{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:H2VWCL7K7DZT3JTPP7QUJ2FXE2","short_pith_number":"pith:H2VWCL7K","canonical_record":{"source":{"id":"1603.06777","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-22T13:20:36Z","cross_cats_sorted":[],"title_canon_sha256":"387dc767269460074e6ebdc71ccd30e370500d80dc540841bf5c526e2f5643a2","abstract_canon_sha256":"e75e12b3657fafe1151e2b438a073c172e4dfc107579cdffad2ee163b29a5156"},"schema_version":"1.0"},"canonical_sha256":"3eab612feaf8f33da66f7fe144e8b7268fdfa1a45539250ead71d2e899d4d3c9","source":{"kind":"arxiv","id":"1603.06777","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.06777","created_at":"2026-05-18T00:58:33Z"},{"alias_kind":"arxiv_version","alias_value":"1603.06777v1","created_at":"2026-05-18T00:58:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.06777","created_at":"2026-05-18T00:58:33Z"},{"alias_kind":"pith_short_12","alias_value":"H2VWCL7K7DZT","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"H2VWCL7K7DZT3JTP","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"H2VWCL7K","created_at":"2026-05-18T12:30:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:H2VWCL7K7DZT3JTPP7QUJ2FXE2","target":"record","payload":{"canonical_record":{"source":{"id":"1603.06777","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-22T13:20:36Z","cross_cats_sorted":[],"title_canon_sha256":"387dc767269460074e6ebdc71ccd30e370500d80dc540841bf5c526e2f5643a2","abstract_canon_sha256":"e75e12b3657fafe1151e2b438a073c172e4dfc107579cdffad2ee163b29a5156"},"schema_version":"1.0"},"canonical_sha256":"3eab612feaf8f33da66f7fe144e8b7268fdfa1a45539250ead71d2e899d4d3c9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:58:33.854960Z","signature_b64":"it+058g3iceOc/pW+gNMQZ45+xmESmOJUkM9XeCPOPiPFwyPw3pQ4ou1ksmP4B6zpaWMZj66/2WHwfxETRjNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3eab612feaf8f33da66f7fe144e8b7268fdfa1a45539250ead71d2e899d4d3c9","last_reissued_at":"2026-05-18T00:58:33.854345Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:58:33.854345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1603.06777","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":"2026-05-18T00:58:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/BrJNEblZovizZRAvDWbvTjkZR/XRigWOk9X/slgtW41HFEJlpADqYP0+7HjehFooqPQ46dIPT8EyJiCiqAgCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T08:47:30.207784Z"},"content_sha256":"8ad756f53c744cc1d8cf1482b6d8b71387cbda03cf68de9d316711583cee3434","schema_version":"1.0","event_id":"sha256:8ad756f53c744cc1d8cf1482b6d8b71387cbda03cf68de9d316711583cee3434"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:H2VWCL7K7DZT3JTPP7QUJ2FXE2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Energy-Efficient ConvNets Through Approximate Computing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bert De Brabandere, Bert Moons, Luc Van Gool, Marian Verhelst","submitted_at":"2016-03-22T13:20:36Z","abstract_excerpt":"Recently ConvNets or convolutional neural networks (CNN) have come up as state-of-the-art classification and detection algorithms, achieving near-human performance in visual detection. However, ConvNet algorithms are typically very computation and memory intensive. In order to be able to embed ConvNet-based classification into wearable platforms and embedded systems such as smartphones or ubiquitous electronics for the internet-of-things, their energy consumption should be reduced drastically. This paper proposes methods based on approximate computing to reduce energy consumption in state-of-t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.06777","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":"2026-05-18T00:58:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FSgebIFEUuTS/0DMpWo3K0RxUZhoRQwnl1ZQg3djsyeOFZh5SJHjTFK5t5qrAHOKNiU+0t0v8BpBMPq6TGIQDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T08:47:30.208116Z"},"content_sha256":"a93976f0e86e67fe88df1bba7f0351dd583d936c323cac3467d71453fb27eca0","schema_version":"1.0","event_id":"sha256:a93976f0e86e67fe88df1bba7f0351dd583d936c323cac3467d71453fb27eca0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H2VWCL7K7DZT3JTPP7QUJ2FXE2/bundle.json","state_url":"https://pith.science