{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XXPUVHHWM4E322U6NX7BMXGL7S","short_pith_number":"pith:XXPUVHHW","schema_version":"1.0","canonical_sha256":"bddf4a9cf66709bd6a9e6dfe165ccbfc9221385a1c34552a61341768fd9b8463","source":{"kind":"arxiv","id":"2412.18778","version":1},"attestation_state":"computed","paper":{"title":"Unified Local and Global Attention Interaction Modeling 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":"Corey Toler-Franklin, Coy D. Heldermon, Tan Nguyen","submitted_at":"2024-12-25T04:53:19Z","abstract_excerpt":"We present a novel method that extends the self-attention mechanism of a vision transformer (ViT) for more accurate object detection across diverse datasets. ViTs show strong capability for image understanding tasks such as object detection, segmentation, and classification. This is due in part to their ability to leverage global information from interactions among visual tokens. However, the self-attention mechanism in ViTs are limited because they do not allow visual tokens to exchange local or global information with neighboring features before computing global attention. This is problemati"},"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":"2412.18778","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-25T04:53:19Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d57670c4b58348ab97e7b61f62ea9db7e63674f08566ac7f926d2a819f7c6adf","abstract_canon_sha256":"44a45aabd5b0bee2852a7f05b984987e9ad2cdde40045c7c8f5e213d4af784be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:10.691553Z","signature_b64":"gGqVs1erH3kyk4A0klY4sHna34D5qCqacI8FRWTGEJLMHp4G6WLC3x0s+t9o4rFhPjR7G3RS4njZ3pkg5CJpDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bddf4a9cf66709bd6a9e6dfe165ccbfc9221385a1c34552a61341768fd9b8463","last_reissued_at":"2026-07-05T09:54:10.691028Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:10.691028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unified Local and Global Attention Interaction Modeling 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":"Corey Toler-Franklin, Coy D. Heldermon, Tan Nguyen","submitted_at":"2024-12-25T04:53:19Z","abstract_excerpt":"We present a novel method that extends the self-attention mechanism of a vision transformer (ViT) for more accurate object detection across diverse datasets. ViTs show strong capability for image understanding tasks such as object detection, segmentation, and classification. This is due in part to their ability to leverage global information from interactions among visual tokens. However, the self-attention mechanism in ViTs are limited because they do not allow visual tokens to exchange local or global information with neighboring features before computing global attention. This is problemati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18778","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/2412.18778/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":"2412.18778","created_at":"2026-07-05T09:54:10.691082+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18778v1","created_at":"2026-07-05T09:54:10.691082+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18778","created_at":"2026-07-05T09:54:10.691082+00:00"},{"alias_kind":"pith_short_12","alias_value":"XXPUVHHWM4E3","created_at":"2026-07-05T09:54:10.691082+00:00"},{"alias_kind":"pith_short_16","alias_value":"XXPUVHHWM4E322U6","created_at":"2026-07-05T09:54:10.691082+00:00"},{"alias_kind":"pith_short_8","alias_value":"XXPUVHHW","created_at":"2026-07-05T09:54:10.691082+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/XXPUVHHWM4E322U6NX7BMXGL7S","json":"https://pith.science/pith/XXPUVHHWM4E322U6NX7BMXGL7S.json","graph_json":"https://pith.science/api/pith-number/XXPUVHHWM4E322U6NX7BMXGL7S/graph.json","events_json":"https://pith.science/api/pith-number/XXPUVHHWM4E322U6NX7BMXGL7S/events.json","paper":"https://pith.science/paper/XXPUVHHW"},"agent_actions":{"view_html":"https://pith.science/pith/XXPUVHHWM4E322U6NX7BMXGL7S","download_json":"https://pith.science/pith/XXPUVHHWM4E322U6NX7BMXGL7S.json","view_paper":"https://pith.science/paper/XXPUVHHW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18778&json=true","fetch_graph":"https://pith.science/api/pith-number/XXPUVHHWM4E322U6NX7BMXGL7S/graph.json","fetch_events":"https://pith.science/api/pith-number/XXPUVHHWM4E322U6NX7BMXGL7S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XXPUVHHWM4E322U6NX7BMXGL7S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XXPUVHHWM4E322U6NX7BMXGL7S/action/storage_attestation","attest_author":"https://pith.science/pith/XXPUVHHWM4E322U6NX7BMXGL7S/action/author_attestation","sign_citation":"https://pith.science/pith/XXPUVHHWM4E322U6NX7BMXGL7S/action/citation_signature","submit_replication":"https://pith.science/pith/XXPUVHHWM4E322U6NX7BMXGL7S/action/replication_record"}},"created_at":"2026-07-05T09:54:10.691082+00:00","updated_at":"2026-07-05T09:54:10.691082+00:00"}