{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NBTYT5KMEUZ4K4FHKU5UNMMLRL","short_pith_number":"pith:NBTYT5KM","canonical_record":{"source":{"id":"2506.06505","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T20:01:09Z","cross_cats_sorted":["cs.AR"],"title_canon_sha256":"e30b55ca4cbbd64183ab8eed38cdb8d69b2f40c3b6d7b0e8d5e98754a7fc6692","abstract_canon_sha256":"dc0389f8e56fcabc27a1fa1f14fb5aa521948e74a14a359afe48b08546f65e6f"},"schema_version":"1.0"},"canonical_sha256":"686789f54c2533c570a7553b46b18b8af51556ba03bc51907faa42c71fe48d4c","source":{"kind":"arxiv","id":"2506.06505","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06505","created_at":"2026-07-05T11:17:51Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06505v1","created_at":"2026-07-05T11:17:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06505","created_at":"2026-07-05T11:17:51Z"},{"alias_kind":"pith_short_12","alias_value":"NBTYT5KMEUZ4","created_at":"2026-07-05T11:17:51Z"},{"alias_kind":"pith_short_16","alias_value":"NBTYT5KMEUZ4K4FH","created_at":"2026-07-05T11:17:51Z"},{"alias_kind":"pith_short_8","alias_value":"NBTYT5KM","created_at":"2026-07-05T11:17:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NBTYT5KMEUZ4K4FHKU5UNMMLRL","target":"record","payload":{"canonical_record":{"source":{"id":"2506.06505","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T20:01:09Z","cross_cats_sorted":["cs.AR"],"title_canon_sha256":"e30b55ca4cbbd64183ab8eed38cdb8d69b2f40c3b6d7b0e8d5e98754a7fc6692","abstract_canon_sha256":"dc0389f8e56fcabc27a1fa1f14fb5aa521948e74a14a359afe48b08546f65e6f"},"schema_version":"1.0"},"canonical_sha256":"686789f54c2533c570a7553b46b18b8af51556ba03bc51907faa42c71fe48d4c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:51.310475Z","signature_b64":"iJl7scDWhHgRWah5Qq0Jqdw8mGN6rvQTHnz/dLju3TWJIxNCGSo9T5HuExS9kYzqeq00oMV99qTFKYFUsTzSDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"686789f54c2533c570a7553b46b18b8af51556ba03bc51907faa42c71fe48d4c","last_reissued_at":"2026-07-05T11:17:51.310031Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:51.310031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.06505","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":"2026-07-05T11:17:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mOcESLYZ9VoOs169OF6qtLkdojN5upRvQJzB01/sYhtQDF0rH+OOJNb1DxMNZS2QgfHa8jkpapaWXqhoZ5skCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:58:09.953885Z"},"content_sha256":"131be51cdc02992ed7c82504098f05ceec1d97f953603cab2cefdc3da410f14b","schema_version":"1.0","event_id":"sha256:131be51cdc02992ed7c82504098f05ceec1d97f953603cab2cefdc3da410f14b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NBTYT5KMEUZ4K4FHKU5UNMMLRL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"InstantFT: An FPGA-Based Runtime Subsecond Fine-tuning of CNN Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.LG","authors_text":"Hiroki Matsutani, Keisuke Sugiura","submitted_at":"2025-06-06T20:01:09Z","abstract_excerpt":"Training deep neural networks (DNNs) requires significantly more computation and memory than inference, making runtime adaptation of DNNs challenging on resource-limited IoT platforms. We propose InstantFT, an FPGA-based method for ultra-fast CNN fine-tuning on IoT devices, by optimizing the forward and backward computations in parameter-efficient fine-tuning (PEFT). Experiments on datasets with concept drift demonstrate that InstantFT fine-tunes a pre-trained CNN 17.4x faster than existing Low-Rank Adaptation (LoRA)-based approaches, while achieving comparable accuracy. Our FPGA-based Instant"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06505","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/2506.06505/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:17:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rVtTiwqLI+XBfzqP+JIE8LKaZDkW40fZtd4vhau4Z9QfGBbwwEIOb7l1YMkBvuhDlwDyF6dvmDtVZAXTE/a/BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:58:09.954332Z"},"content_sha256":"69b6430cc8cb0760d2a9f7e08acf6dc792f406d19d69645b94b7dba45754a4fb","schema_version":"1.0","event_id":"sha256:69b6430cc8cb0760d2a9f7e08acf6dc792f406d19d69645b94b7dba45754a4fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NBTYT5KMEUZ4K4FHKU5UNMMLRL/bundle.json","state_url":"https://pith.science/pith/NBTYT5KMEUZ4K