{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NBKLQUMEBGLO7BWMB5VPE5L2UU","short_pith_number":"pith:NBKLQUME","schema_version":"1.0","canonical_sha256":"6854b851840996ef86cc0f6af2757aa53b65b9601832c4e8e6e795e112e30c2d","source":{"kind":"arxiv","id":"2411.09420","version":3},"attestation_state":"computed","paper":{"title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jaskaran Singh Walia, Joe Dhanith P R, Shravan Venkatraman","submitted_at":"2024-11-14T13:15:27Z","abstract_excerpt":"Vision Transformers (ViTs) have redefined image classification by leveraging self-attention to capture complex patterns and long-range dependencies between image patches. However, a key challenge for ViTs is efficiently incorporating multi-scale feature representations, which is inherent in convolutional neural networks (CNNs) through their hierarchical structure. Graph transformers have made strides in addressing this by leveraging graph-based modeling, but they often lose or insufficiently represent spatial hierarchies, especially since redundant or less relevant areas dilute the image's con"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2411.09420","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-14T13:15:27Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c8fe453db24b6ebefd6c1dcecde4f904fb3c149b3fbfb2ad6951969df341b10c","abstract_canon_sha256":"7e0cdb521e3e79aa3b62efa855e8d5965cfed37debf5f811de8ceadb1b8e86f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:26.096763Z","signature_b64":"JeyhiG9cmd0W54hh05bMMprgslQSYoXFJ/pucvtvJjMunU3xkfdnbjqGz/S3S4pzyQzjJMByQFFai6b993beCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6854b851840996ef86cc0f6af2757aa53b65b9601832c4e8e6e795e112e30c2d","last_reissued_at":"2026-07-05T09:58:26.096330Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:26.096330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jaskaran Singh Walia, Joe Dhanith P R, Shravan Venkatraman","submitted_at":"2024-11-14T13:15:27Z","abstract_excerpt":"Vision Transformers (ViTs) have redefined image classification by leveraging self-attention to capture complex patterns and long-range dependencies between image patches. However, a key challenge for ViTs is efficiently incorporating multi-scale feature representations, which is inherent in convolutional neural networks (CNNs) through their hierarchical structure. Graph transformers have made strides in addressing this by leveraging graph-based modeling, but they often lose or insufficiently represent spatial hierarchies, especially since redundant or less relevant areas dilute the image's con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09420","kind":"arxiv","version":3},"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/2411.09420/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.09420","created_at":"2026-07-05T09:58:26.096391+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.09420v3","created_at":"2026-07-05T09:58:26.096391+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09420","created_at":"2026-07-05T09:58:26.096391+00:00"},{"alias_kind":"pith_short_12","alias_value":"NBKLQUMEBGLO","created_at":"2026-07-05T09:58:26.096391+00:00"},{"alias_kind":"pith_short_16","alias_value":"NBKLQUMEBGLO7BWM","created_at":"2026-07-05T09:58:26.096391+00:00"},{"alias_kind":"pith_short_8","alias_value":"NBKLQUME","created_at":"2026-07-05T09:58:26.096391+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NBKLQUMEBGLO7BWMB5VPE5L2UU","json":"https://pith.science/pith/NBKLQUMEBGLO7BWMB5VPE5L2UU.json","graph_json":"https://pith.science/api/pith-number/NBKLQUMEBGLO7BWMB5VPE5L2UU/graph.json","events_json":"https://pith.science/api/pith-number/NBKLQUMEBGLO7BWMB5VPE5L2UU/events.json","paper":"https://pith.science/paper/NBKLQUME"},"agent_actions":{"view_html":"https://pith.science/pith/NBKLQUMEBGLO7BWMB5VPE5L2UU","download_json":"https://pith.science/pith/NBKLQUMEBGLO7BWMB5VPE5L2UU.json","view_paper":"https://pith.science/paper/NBKLQUME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.09420&json=true","fetch_graph":"https://pith.science/api/pith-number/NBKLQUMEBGLO7BWMB5VPE5L2UU/graph.json","fetch_events":"https://pith.science/api/pith-number/NBKLQUMEBGLO7BWMB5VPE5L2UU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NBKLQUMEBGLO7BWMB5VPE5L2UU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NBKLQUMEBGLO7BWMB5VPE5L2UU/action/storage_attestation","attest_author":"https://pith.science/pith/NBKLQUMEBGLO7BWMB5VPE5L2UU/action/author_attestation","sign_citation":"https://pith.science/pith/NBKLQUMEBGLO7BWMB5VPE5L2UU/action/citation_signature","submit_replication":"https://pith.science/pith/NBKLQUMEBGLO7BWMB5VPE5L2UU/action/replication_record"}},"created_at":"2026-07-05T09:58:26.096391+00:00","updated_at":"2026-07-05T09:58:26.096391+00:00"}