{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DYW2XBTB76DMEAARWCLSX4CKOW","short_pith_number":"pith:DYW2XBTB","schema_version":"1.0","canonical_sha256":"1e2dab8661ff86c20011b0972bf04a75ab397374799cb0964fc7754e1813ddeb","source":{"kind":"arxiv","id":"2407.12736","version":4},"attestation_state":"computed","paper":{"title":"CHOSEN: Compilation to Hardware Optimization Stack for Efficient Vision Transformer Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.AR"],"primary_cat":"cs.CV","authors_text":"Arash Fayyazi, Armin Abdollahi, Massoud Pedram, Mohammad Erfan Sadeghi, Suhas Somashekar","submitted_at":"2024-07-17T16:56:06Z","abstract_excerpt":"Vision Transformers (ViTs) represent a groundbreaking shift in machine learning approaches to computer vision. Unlike traditional approaches, ViTs employ the self-attention mechanism, which has been widely used in natural language processing, to analyze image patches. Despite their advantages in modeling visual tasks, deploying ViTs on hardware platforms, notably Field-Programmable Gate Arrays (FPGAs), introduces considerable challenges. These challenges stem primarily from the non-linear calculations and high computational and memory demands of ViTs. This paper introduces CHOSEN, a software-h"},"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":"2407.12736","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T16:56:06Z","cross_cats_sorted":["cs.AI","cs.AR"],"title_canon_sha256":"d206034516c0baeb0fcb7fb760ebef72ab5321ae0abcadfe03107612f19f3529","abstract_canon_sha256":"6861b72c8e170c7d6d38a0958153b231ee1e10ecf88c5550033a3fc84c0513b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:20.285080Z","signature_b64":"a204k0ZcqRtutdBV9x7PuCmrDe6KA4VtamJLEPinwKz8FlRMAZrFoaN3VyIE/49Qqfwv94Z9rQ9FzBiMCiKgCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e2dab8661ff86c20011b0972bf04a75ab397374799cb0964fc7754e1813ddeb","last_reissued_at":"2026-07-05T11:19:20.284597Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:20.284597Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CHOSEN: Compilation to Hardware Optimization Stack for Efficient Vision Transformer Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.AR"],"primary_cat":"cs.CV","authors_text":"Arash Fayyazi, Armin Abdollahi, Massoud Pedram, Mohammad Erfan Sadeghi, Suhas Somashekar","submitted_at":"2024-07-17T16:56:06Z","abstract_excerpt":"Vision Transformers (ViTs) represent a groundbreaking shift in machine learning approaches to computer vision. Unlike traditional approaches, ViTs employ the self-attention mechanism, which has been widely used in natural language processing, to analyze image patches. Despite their advantages in modeling visual tasks, deploying ViTs on hardware platforms, notably Field-Programmable Gate Arrays (FPGAs), introduces considerable challenges. These challenges stem primarily from the non-linear calculations and high computational and memory demands of ViTs. This paper introduces CHOSEN, a software-h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12736","kind":"arxiv","version":4},"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/2407.12736/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":"2407.12736","created_at":"2026-07-05T11:19:20.284655+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.12736v4","created_at":"2026-07-05T11:19:20.284655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12736","created_at":"2026-07-05T11:19:20.284655+00:00"},{"alias_kind":"pith_short_12","alias_value":"DYW2XBTB76DM","created_at":"2026-07-05T11:19:20.284655+00:00"},{"alias_kind":"pith_short_16","alias_value":"DYW2XBTB76DMEAAR","created_at":"2026-07-05T11:19:20.284655+00:00"},{"alias_kind":"pith_short_8","alias_value":"DYW2XBTB","created_at":"2026-07-05T11:19:20.284655+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06955","citing_title":"TRAPTI: Time-Resolved Analysis for SRAM Banking and Power Gating Optimization in Embedded Transformer Inference","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DYW2XBTB76DMEAARWCLSX4CKOW","json":"https://pith.science/pith/DYW2XBTB76DMEAARWCLSX4CKOW.json","graph_json":"https://pith.science/api/pith-number/DYW2XBTB76DMEAARWCLSX4CKOW/graph.json","events_json":"https://pith.science/api/pith-number/DYW2XBTB76DMEAARWCLSX4CKOW/events.json","paper":"https://pith.science/paper/DYW2XBTB"},"agent_actions":{"view_html":"https://pith.science/pith/DYW2XBTB76DMEAARWCLSX4CKOW","download_json":"https://pith.science/pith/DYW2XBTB76DMEAARWCLSX4CKOW.json","view_paper":"https://pith.science/paper/DYW2XBTB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.12736&json=true","fetch_graph":"https://pith.science/api/pith-number/DYW2XBTB76DMEAARWCLSX4CKOW/graph.json","fetch_events":"https://pith.science/api/pith-number/DYW2XBTB76DMEAARWCLSX4CKOW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DYW2XBTB76DMEAARWCLSX4CKOW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DYW2XBTB76DMEAARWCLSX4CKOW/action/storage_attestation","attest_author":"https://pith.science/pith/DYW2XBTB76DMEAARWCLSX4CKOW/action/author_attestation","sign_citation":"https://pith.science/pith/DYW2XBTB76DMEAARWCLSX4CKOW/action/citation_signature","submit_replication":"https://pith.science/pith/DYW2XBTB76DMEAARWCLSX4CKOW/action/replication_record"}},"created_at":"2026-07-05T11:19:20.284655+00:00","updated_at":"2026-07-05T11:19:20.284655+00:00"}