reissued_at":"2026-07-05T08:03:01.358380Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:01.358380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.01139","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":"2026-07-05T08:03:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cvt5U2/9yG6KgPd/YFPHEdQ7CjZN06TD56lYmNS7FysGtUHeVfoYbd1GnKeoj76aj6pLpS4eIH24h3nbZ3lKCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T08:18:43.461720Z"},"content_sha256":"257c83fb6bf4fa1372fe52c8fd35cdfeefad8c8dc0c4aaf9f3389e2383ff9488","schema_version":"1.0","event_id":"sha256:257c83fb6bf4fa1372fe52c8fd35cdfeefad8c8dc0c4aaf9f3389e2383ff9488"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FRY23P3V2NZE5GNCF3WV3OUKA2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Structured Initialization for Attention in Vision Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianqiao Zheng, Simon Lucey, Xueqian Li","submitted_at":"2024-04-01T14:34:47Z","abstract_excerpt":"The training of vision transformer (ViT) networks on small-scale datasets poses a significant challenge. By contrast, convolutional neural networks (CNNs) have an architectural inductive bias enabling them to perform well on such problems. In this paper, we argue that the architectural bias inherent to CNNs can be reinterpreted as an initialization bias within ViT. This insight is significant as it empowers ViTs to perform equally well on small-scale problems while maintaining their flexibility for large-scale applications. Our inspiration for this ``structured'' initialization stems from our "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01139","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/2404.01139/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":"2026-07-05T08:03:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wdnHIFeFAFOr1WeXMNxcTrg55k7HiebEZ/dt8vqED1SkAs4HcKeFrdwuDh888PUMz7c6ZF+NYO15ANa4CcJeAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T08:18:43.462218Z"},"content_sha256":"8c6be57b1373cb68fa7012bc9a8e9fd1a4fb121290e80b7607d9217414d89586","schema_version":"1.0","event_id":"sha256:8c6be57b1373cb68fa7012bc9a8e9fd1a4fb121290e80b7607d9217414d89586"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FRY23P3V2NZE5GNCF3WV3OUKA2/bundle.json","state_url":"https://pith.science/pith/FRY23P3V2NZE5GNCF3WV3OUKA2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FRY23P3V2NZE5GNCF3WV3OUKA2/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":"2026-08-07T08:18:43Z","links":{"resolver":"https://pith.science/pith/FRY23P3V2NZE5GNCF3WV3OUKA2","bundle":"https://pith.science/pith/FRY23P3V2NZE5GNCF3WV3OUKA2/bundle.json","state":"https://pith.science/pith/FRY23P3V2NZE5GNCF3WV3OUKA2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FRY23P3V2NZE5GNCF3WV3OUKA2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FRY23P3V2NZE5GNCF3WV3OUKA2","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":"28ee1977053aeeaa26569cff557a9aabecc1dd6c24e36bc8cdfcf21fea164598","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T14:34:47Z","title_canon_sha256":"c34b0f7e6be977acc9374140f919e5eb875aca93ba0fa01fc541f96972dd792f"},"schema_version":"1.0","source":{"id":"2404.01139","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.01139","created_at":"2026-07-05T08:03:01Z"},{"alias_kind":"arxiv_version","alias_value":"2404.01139v1","created_at":"2026-07-05T08:03:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01139","created_at":"2026-07-05T08:03:01Z"},{"alias_kind":"pith_short_12","alias_value":"FRY23P3V2NZE","created_at":"2026-07-05T08:03:01Z"},{"alias_kind":"pith_short_16","alias_value":"FRY23P3V2NZE5GNC","created_at":"2026-07-05T08:03:01Z"},{"alias_kind":"pith_short_8","alias_value":"FRY23P3V","created_at":"2026-07-05T08:03:01Z"}],"graph_snapshots":[{"event_id":"sha256:8c6be57b1373cb68fa7012bc9a8e9fd1a4fb121290e80b7607d9217414d89586","target":"graph","created_at":"2026-07-05T08:03:01Z","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/2404.01139/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The training of vision transformer (ViT) networks on small-scale datasets poses a significant challenge. By contrast, convolutional neural networks (CNNs) have an architectural inductive bias enabling them to perform well on such problems. In this paper, we argue that the architectural bias inherent to CNNs can be reinterpreted as an initialization bias within ViT. This insight is significant as it empowers ViTs to perform equally well on small-scale problems while maintaining their flexibility for large-scale applications. Our inspiration for this ``structured'' initialization stems from our ","authors_text":"Jianqiao Zheng, Simon Lucey, Xueqian Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T14:34:47Z","title":"Structured Initialization for Attention in Vision Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01139","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":"sha256:257c83fb6bf4fa1372fe52c8fd35cdfeefad8c8dc0c4aaf9f3389e2383ff9488","target":"record","created_at":"2026-07-05T08:03:01Z","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":"28ee1977053aeeaa26569cff557a9aabecc1dd6c24e36bc8cdfcf21fea164598","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-01T14:34:47Z","title_canon_sha256":"c34b0f7e6be977acc9374140f919e5eb875aca93ba0fa01fc541f96972dd792f"},"schema_version":"1.0","source":{"id":"2404.01139","kind":"arxiv","version":1}},"canonical_sha256":"2c71adbf75d3724e99a22eed5dba8a06aeca9b620803f1ee6707a9df0fa184f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c71adbf75d3724e99a22eed5dba8a06aeca9b620803f1ee6707a9df0fa184f2","first_computed_at":"2026-07-05T08:03:01.358380Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:03:01.358380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lW7CsTyCapVFmPE8orgN4R9V0k/ikEgP1mqaM4WYa1e9wZ483sBoiNK0+Yj7OHzoNZ7+ECKrgJtXIeiZZR5HDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:03:01.358910Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.01139","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:257c83fb6bf4fa1372fe52c8fd35cdfeefad8c8dc0c4aaf9f3389e2383ff9488","sha256:8c6be57b1373cb68fa7012bc9a8e9fd1a4fb121290e80b7607d9217414d89586"],"state_sha256":"a00f863260923602ed330925dccaae902416adf7a9c7f001c31f583ee8b49259"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"32k3Mqax+8uz/rw3VX+HmIQpy8R+vnrM3OUm8ZwwWF5hteshkwtngn6DWPG5jbVCBeO/N8OmjDs0jI8xOFbnBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T08:18:43.466144Z","bundle_sha256":"0f7998648140e9673de571bc8c8c527e4a28fcdee5f014187ed07ddec4310267"}}