/pith/H2VWCL7K7DZT3JTPP7QUJ2FXE2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H2VWCL7K7DZT3JTPP7QUJ2FXE2/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":"2026-05-20T08:47:30Z","links":{"resolver":"https://pith.science/pith/H2VWCL7K7DZT3JTPP7QUJ2FXE2","bundle":"https://pith.science/pith/H2VWCL7K7DZT3JTPP7QUJ2FXE2/bundle.json","state":"https://pith.science/pith/H2VWCL7K7DZT3JTPP7QUJ2FXE2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H2VWCL7K7DZT3JTPP7QUJ2FXE2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:H2VWCL7K7DZT3JTPP7QUJ2FXE2","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":"e75e12b3657fafe1151e2b438a073c172e4dfc107579cdffad2ee163b29a5156","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-22T13:20:36Z","title_canon_sha256":"387dc767269460074e6ebdc71ccd30e370500d80dc540841bf5c526e2f5643a2"},"schema_version":"1.0","source":{"id":"1603.06777","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.06777","created_at":"2026-05-18T00:58:33Z"},{"alias_kind":"arxiv_version","alias_value":"1603.06777v1","created_at":"2026-05-18T00:58:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.06777","created_at":"2026-05-18T00:58:33Z"},{"alias_kind":"pith_short_12","alias_value":"H2VWCL7K7DZT","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"H2VWCL7K7DZT3JTP","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"H2VWCL7K","created_at":"2026-05-18T12:30:19Z"}],"graph_snapshots":[{"event_id":"sha256:a93976f0e86e67fe88df1bba7f0351dd583d936c323cac3467d71453fb27eca0","target":"graph","created_at":"2026-05-18T00:58:33Z","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":"Recently ConvNets or convolutional neural networks (CNN) have come up as state-of-the-art classification and detection algorithms, achieving near-human performance in visual detection. However, ConvNet algorithms are typically very computation and memory intensive. In order to be able to embed ConvNet-based classification into wearable platforms and embedded systems such as smartphones or ubiquitous electronics for the internet-of-things, their energy consumption should be reduced drastically. This paper proposes methods based on approximate computing to reduce energy consumption in state-of-t","authors_text":"Bert De Brabandere, Bert Moons, Luc Van Gool, Marian Verhelst","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-22T13:20:36Z","title":"Energy-Efficient ConvNets Through Approximate Computing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.06777","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":"sha256:8ad756f53c744cc1d8cf1482b6d8b71387cbda03cf68de9d316711583cee3434","target":"record","created_at":"2026-05-18T00:58:33Z","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":"e75e12b3657fafe1151e2b438a073c172e4dfc107579cdffad2ee163b29a5156","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-22T13:20:36Z","title_canon_sha256":"387dc767269460074e6ebdc71ccd30e370500d80dc540841bf5c526e2f5643a2"},"schema_version":"1.0","source":{"id":"1603.06777","kind":"arxiv","version":1}},"canonical_sha256":"3eab612feaf8f33da66f7fe144e8b7268fdfa1a45539250ead71d2e899d4d3c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3eab612feaf8f33da66f7fe144e8b7268fdfa1a45539250ead71d2e899d4d3c9","first_computed_at":"2026-05-18T00:58:33.854345Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:58:33.854345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"it+058g3iceOc/pW+gNMQZ45+xmESmOJUkM9XeCPOPiPFwyPw3pQ4ou1ksmP4B6zpaWMZj66/2WHwfxETRjNDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:58:33.854960Z","signed_message":"canonical_sha256_bytes"},"source_id":"1603.06777","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ad756f53c744cc1d8cf1482b6d8b71387cbda03cf68de9d316711583cee3434","sha256:a93976f0e86e67fe88df1bba7f0351dd583d936c323cac3467d71453fb27eca0"],"state_sha256":"fbf2f2afe0fb100b1a811ee6923d3567194f072baf88df55b629070a3e690af9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xyN4WWdXuqcdIe1hUd77NnP2rTVrqV3ZvSFA88y1ybu21O4JxwOaJAF6xPfRDuKvL5BLxUYLvtrERxYDD40dBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T08:47:30.210032Z","bundle_sha256":"1ed7e4ea3b2464bc58f68371cf0437417664cec6f690e5232672559f6561197d"}}