{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:DZCCT5HJTNKDQBKCMQDTSSCEJW","short_pith_number":"pith:DZCCT5HJ","canonical_record":{"source":{"id":"1906.11367","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-26T22:24:56Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"2401218192f54c5c8aa867e3e3884b1e3d9d6ebcce02a03adf1748fa93b67955","abstract_canon_sha256":"1eae473dc86e9bb385eed5f0bb2d76e1abb40835cae37479e9b270a2a14aea92"},"schema_version":"1.0"},"canonical_sha256":"1e4429f4e99b5438054264073948444daaa572e7337af69fa16e7a20bf9f1189","source":{"kind":"arxiv","id":"1906.11367","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.11367","created_at":"2026-05-17T23:42:07Z"},{"alias_kind":"arxiv_version","alias_value":"1906.11367v1","created_at":"2026-05-17T23:42:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.11367","created_at":"2026-05-17T23:42:07Z"},{"alias_kind":"pith_short_12","alias_value":"DZCCT5HJTNKD","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"DZCCT5HJTNKDQBKC","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"DZCCT5HJ","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:DZCCT5HJTNKDQBKCMQDTSSCEJW","target":"record","payload":{"canonical_record":{"source":{"id":"1906.11367","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-26T22:24:56Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"2401218192f54c5c8aa867e3e3884b1e3d9d6ebcce02a03adf1748fa93b67955","abstract_canon_sha256":"1eae473dc86e9bb385eed5f0bb2d76e1abb40835cae37479e9b270a2a14aea92"},"schema_version":"1.0"},"canonical_sha256":"1e4429f4e99b5438054264073948444daaa572e7337af69fa16e7a20bf9f1189","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:07.350730Z","signature_b64":"cu9JMMzlE+iiw6kgegsFNA3l4+UDpzNh/pRtYJMesdqqiJG8QFpCDO3hvIs4FZHB1yk73coGwFcIlxog8pQyAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e4429f4e99b5438054264073948444daaa572e7337af69fa16e7a20bf9f1189","last_reissued_at":"2026-05-17T23:42:07.350028Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:07.350028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.11367","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":"2026-05-17T23:42:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/NOfLMOtAhVcNEbmNCkLb5uvxidrSvfIQGfNahAhHsPCaAjRQXAHtfua2RTvE1/jQCdUZgEp1iPFZPT+OSIJBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T05:48:11.515914Z"},"content_sha256":"a3453c706ac688a6e7d34a736e116830054a0aeac6f6262f730f57ca16b2686c","schema_version":"1.0","event_id":"sha256:a3453c706ac688a6e7d34a736e116830054a0aeac6f6262f730f57ca16b2686c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:DZCCT5HJTNKDQBKCMQDTSSCEJW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Accelerating Large-Kernel Convolution Using Summed-Area Tables","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Linguang Zhang, Maciej Halber, Szymon Rusinkiewicz","submitted_at":"2019-06-26T22:24:56Z","abstract_excerpt":"Expanding the receptive field to capture large-scale context is key to obtaining good performance in dense prediction tasks, such as human pose estimation. While many state-of-the-art fully-convolutional architectures enlarge the receptive field by reducing resolution using strided convolution or pooling layers, the most straightforward strategy is adopting large filters. This, however, is costly because of the quadratic increase in the number of parameters and multiply-add operations. In this work, we explore using learnable box filters to allow for convolution with arbitrarily large kernel s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.11367","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":"2026-05-17T23:42:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/HRKQ64dOCIQkmGlUU4zV6prk2hTCCDaa2Qvs7J5TxzAdHQfhUGt8zLQZxeglTKa+2Qh2WsZ5yJ5MD2RQHFdCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T05:48:11.516259Z"},"content_sha256":"544c3718465165877ce8b61d400f2157f29def395f8b774e9ed683af00ff163f","schema_version":"1.0","event_id":"sha256:544c3718465165877ce8b61d400f2157f29def395f8b774e9ed683af00ff163f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DZCCT5HJTNKDQBKCMQDTSSCEJW/bundle.json","state_url":"https://pith.science/pith/DZCCT5HJTNKDQBKCMQDTSSCEJW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DZCCT5HJTNKDQBKCMQDTSSCEJW/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":"2026-05-31T05:48:11Z","links":{"resolver":"https://pith.science/pith/DZCCT5HJTNKDQBKCMQDTSSCEJW","bundle":"https://pith.science/pith/DZCCT5HJTNKDQBKCMQDTSSCEJW/bundle.json","state":"https://pith.science/pith/DZCCT5HJTNKDQBKCMQDTSSCEJW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DZCCT5HJTNKDQBKCMQDTSSCEJW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:DZCCT5HJTNKDQBKCMQDTSSCEJW","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":"1eae473dc86e9bb385eed5f0bb2d76e1abb40835cae37479e9b270a2a14aea92","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-26T22:24:56Z","title_canon_sha256":"2401218192f54c5c8aa867e3e3884b1e3d9d6ebcce02a03adf1748fa93b67955"},"schema_version":"1.0","source":{"id":"1906.11367","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.11367","created_at":"2026-05-17T23:42:07Z"},{"alias_kind":"arxiv_version","alias_value":"1906.11367v1","created_at":"2026-05-17T23:42:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.11367","created_at":"2026-05-17T23:42:07Z"},{"alias_kind":"pith_short_12","alias_value":"DZCCT5HJTNKD","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"DZCCT5HJTNKDQBKC","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"DZCCT5HJ","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:544c3718465165877ce8b61d400f2157f29def395f8b774e9ed683af00ff163f","target":"graph","created_at":"2026-05-17T23:42:07Z","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":"Expanding the receptive field to capture large-scale context is key to obtaining good performance in dense prediction tasks, such as human pose estimation. While many state-of-the-art fully-convolutional architectures enlarge the receptive field by reducing resolution using strided convolution or pooling layers, the most straightforward strategy is adopting large filters. This, however, is costly because of the quadratic increase in the number of parameters and multiply-add operations. In this work, we explore using learnable box filters to allow for convolution with arbitrarily large kernel s","authors_text":"Linguang Zhang, Maciej Halber, Szymon Rusinkiewicz","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-26T22:24:56Z","title":"Accelerating Large-Kernel Convolution Using Summed-Area Tables"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.11367","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:a3453c706ac688a6e7d34a736e116830054a0aeac6f6262f730f57ca16b2686c","target":"record","created_at":"2026-05-17T23:42:07Z","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":"1eae473dc86e9bb385eed5f0bb2d76e1abb40835cae37479e9b270a2a14aea92","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-26T22:24:56Z","title_canon_sha256":"2401218192f54c5c8aa867e3e3884b1e3d9d6ebcce02a03adf1748fa93b67955"},"schema_version":"1.0","source":{"id":"1906.11367","kind":"arxiv","version":1}},"canonical_sha256":"1e4429f4e99b5438054264073948444daaa572e7337af69fa16e7a20bf9f1189","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e4429f4e99b5438054264073948444daaa572e7337af69fa16e7a20bf9f1189","first_computed_at":"2026-05-17T23:42:07.350028Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:07.350028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cu9JMMzlE+iiw6kgegsFNA3l4+UDpzNh/pRtYJMesdqqiJG8QFpCDO3hvIs4FZHB1yk73coGwFcIlxog8pQyAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:07.350730Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.11367","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3453c706ac688a6e7d34a736e116830054a0aeac6f6262f730f57ca16b2686c","sha256:544c3718465165877ce8b61d400f2157f29def395f8b774e9ed683af00ff163f"],"state_sha256":"a78ad2f9962ca98f5ef364adf706ac8a17843f0a4913a350cc48657b30728bad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nb1tn+fz7NE/yqPEG5r+CSbitrPsFWI8fX8O7YmYcpga67PtudQMMVSEpfKbtBUtsO4c9METDsjYjMth2i+LCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T05:48:11.518291Z","bundle_sha256":"8e5e047ed95c814804247e302ba4fcc7f3dcd6c98ea87342ca5989960d72ef3e"}}