{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:X4FUH5NOGHZJYYC22XLVAJ6QJK","short_pith_number":"pith:X4FUH5NO","canonical_record":{"source":{"id":"1706.06873","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-21T13:00:39Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"fd122a80cc68a746f1b357e86e69f7b4b9f6da407e01399825c8ebb11a344597","abstract_canon_sha256":"07cac6226f494641f7da40a3875fc1b1cc98f8d8869d776e0da0cbd8537d48bf"},"schema_version":"1.0"},"canonical_sha256":"bf0b43f5ae31f29c605ad5d75027d04ab88fbd518fae5f0a7570447885a29ee8","source":{"kind":"arxiv","id":"1706.06873","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.06873","created_at":"2026-05-18T00:41:56Z"},{"alias_kind":"arxiv_version","alias_value":"1706.06873v1","created_at":"2026-05-18T00:41:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.06873","created_at":"2026-05-18T00:41:56Z"},{"alias_kind":"pith_short_12","alias_value":"X4FUH5NOGHZJ","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"X4FUH5NOGHZJYYC2","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"X4FUH5NO","created_at":"2026-05-18T12:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:X4FUH5NOGHZJYYC22XLVAJ6QJK","target":"record","payload":{"canonical_record":{"source":{"id":"1706.06873","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-21T13:00:39Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"fd122a80cc68a746f1b357e86e69f7b4b9f6da407e01399825c8ebb11a344597","abstract_canon_sha256":"07cac6226f494641f7da40a3875fc1b1cc98f8d8869d776e0da0cbd8537d48bf"},"schema_version":"1.0"},"canonical_sha256":"bf0b43f5ae31f29c605ad5d75027d04ab88fbd518fae5f0a7570447885a29ee8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:41:56.687733Z","signature_b64":"/Yh2VtZHw1Fl3og79tDLQJigUhjXt63tHwA94RXDffziNbldjfwU1qnxnCfmI9jz8g0fEuW5PIsWEe7kOqhQAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf0b43f5ae31f29c605ad5d75027d04ab88fbd518fae5f0a7570447885a29ee8","last_reissued_at":"2026-05-18T00:41:56.687258Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:41:56.687258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.06873","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":"2026-05-18T00:41:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xk5tUY99rTsb7yPbtXBwjqYYPRIx7VhdqldYs+/Y7aEnTGHJgulBZboX+rIR/LRwThXQb/PJpSvKzu/LvQ58CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T03:06:14.093078Z"},"content_sha256":"4de490401630d13fd0c6bcb604379a5120f778a0c8197ed6a0aa752158527e7d","schema_version":"1.0","event_id":"sha256:4de490401630d13fd0c6bcb604379a5120f778a0c8197ed6a0aa752158527e7d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:X4FUH5NOGHZJYYC22XLVAJ6QJK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MEC: Memory-efficient Convolution for Deep Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Daniel Brand, Minsik Cho","submitted_at":"2017-06-21T13:00:39Z","abstract_excerpt":"Convolution is a critical component in modern deep neural networks, thus several algorithms for convolution have been developed. Direct convolution is simple but suffers from poor performance. As an alternative, multiple indirect methods have been proposed including im2col-based convolution, FFT-based convolution, or Winograd-based algorithm. However, all these indirect methods have high memory-overhead, which creates performance degradation and offers a poor trade-off between performance and memory consumption. In this work, we propose a memory-efficient convolution or MEC with compact loweri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.06873","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":"2026-05-18T00:41:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PpmK4cdVvPFw0/we7/OnAVKexB7lcyDNGl1B32Ao97uFFqZP24sZ/jvLJMqWKCFPj+K6fC479/q3PyJb6rg6BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T03:06:14.093806Z"},"content_sha256":"7658d56ad3ee5311989b22690eb4c7467272398c4c0ee521b97d7b68f1190f77","schema_version":"1.0","event_id":"sha256:7658d56ad3ee5311989b22690eb4c7467272398c4c0ee521b97d7b68f1190f77"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X4FUH5NOGHZJYYC22XLVAJ6QJK/bundle.json","state_url":"https