4FHKU5UNMMLRL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NBTYT5KMEUZ4K4FHKU5UNMMLRL/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":"2026-07-06T20:58:09Z","links":{"resolver":"https://pith.science/pith/NBTYT5KMEUZ4K4FHKU5UNMMLRL","bundle":"https://pith.science/pith/NBTYT5KMEUZ4K4FHKU5UNMMLRL/bundle.json","state":"https://pith.science/pith/NBTYT5KMEUZ4K4FHKU5UNMMLRL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NBTYT5KMEUZ4K4FHKU5UNMMLRL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NBTYT5KMEUZ4K4FHKU5UNMMLRL","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":"dc0389f8e56fcabc27a1fa1f14fb5aa521948e74a14a359afe48b08546f65e6f","cross_cats_sorted":["cs.AR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T20:01:09Z","title_canon_sha256":"e30b55ca4cbbd64183ab8eed38cdb8d69b2f40c3b6d7b0e8d5e98754a7fc6692"},"schema_version":"1.0","source":{"id":"2506.06505","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06505","created_at":"2026-07-05T11:17:51Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06505v1","created_at":"2026-07-05T11:17:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06505","created_at":"2026-07-05T11:17:51Z"},{"alias_kind":"pith_short_12","alias_value":"NBTYT5KMEUZ4","created_at":"2026-07-05T11:17:51Z"},{"alias_kind":"pith_short_16","alias_value":"NBTYT5KMEUZ4K4FH","created_at":"2026-07-05T11:17:51Z"},{"alias_kind":"pith_short_8","alias_value":"NBTYT5KM","created_at":"2026-07-05T11:17:51Z"}],"graph_snapshots":[{"event_id":"sha256:69b6430cc8cb0760d2a9f7e08acf6dc792f406d19d69645b94b7dba45754a4fb","target":"graph","created_at":"2026-07-05T11:17:51Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.06505/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training deep neural networks (DNNs) requires significantly more computation and memory than inference, making runtime adaptation of DNNs challenging on resource-limited IoT platforms. We propose InstantFT, an FPGA-based method for ultra-fast CNN fine-tuning on IoT devices, by optimizing the forward and backward computations in parameter-efficient fine-tuning (PEFT). Experiments on datasets with concept drift demonstrate that InstantFT fine-tunes a pre-trained CNN 17.4x faster than existing Low-Rank Adaptation (LoRA)-based approaches, while achieving comparable accuracy. Our FPGA-based Instant","authors_text":"Hiroki Matsutani, Keisuke Sugiura","cross_cats":["cs.AR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T20:01:09Z","title":"InstantFT: An FPGA-Based Runtime Subsecond Fine-tuning of CNN Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06505","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":"sha256:131be51cdc02992ed7c82504098f05ceec1d97f953603cab2cefdc3da410f14b","target":"record","created_at":"2026-07-05T11:17:51Z","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":"dc0389f8e56fcabc27a1fa1f14fb5aa521948e74a14a359afe48b08546f65e6f","cross_cats_sorted":["cs.AR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-06T20:01:09Z","title_canon_sha256":"e30b55ca4cbbd64183ab8eed38cdb8d69b2f40c3b6d7b0e8d5e98754a7fc6692"},"schema_version":"1.0","source":{"id":"2506.06505","kind":"arxiv","version":1}},"canonical_sha256":"686789f54c2533c570a7553b46b18b8af51556ba03bc51907faa42c71fe48d4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"686789f54c2533c570a7553b46b18b8af51556ba03bc51907faa42c71fe48d4c","first_computed_at":"2026-07-05T11:17:51.310031Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:51.310031Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iJl7scDWhHgRWah5Qq0Jqdw8mGN6rvQTHnz/dLju3TWJIxNCGSo9T5HuExS9kYzqeq00oMV99qTFKYFUsTzSDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:51.310475Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.06505","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:131be51cdc02992ed7c82504098f05ceec1d97f953603cab2cefdc3da410f14b","sha256:69b6430cc8cb0760d2a9f7e08acf6dc792f406d19d69645b94b7dba45754a4fb"],"state_sha256":"27b373b058d809f577f5f65adb41b97e2dbe8f8d37695737771d6935f598411c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9aV/2PvPGU7cPDFRxpStdtP+9lPpEn1CiBbtclrKQ4zlbhhdXuNTe8oLQJokfchVVGEYWlxik+OqC/vA0LwIBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:58:09.956230Z","bundle_sha256":"7632e91b2b9431efafe1f225577d670bc7460593e3c43276adbff84461ff6eb8"}}