{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZOIPPVGPLC4QMDDYDFO5UPPJBS","short_pith_number":"pith:ZOIPPVGP","schema_version":"1.0","canonical_sha256":"cb90f7d4cf58b9060c78195dda3de90c9cfff4437a562353eb66943395fa7f1f","source":{"kind":"arxiv","id":"2606.17249","version":1},"attestation_state":"computed","paper":{"title":"From Compression to Deployment: Real-Time and Energy-Efficient FastGRNN on Ultra-Constrained Microcontrollers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NE","eess.SP"],"primary_cat":"cs.AR","authors_text":"Emre Can Kizilates","submitted_at":"2026-06-15T19:49:38Z","abstract_excerpt":"The dominant trajectory of modern machine learning has been to scale up: larger models, larger accelerators, larger memory budgets. Yet a multi-year global semiconductor supply constraint and the growing energy and carbon cost of always-online inference expose the fragility of this trajectory and motivate the opposite direction: refactoring AI and ML algorithms to fit the small, ubiquitous microcontrollers already in mass production in wearables, sensors, and edge appliances. We present an end-to-end open-source reproduction of FastGRNN, a compact gated recurrent cell, deployed on two bare-met"},"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":"2606.17249","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2026-06-15T19:49:38Z","cross_cats_sorted":["cs.LG","cs.NE","eess.SP"],"title_canon_sha256":"eed063c8b6584f308f45e2cba72773366228a4073c13fb6e33297cb25656be39","abstract_canon_sha256":"29a7f925d890e5ed4effb922880ab7aa266c62b0b13cb689d40c8297415cacfb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:06.886723Z","signature_b64":"2W1aD11K/wW1Lk3qooksTPuf2cEqN4gY9Pa6ddk5A+XoRafTRLjHfvG27d23x9fJ7ji794zkQUvt6r2x/ECPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb90f7d4cf58b9060c78195dda3de90c9cfff4437a562353eb66943395fa7f1f","last_reissued_at":"2026-06-19T16:10:06.886384Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:06.886384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Compression to Deployment: Real-Time and Energy-Efficient FastGRNN on Ultra-Constrained Microcontrollers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NE","eess.SP"],"primary_cat":"cs.AR","authors_text":"Emre Can Kizilates","submitted_at":"2026-06-15T19:49:38Z","abstract_excerpt":"The dominant trajectory of modern machine learning has been to scale up: larger models, larger accelerators, larger memory budgets. Yet a multi-year global semiconductor supply constraint and the growing energy and carbon cost of always-online inference expose the fragility of this trajectory and motivate the opposite direction: refactoring AI and ML algorithms to fit the small, ubiquitous microcontrollers already in mass production in wearables, sensors, and edge appliances. We present an end-to-end open-source reproduction of FastGRNN, a compact gated recurrent cell, deployed on two bare-met"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17249","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/2606.17249/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":"2606.17249","created_at":"2026-06-19T16:10:06.886445+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.17249v1","created_at":"2026-06-19T16:10:06.886445+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17249","created_at":"2026-06-19T16:10:06.886445+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZOIPPVGPLC4Q","created_at":"2026-06-19T16:10:06.886445+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZOIPPVGPLC4QMDDY","created_at":"2026-06-19T16:10:06.886445+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZOIPPVGP","created_at":"2026-06-19T16:10:06.886445+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/ZOIPPVGPLC4QMDDYDFO5UPPJBS","json":"https://pith.science/pith/ZOIPPVGPLC4QMDDYDFO5UPPJBS.json","graph_json":"https://pith.science/api/pith-number/ZOIPPVGPLC4QMDDYDFO5UPPJBS/graph.json","events_json":"https://pith.science/api/pith-number/ZOIPPVGPLC4QMDDYDFO5UPPJBS/events.json","paper":"https://pith.science/paper/ZOIPPVGP"},"agent_actions":{"view_html":"https://pith.science/pith/ZOIPPVGPLC4QMDDYDFO5UPPJBS","download_json":"https://pith.science/pith/ZOIPPVGPLC4QMDDYDFO5UPPJBS.json","view_paper":"https://pith.science/paper/ZOIPPVGP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.17249&json=true","fetch_graph":"https://pith.science/api/pith-number/ZOIPPVGPLC4QMDDYDFO5UPPJBS/graph.json","fetch_events":"https://pith.science/api/pith-number/ZOIPPVGPLC4QMDDYDFO5UPPJBS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZOIPPVGPLC4QMDDYDFO5UPPJBS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZOIPPVGPLC4QMDDYDFO5UPPJBS/action/storage_attestation","attest_author":"https://pith.science/pith/ZOIPPVGPLC4QMDDYDFO5UPPJBS/action/author_attestation","sign_citation":"https://pith.science/pith/ZOIPPVGPLC4QMDDYDFO5UPPJBS/action/citation_signature","submit_replication":"https://pith.science/pith/ZOIPPVGPLC4QMDDYDFO5UPPJBS/action/replication_record"}},"created_at":"2026-06-19T16:10:06.886445+00:00","updated_at":"2026-06-19T16:10:06.886445+00:00"}