{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:LJGAV3F7LLOADO4CSIOLAPG2BD","short_pith_number":"pith:LJGAV3F7","canonical_record":{"source":{"id":"1905.02649","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-07T15:47:27Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"d4984c2644e34b245eb847328f0c816433643d3168c75b8cdb0d133d1983aa5f","abstract_canon_sha256":"229b62f0181c7822a8c2894ac725e39315cdd4adb5b27269b4d3ae1b8ab1de07"},"schema_version":"1.0"},"canonical_sha256":"5a4c0aecbf5adc01bb82921cb03cda08c330f4f6866b7a74ca714af457efac77","source":{"kind":"arxiv","id":"1905.02649","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.02649","created_at":"2026-05-17T23:46:50Z"},{"alias_kind":"arxiv_version","alias_value":"1905.02649v1","created_at":"2026-05-17T23:46:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.02649","created_at":"2026-05-17T23:46:50Z"},{"alias_kind":"pith_short_12","alias_value":"LJGAV3F7LLOA","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"LJGAV3F7LLOADO4C","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"LJGAV3F7","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:LJGAV3F7LLOADO4CSIOLAPG2BD","target":"record","payload":{"canonical_record":{"source":{"id":"1905.02649","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-07T15:47:27Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"d4984c2644e34b245eb847328f0c816433643d3168c75b8cdb0d133d1983aa5f","abstract_canon_sha256":"229b62f0181c7822a8c2894ac725e39315cdd4adb5b27269b4d3ae1b8ab1de07"},"schema_version":"1.0"},"canonical_sha256":"5a4c0aecbf5adc01bb82921cb03cda08c330f4f6866b7a74ca714af457efac77","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:50.808372Z","signature_b64":"33G0H0KJgG5sqCFqIMioqi7EKm7lt6bZM+In5rLacFo2GJ7yCxIEYBI2AKFAMdvpleA0llt5l4RuN6CMIpdECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a4c0aecbf5adc01bb82921cb03cda08c330f4f6866b7a74ca714af457efac77","last_reissued_at":"2026-05-17T23:46:50.807779Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:50.807779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.02649","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":"2026-05-17T23:46:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1deWF7FgzGnsQRGsPbBbWxOctYFtjhKfAuSXo7d+LJJ6rDfsh/MlLEV/mkDIMgKKXtJ0VDicd7cXtk46UsxCDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T15:22:19.106308Z"},"content_sha256":"4859fae5b5dfae031a14b517342b5bb03361f73da5f68bc0482ae35452ff6e5f","schema_version":"1.0","event_id":"sha256:4859fae5b5dfae031a14b517342b5bb03361f73da5f68bc0482ae35452ff6e5f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:LJGAV3F7LLOADO4CSIOLAPG2BD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"High Frequency Residual Learning for Multi-Scale Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Bowen Cheng, Jianfeng Wang, Lei Zhang, Rong Xiao, Thomas Huang","submitted_at":"2019-05-07T15:47:27Z","abstract_excerpt":"We present a novel high frequency residual learning framework, which leads to a highly efficient multi-scale network (MSNet) architecture for mobile and embedded vision problems. The architecture utilizes two networks: a low resolution network to efficiently approximate low frequency components and a high resolution network to learn high frequency residuals by reusing the upsampled low resolution features. With a classifier calibration module, MSNet can dynamically allocate computation resources during inference to achieve a better speed and accuracy trade-off. We evaluate our methods on the c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.02649","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":"2026-05-17T23:46:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yUKu49JUoO3jQoeFhPVKaysjmHYyLDcgzTokjsd6hpM/aU3BSVvaHhid7dZf9ZzX0/BK91Mu399oGTakqLAEDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T15:22:19.107026Z"},"content_sha256":"2aa19b8e4a3e8dade8e6756aef4c32faa1db0a0e8131b21206177308c489c0e5","schema_version":"1.0","event_id":"sha256:2aa19b8e4a3e8dade8e6756aef4c32faa1db0a0e8131b21206177308c489c0e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LJGAV3F7LLOADO4CSIOLAPG2BD/bundle.json","state_url":"https://pith.science