{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:YLNATIN4YNU7X3HDY5NUPH7HR3","short_pith_number":"pith:YLNATIN4","canonical_record":{"source":{"id":"1902.11128","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-27T02:42:33Z","cross_cats_sorted":["cs.AR","cs.LG","stat.ML"],"title_canon_sha256":"c881caeb71c6688062954944464237a9412f69a86ea6cfb456e5431b15cb559e","abstract_canon_sha256":"801132676719d874d93e8bb119b4b65527fc5e7568da7a41a8150044fe5e69eb"},"schema_version":"1.0"},"canonical_sha256":"c2da09a1bcc369fbece3c75b479fe78ee44d22926116cd8dc6b80637624ca905","source":{"kind":"arxiv","id":"1902.11128","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.11128","created_at":"2026-05-17T23:52:25Z"},{"alias_kind":"arxiv_version","alias_value":"1902.11128v1","created_at":"2026-05-17T23:52:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.11128","created_at":"2026-05-17T23:52:25Z"},{"alias_kind":"pith_short_12","alias_value":"YLNATIN4YNU7","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"YLNATIN4YNU7X3HD","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"YLNATIN4","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:YLNATIN4YNU7X3HDY5NUPH7HR3","target":"record","payload":{"canonical_record":{"source":{"id":"1902.11128","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-27T02:42:33Z","cross_cats_sorted":["cs.AR","cs.LG","stat.ML"],"title_canon_sha256":"c881caeb71c6688062954944464237a9412f69a86ea6cfb456e5431b15cb559e","abstract_canon_sha256":"801132676719d874d93e8bb119b4b65527fc5e7568da7a41a8150044fe5e69eb"},"schema_version":"1.0"},"canonical_sha256":"c2da09a1bcc369fbece3c75b479fe78ee44d22926116cd8dc6b80637624ca905","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:25.706707Z","signature_b64":"SXV0cC6BU++CNVIaq139UmgsYFNbADR5Kb/uAnydriRpNeevNQJ7mW/HNIb9i+AHzg9tKwJLl1DpLft9R5hcAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2da09a1bcc369fbece3c75b479fe78ee44d22926116cd8dc6b80637624ca905","last_reissued_at":"2026-05-17T23:52:25.706195Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:25.706195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.11128","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:52:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c9BykCqrxehSGINUFFLPoXj0FEvDIJpv366DE+U6A/1BPfqPesEkH7tUa4qi00ZE4n5uYk68q0qGJ7iKdzzCDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T18:26:52.979939Z"},"content_sha256":"e9fdabd75eb56d7486a5eee8cc118d89152408f1f15083ee4eb454216a1eb6b5","schema_version":"1.0","event_id":"sha256:e9fdabd75eb56d7486a5eee8cc118d89152408f1f15083ee4eb454216a1eb6b5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:YLNATIN4YNU7X3HDY5NUPH7HR3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FixyNN: Efficient Hardware for Mobile Computer Vision via Transfer Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AR","cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Chuteng Zhou, Jae-sun Seo, Matthew Mattina, Patrick Hansen, Paul N. Whatmough, Shreyas Kolala Venkataramanaiah","submitted_at":"2019-02-27T02:42:33Z","abstract_excerpt":"The computational demands of computer vision tasks based on state-of-the-art Convolutional Neural Network (CNN) image classification far exceed the energy budgets of mobile devices. This paper proposes FixyNN, which consists of a fixed-weight feature extractor that generates ubiquitous CNN features, and a conventional programmable CNN accelerator which processes a dataset-specific CNN. Image classification models for FixyNN are trained end-to-end via transfer learning, with the common feature extractor representing the transfered part, and the programmable part being learnt on the target