://pith.science/pith/X4FUH5NOGHZJYYC22XLVAJ6QJK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X4FUH5NOGHZJYYC22XLVAJ6QJK/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":"2026-06-01T03:06:14Z","links":{"resolver":"https://pith.science/pith/X4FUH5NOGHZJYYC22XLVAJ6QJK","bundle":"https://pith.science/pith/X4FUH5NOGHZJYYC22XLVAJ6QJK/bundle.json","state":"https://pith.science/pith/X4FUH5NOGHZJYYC22XLVAJ6QJK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X4FUH5NOGHZJYYC22XLVAJ6QJK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:X4FUH5NOGHZJYYC22XLVAJ6QJK","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":"07cac6226f494641f7da40a3875fc1b1cc98f8d8869d776e0da0cbd8537d48bf","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-21T13:00:39Z","title_canon_sha256":"fd122a80cc68a746f1b357e86e69f7b4b9f6da407e01399825c8ebb11a344597"},"schema_version":"1.0","source":{"id":"1706.06873","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.06873","created_at":"2026-05-18T00:41:56Z"},{"alias_kind":"arxiv_version","alias_value":"1706.06873v1","created_at":"2026-05-18T00:41:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.06873","created_at":"2026-05-18T00:41:56Z"},{"alias_kind":"pith_short_12","alias_value":"X4FUH5NOGHZJ","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"X4FUH5NOGHZJYYC2","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"X4FUH5NO","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:7658d56ad3ee5311989b22690eb4c7467272398c4c0ee521b97d7b68f1190f77","target":"graph","created_at":"2026-05-18T00:41:56Z","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":"Convolution is a critical component in modern deep neural networks, thus several algorithms for convolution have been developed. Direct convolution is simple but suffers from poor performance. As an alternative, multiple indirect methods have been proposed including im2col-based convolution, FFT-based convolution, or Winograd-based algorithm. However, all these indirect methods have high memory-overhead, which creates performance degradation and offers a poor trade-off between performance and memory consumption. In this work, we propose a memory-efficient convolution or MEC with compact loweri","authors_text":"Daniel Brand, Minsik Cho","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-21T13:00:39Z","title":"MEC: Memory-efficient Convolution for Deep Neural Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.06873","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":"sha256:4de490401630d13fd0c6bcb604379a5120f778a0c8197ed6a0aa752158527e7d","target":"record","created_at":"2026-05-18T00:41:56Z","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":"07cac6226f494641f7da40a3875fc1b1cc98f8d8869d776e0da0cbd8537d48bf","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-21T13:00:39Z","title_canon_sha256":"fd122a80cc68a746f1b357e86e69f7b4b9f6da407e01399825c8ebb11a344597"},"schema_version":"1.0","source":{"id":"1706.06873","kind":"arxiv","version":1}},"canonical_sha256":"bf0b43f5ae31f29c605ad5d75027d04ab88fbd518fae5f0a7570447885a29ee8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf0b43f5ae31f29c605ad5d75027d04ab88fbd518fae5f0a7570447885a29ee8","first_computed_at":"2026-05-18T00:41:56.687258Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:41:56.687258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/Yh2VtZHw1Fl3og79tDLQJigUhjXt63tHwA94RXDffziNbldjfwU1qnxnCfmI9jz8g0fEuW5PIsWEe7kOqhQAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:41:56.687733Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.06873","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4de490401630d13fd0c6bcb604379a5120f778a0c8197ed6a0aa752158527e7d","sha256:7658d56ad3ee5311989b22690eb4c7467272398c4c0ee521b97d7b68f1190f77"],"state_sha256":"dde40d240d1ad063dddbdac8b9a59781c2c40ef4decd6f07051cc34a4da0bb09"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B8sBMvtt0Q4wKLjATI9R5NulBwhwXsvY94vEydQQy+lRv819BnqcRSRyjnxdo1q/KnctcI0AteMazW3yWf5+Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T03:06:14.096983Z","bundle_sha256":"d53607a73a0d39fee6f337dc1fb15d9293bbd65eb15107d6b40485d5bec6b7dd"}}