/pith/LJGAV3F7LLOADO4CSIOLAPG2BD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LJGAV3F7LLOADO4CSIOLAPG2BD/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":"2026-06-08T15:22:19Z","links":{"resolver":"https://pith.science/pith/LJGAV3F7LLOADO4CSIOLAPG2BD","bundle":"https://pith.science/pith/LJGAV3F7LLOADO4CSIOLAPG2BD/bundle.json","state":"https://pith.science/pith/LJGAV3F7LLOADO4CSIOLAPG2BD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LJGAV3F7LLOADO4CSIOLAPG2BD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:LJGAV3F7LLOADO4CSIOLAPG2BD","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":"229b62f0181c7822a8c2894ac725e39315cdd4adb5b27269b4d3ae1b8ab1de07","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-07T15:47:27Z","title_canon_sha256":"d4984c2644e34b245eb847328f0c816433643d3168c75b8cdb0d133d1983aa5f"},"schema_version":"1.0","source":{"id":"1905.02649","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.02649","created_at":"2026-05-17T23:46:50Z"},{"alias_kind":"arxiv_version","alias_value":"1905.02649v1","created_at":"2026-05-17T23:46:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.02649","created_at":"2026-05-17T23:46:50Z"},{"alias_kind":"pith_short_12","alias_value":"LJGAV3F7LLOA","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"LJGAV3F7LLOADO4C","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"LJGAV3F7","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:2aa19b8e4a3e8dade8e6756aef4c32faa1db0a0e8131b21206177308c489c0e5","target":"graph","created_at":"2026-05-17T23:46:50Z","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":"We present a novel high frequency residual learning framework, which leads to a highly efficient multi-scale network (MSNet) architecture for mobile and embedded vision problems. The architecture utilizes two networks: a low resolution network to efficiently approximate low frequency components and a high resolution network to learn high frequency residuals by reusing the upsampled low resolution features. With a classifier calibration module, MSNet can dynamically allocate computation resources during inference to achieve a better speed and accuracy trade-off. We evaluate our methods on the c","authors_text":"Bowen Cheng, Jianfeng Wang, Lei Zhang, Rong Xiao, Thomas Huang","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-07T15:47:27Z","title":"High Frequency Residual Learning for Multi-Scale Image Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.02649","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":"sha256:4859fae5b5dfae031a14b517342b5bb03361f73da5f68bc0482ae35452ff6e5f","target":"record","created_at":"2026-05-17T23:46:50Z","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":"229b62f0181c7822a8c2894ac725e39315cdd4adb5b27269b4d3ae1b8ab1de07","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-07T15:47:27Z","title_canon_sha256":"d4984c2644e34b245eb847328f0c816433643d3168c75b8cdb0d133d1983aa5f"},"schema_version":"1.0","source":{"id":"1905.02649","kind":"arxiv","version":1}},"canonical_sha256":"5a4c0aecbf5adc01bb82921cb03cda08c330f4f6866b7a74ca714af457efac77","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a4c0aecbf5adc01bb82921cb03cda08c330f4f6866b7a74ca714af457efac77","first_computed_at":"2026-05-17T23:46:50.807779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:50.807779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"33G0H0KJgG5sqCFqIMioqi7EKm7lt6bZM+In5rLacFo2GJ7yCxIEYBI2AKFAMdvpleA0llt5l4RuN6CMIpdECg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:50.808372Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.02649","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4859fae5b5dfae031a14b517342b5bb03361f73da5f68bc0482ae35452ff6e5f","sha256:2aa19b8e4a3e8dade8e6756aef4c32faa1db0a0e8131b21206177308c489c0e5"],"state_sha256":"204f7e16b8a90d75f1933dfe38d119a940520543f8b184ea587446a59958fbbf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z5XsfK36F4z/I1APiJB12Xi/in3RvxSzZP5/YeVBLNio/Z60xtxkisr2Gs/EaHDbyWY3YOyE4URyTr7uZsreAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T15:22:19.110760Z","bundle_sha256":"4c17c5d3ed8c054176c8a508603558515fc9282d28202df8d5df59da19e16e65"}}