{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:5WEIXX6S7XNQXBWKQ43KIM6JEB","short_pith_number":"pith:5WEIXX6S","canonical_record":{"source":{"id":"1709.04731","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-14T12:30:41Z","cross_cats_sorted":[],"title_canon_sha256":"e547fd26b88b8a4a1d661a6b6cff52eee577fe8f96d9649601b618788711c631","abstract_canon_sha256":"a49db86e98e5880e13b0136e1101ca059f4a48a4ea9b9061442cf47c9da3b420"},"schema_version":"1.0"},"canonical_sha256":"ed888bdfd2fddb0b86ca8736a433c9207510c2ba22bf70dcef6c9c9d4cc79924","source":{"kind":"arxiv","id":"1709.04731","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.04731","created_at":"2026-05-18T00:35:10Z"},{"alias_kind":"arxiv_version","alias_value":"1709.04731v1","created_at":"2026-05-18T00:35:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.04731","created_at":"2026-05-18T00:35:10Z"},{"alias_kind":"pith_short_12","alias_value":"5WEIXX6S7XNQ","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"5WEIXX6S7XNQXBWK","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"5WEIXX6S","created_at":"2026-05-18T12:31:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:5WEIXX6S7XNQXBWKQ43KIM6JEB","target":"record","payload":{"canonical_record":{"source":{"id":"1709.04731","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-14T12:30:41Z","cross_cats_sorted":[],"title_canon_sha256":"e547fd26b88b8a4a1d661a6b6cff52eee577fe8f96d9649601b618788711c631","abstract_canon_sha256":"a49db86e98e5880e13b0136e1101ca059f4a48a4ea9b9061442cf47c9da3b420"},"schema_version":"1.0"},"canonical_sha256":"ed888bdfd2fddb0b86ca8736a433c9207510c2ba22bf70dcef6c9c9d4cc79924","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:10.293298Z","signature_b64":"Ez0/mQYCRYekiW/E4JOov0ZGrkeh8/bJobKXci2+F7thuicz742gzcrbvi3E7fxBm1zj25l8zltunkZDthNLCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed888bdfd2fddb0b86ca8736a433c9207510c2ba22bf70dcef6c9c9d4cc79924","last_reissued_at":"2026-05-18T00:35:10.292890Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:10.292890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.04731","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":"2026-05-18T00:35:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rn/lJXhFe8WbT6uJ8QuEJ8xcdq9Iq50blal9GYwSLcl4saoDsrrF5Easj2Y3qOBKh023HeGI7swfWNE2WSJcAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T18:15:15.983053Z"},"content_sha256":"c5d4dea4a90a100e16d34c96662b15efd7204bc702e1770913a855171416f0f9","schema_version":"1.0","event_id":"sha256:c5d4dea4a90a100e16d34c96662b15efd7204bc702e1770913a855171416f0f9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:5WEIXX6S7XNQXBWKQ43KIM6JEB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Binary-decomposed DCNN for accelerating computation and compressing model without retraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hironobu Fujiyoshi, Ikuro Sato, Mitsuru Ambai, Ryuji Kamiya, Takayoshi Yamashita, Yuji Yamauchi","submitted_at":"2017-09-14T12:30:41Z","abstract_excerpt":"Recent trends show recognition accuracy increasing even more profoundly. Inference process of Deep Convolutional Neural Networks (DCNN) has a large number of parameters, requires a large amount of computation, and can be very slow. The large number of parameters also require large amounts of memory. This is resulting in increasingly long computation times and large model sizes. To implement mobile and other low performance devices incorporating DCNN, model sizes must be compressed and computation must be accelerated. To that end, this paper proposes Binary-decomposed DCNN, which resolves these"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.04731","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":"2026-05-18T00:35:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WrPeuASkhxVOq9GaREWDx/JMnWu2ybBIDx8H6dFBBjxQ2BKZnDl4+7OEJhHyEO6IE/5WdlyBUBdsWGu5RwGdBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T18:15:15.983417Z"},"content_sha256":"40614f874e7b8813e7e987ae8a4d8cdafc6366c50ff607ab50748835d5215c9b","schema_version":"1.0","event_id":"sha256:40614f874e7b8813e7e987ae8a4d8cdafc6366c50ff607ab50748835d5215c9b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5WEIXX6S7XNQXBWKQ43KIM6JEB/bundle.json","state_url":"https://pith.science/pith/5WEIXX6S7XNQXBWKQ43KIM6JEB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5WEIXX6S7XNQXBWKQ43KIM6JEB/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":"2026-06-05T18:15:15Z","links":{"resolver":"https://pith.science/pith/5WEIXX6S7XNQXBWKQ43KIM6JEB","bundle":"https://pith.science/pith/5WEIXX6S7XNQXBWKQ43KIM6JEB/bundle.json","state":"https://pith.science/pith/5WEIXX6S7XNQXBWKQ43KIM6JEB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5WEIXX6S7XNQXBWKQ43KIM6JEB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:5WEIXX6S7XNQXBWKQ43KIM6JEB","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":"a49db86e98e5880e13b0136e1101ca059f4a48a4ea9b9061442cf47c9da3b420","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-14T12:30:41Z","title_canon_sha256":"e547fd26b88b8a4a1d661a6b6cff52eee577fe8f96d9649601b618788711c631"},"schema_version":"1.0","source":{"id":"1709.04731","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.04731","created_at":"2026-05-18T00:35:10Z"},{"alias_kind":"arxiv_version","alias_value":"1709.04731v1","created_at":"2026-05-18T00:35:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.04731","created_at":"2026-05-18T00:35:10Z"},{"alias_kind":"pith_short_12","alias_value":"5WEIXX6S7XNQ","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_16","alias_value":"5WEIXX6S7XNQXBWK","created_at":"2026-05-18T12:31:03Z"},{"alias_kind":"pith_short_8","alias_value":"5WEIXX6S","created_at":"2026-05-18T12:31:03Z"}],"graph_snapshots":[{"event_id":"sha256:40614f874e7b8813e7e987ae8a4d8cdafc6366c50ff607ab50748835d5215c9b","target":"graph","created_at":"2026-05-18T00:35:10Z","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":"Recent trends show recognition accuracy increasing even more profoundly. Inference process of Deep Convolutional Neural Networks (DCNN) has a large number of parameters, requires a large amount of computation, and can be very slow. The large number of parameters also require large amounts of memory. This is resulting in increasingly long computation times and large model sizes. To implement mobile and other low performance devices incorporating DCNN, model sizes must be compressed and computation must be accelerated. To that end, this paper proposes Binary-decomposed DCNN, which resolves these","authors_text":"Hironobu Fujiyoshi, Ikuro Sato, Mitsuru Ambai, Ryuji Kamiya, Takayoshi Yamashita, Yuji Yamauchi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-14T12:30:41Z","title":"Binary-decomposed DCNN for accelerating computation and compressing model without retraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.04731","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:c5d4dea4a90a100e16d34c96662b15efd7204bc702e1770913a855171416f0f9","target":"record","created_at":"2026-05-18T00:35:10Z","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":"a49db86e98e5880e13b0136e1101ca059f4a48a4ea9b9061442cf47c9da3b420","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-09-14T12:30:41Z","title_canon_sha256":"e547fd26b88b8a4a1d661a6b6cff52eee577fe8f96d9649601b618788711c631"},"schema_version":"1.0","source":{"id":"1709.04731","kind":"arxiv","version":1}},"canonical_sha256":"ed888bdfd2fddb0b86ca8736a433c9207510c2ba22bf70dcef6c9c9d4cc79924","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed888bdfd2fddb0b86ca8736a433c9207510c2ba22bf70dcef6c9c9d4cc79924","first_computed_at":"2026-05-18T00:35:10.292890Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:35:10.292890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ez0/mQYCRYekiW/E4JOov0ZGrkeh8/bJobKXci2+F7thuicz742gzcrbvi3E7fxBm1zj25l8zltunkZDthNLCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:35:10.293298Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.04731","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5d4dea4a90a100e16d34c96662b15efd7204bc702e1770913a855171416f0f9","sha256:40614f874e7b8813e7e987ae8a4d8cdafc6366c50ff607ab50748835d5215c9b"],"state_sha256":"cac1c798ff3825ad394182cab611fd80c14433f3797d55ed4d2d6fc450c26f28"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yWco60JyUvUxM2SkRpBycwJlIAeQ5luFw8gjGl1BpTpocq1NuHK4gfuL16E6O4ubl/eqb9NIF6YgZkuPY99yAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T18:15:15.986124Z","bundle_sha256":"604cf904c34968bad7f65b0342802cfed84f330c9d33150ed3efe53690744586"}}