{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:R67PUJJHB2NIMRUP5K4YMO5WXN","short_pith_number":"pith:R67PUJJH","schema_version":"1.0","canonical_sha256":"8fbefa25270e9a86468feab9863bb6bb567a20f0e2d242a02c907524667b228c","source":{"kind":"arxiv","id":"2501.15014","version":2},"attestation_state":"computed","paper":{"title":"On Accelerating Edge AI: Optimizing Resource-Constrained Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Achraf Cohen, Brent Venable, Brian Jalaian, Jacob Sander, Venkat R. Dasari","submitted_at":"2025-01-25T01:37:03Z","abstract_excerpt":"Resource-constrained edge deployments demand AI solutions that balance high performance with stringent compute, memory, and energy limitations. In this survey, we present a comprehensive overview of the primary strategies for accelerating deep learning models under such constraints. First, we examine model compression techniques-pruning, quantization, tensor decomposition, and knowledge distillation-that streamline large models into smaller, faster, and more efficient variants. Next, we explore Neural Architecture Search (NAS), a class of automated methods that discover architectures inherentl"},"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":"2501.15014","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-25T01:37:03Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"41d7764395b9d022e727594221a8b4a5dd810113b50a356e8c59bfbf58856566","abstract_canon_sha256":"15d44ba4a33a460b2b9c862e03c85afce6aefffdc71a624a6215ab115226184a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:47.649209Z","signature_b64":"zEishbtVfog44KDliwRMEKHUuz9i5UkhZBd7KFCEm6AnUTFDRBPnNBSddCWCIvMlGWZNv8uBXV5cUwb5MoTCAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fbefa25270e9a86468feab9863bb6bb567a20f0e2d242a02c907524667b228c","last_reissued_at":"2026-07-05T10:06:47.648721Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:47.648721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Accelerating Edge AI: Optimizing Resource-Constrained Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Achraf Cohen, Brent Venable, Brian Jalaian, Jacob Sander, Venkat R. Dasari","submitted_at":"2025-01-25T01:37:03Z","abstract_excerpt":"Resource-constrained edge deployments demand AI solutions that balance high performance with stringent compute, memory, and energy limitations. In this survey, we present a comprehensive overview of the primary strategies for accelerating deep learning models under such constraints. First, we examine model compression techniques-pruning, quantization, tensor decomposition, and knowledge distillation-that streamline large models into smaller, faster, and more efficient variants. Next, we explore Neural Architecture Search (NAS), a class of automated methods that discover architectures inherentl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15014","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/2501.15014/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":"2501.15014","created_at":"2026-07-05T10:06:47.648783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.15014v2","created_at":"2026-07-05T10:06:47.648783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15014","created_at":"2026-07-05T10:06:47.648783+00:00"},{"alias_kind":"pith_short_12","alias_value":"R67PUJJHB2NI","created_at":"2026-07-05T10:06:47.648783+00:00"},{"alias_kind":"pith_short_16","alias_value":"R67PUJJHB2NIMRUP","created_at":"2026-07-05T10:06:47.648783+00:00"},{"alias_kind":"pith_short_8","alias_value":"R67PUJJH","created_at":"2026-07-05T10:06:47.648783+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01742","citing_title":"Joint Architecture-Token-Bitwidth Multi-Axis Optimization of Vision Transformers for Semiconductor IC Packaging","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R67PUJJHB2NIMRUP5K4YMO5WXN","json":"https://pith.science/pith/R67PUJJHB2NIMRUP5K4YMO5WXN.json","graph_json":"https://pith.science/api/pith-number/R67PUJJHB2NIMRUP5K4YMO5WXN/graph.json","events_json":"https://pith.science/api/pith-number/R67PUJJHB2NIMRUP5K4YMO5WXN/events.json","paper":"https://pith.science/paper/R67PUJJH"},"agent_actions":{"view_html":"https://pith.science/pith/R67PUJJHB2NIMRUP5K4YMO5WXN","download_json":"https://pith.science/pith/R67PUJJHB2NIMRUP5K4YMO5WXN.json","view_paper":"https://pith.science/paper/R67PUJJH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.15014&json=true","fetch_graph":"https://pith.science/api/pith-number/R67PUJJHB2NIMRUP5K4YMO5WXN/graph.json","fetch_events":"https://pith.science/api/pith-number/R67PUJJHB2NIMRUP5K4YMO5WXN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R67PUJJHB2NIMRUP5K4YMO5WXN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R67PUJJHB2NIMRUP5K4YMO5WXN/action/storage_attestation","attest_author":"https://pith.science/pith/R67PUJJHB2NIMRUP5K4YMO5WXN/action/author_attestation","sign_citation":"https://pith.science/pith/R67PUJJHB2NIMRUP5K4YMO5WXN/action/citation_signature","submit_replication":"https://pith.science/pith/R67PUJJHB2NIMRUP5K4YMO5WXN/action/replication_record"}},"created_at":"2026-07-05T10:06:47.648783+00:00","updated_at":"2026-07-05T10:06:47.648783+00:00"}