{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:WF2Q2CRDC34KIMOQGOP545BE2C","short_pith_number":"pith:WF2Q2CRD","canonical_record":{"source":{"id":"1904.04971","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-10T01:46:48Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d741211e7e69efb0de256f8637399b89fdaefd709c72ea93257b16a556f2353c","abstract_canon_sha256":"6012c78a932e016f3fdc1f6c1e16862311410dca0a956a5361a9d59afdd6c47a"},"schema_version":"1.0"},"canonical_sha256":"b1750d0a2316f8a431d0339fde7424d0a41b3093dd2721e9d7348a494a2698f1","source":{"kind":"arxiv","id":"1904.04971","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.04971","created_at":"2026-07-05T01:32:55Z"},{"alias_kind":"arxiv_version","alias_value":"1904.04971v3","created_at":"2026-07-05T01:32:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.04971","created_at":"2026-07-05T01:32:55Z"},{"alias_kind":"pith_short_12","alias_value":"WF2Q2CRDC34K","created_at":"2026-07-05T01:32:55Z"},{"alias_kind":"pith_short_16","alias_value":"WF2Q2CRDC34KIMOQ","created_at":"2026-07-05T01:32:55Z"},{"alias_kind":"pith_short_8","alias_value":"WF2Q2CRD","created_at":"2026-07-05T01:32:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:WF2Q2CRDC34KIMOQGOP545BE2C","target":"record","payload":{"canonical_record":{"source":{"id":"1904.04971","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-10T01:46:48Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d741211e7e69efb0de256f8637399b89fdaefd709c72ea93257b16a556f2353c","abstract_canon_sha256":"6012c78a932e016f3fdc1f6c1e16862311410dca0a956a5361a9d59afdd6c47a"},"schema_version":"1.0"},"canonical_sha256":"b1750d0a2316f8a431d0339fde7424d0a41b3093dd2721e9d7348a494a2698f1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:32:55.930280Z","signature_b64":"B5kwQqm70t8W+SjuQsRL8hnIIZEziyrLLTCS6o9FulfLhAwx58gSkciQ5rdg4q+FS8bybws9J9nSxSVJtuX/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1750d0a2316f8a431d0339fde7424d0a41b3093dd2721e9d7348a494a2698f1","last_reissued_at":"2026-07-05T01:32:55.929873Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:32:55.929873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.04971","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:32:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IW8+mi4RR2is8Q/LAtULZlQMOxsxTCBbQUSIAmJzQ8LtEa5dy62hTdDNz7l6Z/0fQ2q2RKfeyGgD8IIHkg06AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:34:16.391187Z"},"content_sha256":"e87d511e287f78b43e7de7a5be3dc4a65dc95b7cef0436c1fdebfbc8c8d0100b","schema_version":"1.0","event_id":"sha256:e87d511e287f78b43e7de7a5be3dc4a65dc95b7cef0436c1fdebfbc8c8d0100b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:WF2Q2CRDC34KIMOQGOP545BE2C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CondConv: Conditionally Parameterized Convolutions for Efficient Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Brandon Yang, Gabriel Bender, Jiquan Ngiam, Quoc V. Le","submitted_at":"2019-04-10T01:46:48Z","abstract_excerpt":"Convolutional layers are one of the basic building blocks of modern deep neural networks. One fundamental assumption is that convolutional kernels should be shared for all examples in a dataset. We propose conditionally parameterized convolutions (CondConv), which learn specialized convolutional kernels for each example. Replacing normal convolutions with CondConv enables us to increase the size and capacity of a network, while maintaining efficient inference. We demonstrate that scaling networks with CondConv improves the performance and inference cost trade-off of several existing convolutio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.04971","kind":"arxiv","version":3},"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/1904.04971/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":"2026-07-05T01:32:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TCmdRw4EYY71yboN6W9Dw4wVwpm5ewZ0Z5aJBVrxHrPaCFLyGMCYpcB24fxti+UyTDuF2DfjdFrUWzZkWHwcCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T19:34:16.392184Z"},"content_sha256":"aac24311be968a10f43910f517bc30db0fbbe44f0517ae735b3d04d6b93ce3fa","schema_version":"1.0","event_id":"sha256:aac24311be968a10f43910f517bc30db0fbbe44f0517ae735b3d04d6b93ce3fa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WF2Q2CRDC34KIMOQGOP545BE2C/bundle.json","state_url":"https://pith.science