datas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.11128","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:52:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mXwmY6GuEWifkRRfPPf5JijoACuL9L7UW0R+jlfuEhepsj8a44ApV2tAiGdEMZ5EkzugVoCWEe6Ug+ORIbBUDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T18:26:52.980650Z"},"content_sha256":"4ab8f3d864067f239accb4efa94fd48678cac7849166ac8d6692a98854899ed0","schema_version":"1.0","event_id":"sha256:4ab8f3d864067f239accb4efa94fd48678cac7849166ac8d6692a98854899ed0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YLNATIN4YNU7X3HDY5NUPH7HR3/bundle.json","state_url":"https://pith.science/pith/YLNATIN4YNU7X3HDY5NUPH7HR3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YLNATIN4YNU7X3HDY5NUPH7HR3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T18:26:52Z","links":{"resolver":"https://pith.science/pith/YLNATIN4YNU7X3HDY5NUPH7HR3","bundle":"https://pith.science/pith/YLNATIN4YNU7X3HDY5NUPH7HR3/bundle.json","state":"https://pith.science/pith/YLNATIN4YNU7X3HDY5NUPH7HR3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YLNATIN4YNU7X3HDY5NUPH7HR3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:YLNATIN4YNU7X3HDY5NUPH7HR3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"801132676719d874d93e8bb119b4b65527fc5e7568da7a41a8150044fe5e69eb","cross_cats_sorted":["cs.AR","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-27T02:42:33Z","title_canon_sha256":"c881caeb71c6688062954944464237a9412f69a86ea6cfb456e5431b15cb559e"},"schema_version":"1.0","source":{"id":"1902.11128","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.11128","created_at":"2026-05-17T23:52:25Z"},{"alias_kind":"arxiv_version","alias_value":"1902.11128v1","created_at":"2026-05-17T23:52:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.11128","created_at":"2026-05-17T23:52:25Z"},{"alias_kind":"pith_short_12","alias_value":"YLNATIN4YNU7","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"YLNATIN4YNU7X3HD","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"YLNATIN4","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:4ab8f3d864067f239accb4efa94fd48678cac7849166ac8d6692a98854899ed0","target":"graph","created_at":"2026-05-17T23:52:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"The computational demands of computer vision tasks based on state-of-the-art Convolutional Neural Network (CNN) image classification far exceed the energy budgets of mobile devices. This paper proposes FixyNN, which consists of a fixed-weight feature extractor that generates ubiquitous CNN features, and a conventional programmable CNN accelerator which processes a dataset-specific CNN. Image classification models for FixyNN are trained end-to-end via transfer learning, with the common feature extractor representing the transfered part, and the programmable part being learnt on the target datas","authors_text":"Chuteng Zhou, Jae-sun Seo, Matthew Mattina, Patrick Hansen, Paul N. Whatmough, Shreyas Kolala Venkataramanaiah","cross_cats":["cs.AR","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-27T02:42:33Z","title":"FixyNN: Efficient Hardware for Mobile Computer Vision via Transfer Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.11128","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e9fdabd75eb56d7486a5eee8cc118d89152408f1f15083ee4eb454216a1eb6b5","target":"record","created_at":"2026-05-17T23:52:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"801132676719d874d93e8bb119b4b65527fc5e7568da7a41a8150044fe5e69eb","cross_cats_sorted":["cs.AR","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-27T02:42:33Z","title_canon_sha256":"c881caeb71c6688062954944464237a9412f69a86ea6cfb456e5431b15cb559e"},"schema_version":"1.0","source":{"id":"1902.11128","kind":"arxiv","version":1}},"canonical_sha256":"c2da09a1bcc369fbece3c75b479fe78ee44d22926116cd8dc6b80637624ca905","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2da09a1bcc369fbece3c75b479fe78ee44d22926116cd8dc6b80637624ca905","first_computed_at":"2026-05-17T23:52:25.706195Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:25.706195Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SXV0cC6BU++CNVIaq139UmgsYFNbADR5Kb/uAnydriRpNeevNQJ7mW/HNIb9i+AHzg9tKwJLl1DpLft9R5hcAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:25.706707Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.11128","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9fdabd75eb56d7486a5eee8cc118d89152408f1f15083ee4eb454216a1eb6b5","sha256:4ab8f3d864067f239accb4efa94fd48678cac7849166ac8d6692a98854899ed0"],"state_sha256":"c5053d434b5a3daa797dab1b70013faeaf960622ad93376e34994bfa5efd2290"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JzNEArFYIXmJq5fRDqEaRwQ4qNf4qDQtcv/E0NIlZGDbXAbL7mZNdpuriBQzc5TlCTXJHT4i083Ccg9q15qoAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T18:26:52.984571Z","bundle_sha256":"0396a5c67887487fd04f0c4983c22b1127b8d77683d0a8f57c79b05424031d22"}}