/pith/WF2Q2CRDC34KIMOQGOP545BE2C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WF2Q2CRDC34KIMOQGOP545BE2C/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":"2026-08-07T19:34:16Z","links":{"resolver":"https://pith.science/pith/WF2Q2CRDC34KIMOQGOP545BE2C","bundle":"https://pith.science/pith/WF2Q2CRDC34KIMOQGOP545BE2C/bundle.json","state":"https://pith.science/pith/WF2Q2CRDC34KIMOQGOP545BE2C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WF2Q2CRDC34KIMOQGOP545BE2C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:WF2Q2CRDC34KIMOQGOP545BE2C","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":"6012c78a932e016f3fdc1f6c1e16862311410dca0a956a5361a9d59afdd6c47a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-10T01:46:48Z","title_canon_sha256":"d741211e7e69efb0de256f8637399b89fdaefd709c72ea93257b16a556f2353c"},"schema_version":"1.0","source":{"id":"1904.04971","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.04971","created_at":"2026-07-05T01:32:55Z"},{"alias_kind":"arxiv_version","alias_value":"1904.04971v3","created_at":"2026-07-05T01:32:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.04971","created_at":"2026-07-05T01:32:55Z"},{"alias_kind":"pith_short_12","alias_value":"WF2Q2CRDC34K","created_at":"2026-07-05T01:32:55Z"},{"alias_kind":"pith_short_16","alias_value":"WF2Q2CRDC34KIMOQ","created_at":"2026-07-05T01:32:55Z"},{"alias_kind":"pith_short_8","alias_value":"WF2Q2CRD","created_at":"2026-07-05T01:32:55Z"}],"graph_snapshots":[{"event_id":"sha256:aac24311be968a10f43910f517bc30db0fbbe44f0517ae735b3d04d6b93ce3fa","target":"graph","created_at":"2026-07-05T01:32:55Z","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/1904.04971/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Convolutional layers are one of the basic building blocks of modern deep neural networks. One fundamental assumption is that convolutional kernels should be shared for all examples in a dataset. We propose conditionally parameterized convolutions (CondConv), which learn specialized convolutional kernels for each example. Replacing normal convolutions with CondConv enables us to increase the size and capacity of a network, while maintaining efficient inference. We demonstrate that scaling networks with CondConv improves the performance and inference cost trade-off of several existing convolutio","authors_text":"Brandon Yang, Gabriel Bender, Jiquan Ngiam, Quoc V. Le","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-10T01:46:48Z","title":"CondConv: Conditionally Parameterized Convolutions for Efficient Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.04971","kind":"arxiv","version":3},"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:e87d511e287f78b43e7de7a5be3dc4a65dc95b7cef0436c1fdebfbc8c8d0100b","target":"record","created_at":"2026-07-05T01:32:55Z","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":"6012c78a932e016f3fdc1f6c1e16862311410dca0a956a5361a9d59afdd6c47a","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-10T01:46:48Z","title_canon_sha256":"d741211e7e69efb0de256f8637399b89fdaefd709c72ea93257b16a556f2353c"},"schema_version":"1.0","source":{"id":"1904.04971","kind":"arxiv","version":3}},"canonical_sha256":"b1750d0a2316f8a431d0339fde7424d0a41b3093dd2721e9d7348a494a2698f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1750d0a2316f8a431d0339fde7424d0a41b3093dd2721e9d7348a494a2698f1","first_computed_at":"2026-07-05T01:32:55.929873Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:32:55.929873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B5kwQqm70t8W+SjuQsRL8hnIIZEziyrLLTCS6o9FulfLhAwx58gSkciQ5rdg4q+FS8bybws9J9nSxSVJtuX/Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:32:55.930280Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.04971","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e87d511e287f78b43e7de7a5be3dc4a65dc95b7cef0436c1fdebfbc8c8d0100b","sha256:aac24311be968a10f43910f517bc30db0fbbe44f0517ae735b3d04d6b93ce3fa"],"state_sha256":"1cbdc3529235a2de8eb3228a96860004cb05dd6b5243803b45d3c504108a0696"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zu07qd7U1Ff+NHbGNof2M1DokNBAI1HjFl4B9OsCaZ/Z7s8fAmB0EhAnx5UUai9N5+VBxN47h6uu0/SbV6IpCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T19:34:16.397939Z","bundle_sha256":"abe20329a797b75c819636676cc383e02165de46658bc8e6898933dc3687544b"}}