{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:QZESQVPFVNHIS4P5WH7I6OE74W","short_pith_number":"pith:QZESQVPF","canonical_record":{"source":{"id":"1908.08986","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-12T08:27:49Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"2a6dc8e1e37a909021df8c1e3a72cfe6b5a048143a4ee063ada168e69bdaa16d","abstract_canon_sha256":"6c0279b2b9de04f7b35616a6e8d709acbe5de9b59aaed267048fb2e85c9cdb84"},"schema_version":"1.0"},"canonical_sha256":"86492855e5ab4e8971fdb1fe8f389fe582d76f0b70ff8d8470593ee1ebf1c7af","source":{"kind":"arxiv","id":"1908.08986","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.08986","created_at":"2026-07-04T23:59:35Z"},{"alias_kind":"arxiv_version","alias_value":"1908.08986v1","created_at":"2026-07-04T23:59:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.08986","created_at":"2026-07-04T23:59:35Z"},{"alias_kind":"pith_short_12","alias_value":"QZESQVPFVNHI","created_at":"2026-07-04T23:59:35Z"},{"alias_kind":"pith_short_16","alias_value":"QZESQVPFVNHIS4P5","created_at":"2026-07-04T23:59:35Z"},{"alias_kind":"pith_short_8","alias_value":"QZESQVPF","created_at":"2026-07-04T23:59:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:QZESQVPFVNHIS4P5WH7I6OE74W","target":"record","payload":{"canonical_record":{"source":{"id":"1908.08986","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-12T08:27:49Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"2a6dc8e1e37a909021df8c1e3a72cfe6b5a048143a4ee063ada168e69bdaa16d","abstract_canon_sha256":"6c0279b2b9de04f7b35616a6e8d709acbe5de9b59aaed267048fb2e85c9cdb84"},"schema_version":"1.0"},"canonical_sha256":"86492855e5ab4e8971fdb1fe8f389fe582d76f0b70ff8d8470593ee1ebf1c7af","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:59:35.565103Z","signature_b64":"f4rku3aNmZNqQIXLnqa6quLpQQSxYCNaCR1TgdYGXY1lWNVTWuJ5xI+fGKXhEGAg+blJlZgF2tBlJahdmcnZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86492855e5ab4e8971fdb1fe8f389fe582d76f0b70ff8d8470593ee1ebf1c7af","last_reissued_at":"2026-07-04T23:59:35.564633Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:59:35.564633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.08986","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":"2026-07-04T23:59:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PQbTzXeMqoib1jiQV+6fmJgZiX+4jjBPgcwddKSS70JeSKRiRxo6+FjeR6cWYZ1SKjqRTdlWzIouNFx7v6k9DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T15:35:58.559542Z"},"content_sha256":"221dbb38dfe262c1069f243145740bab6b1198c88e4355db01a890c64580ff38","schema_version":"1.0","event_id":"sha256:221dbb38dfe262c1069f243145740bab6b1198c88e4355db01a890c64580ff38"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:QZESQVPFVNHIS4P5WH7I6OE74W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Berry Weinstein, Daniel Soudry, Elad Hoffer, Itay Hubara, Tal Ben-Nun, Torsten Hoefler","submitted_at":"2019-08-12T08:27:49Z","abstract_excerpt":"Convolutional neural networks (CNNs) are commonly trained using a fixed spatial image size predetermined for a given model. Although trained on images of aspecific size, it is well established that CNNs can be used to evaluate a wide range of image sizes at test time, by adjusting the size of intermediate feature maps. In this work, we describe and evaluate a novel mixed-size training regime that mixes several image sizes at training time. We demonstrate that models trained using our method are more resilient to image size changes and generalize well even on small images. This allows faster in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.08986","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.08986/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":"2026-07-04T23:59:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cOvgd6kbRBHhi7uHpC6p2nXouIgp2boUTDFGCD4oU9Kadi3YtnzIbVP9qwUiavLbomaTxryQfCM5Y7kaQQabDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T15:35:58.560069Z"},"content_sha256":"bf4b750b3e757028b7c1ed3b740c64bdbcad56bdf22b205183f51c4fdccd216c","schema_version":"1.0","event_id":"sha256:bf4b750b3e757028b7c1ed3b740c64bdbcad56bdf22b205183f51c4fdccd216c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QZESQVPFVNHIS4P5WH7I6OE74W/bundle.json","state_url":"https://pith.science/pith/QZESQVPFVNHIS4P5WH7I6OE74W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QZESQVPFVNHIS4P5WH7I6OE74W/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":"2026-08-16T15:35:58Z","links":{"resolver":"https://pith.science/pith/QZESQVPFVNHIS4P5WH7I6OE74W","bundle":"https://pith.science/pith/QZESQVPFVNHIS4P5WH7I6OE74W/bundle.json","state":"https://pith.science/pith/QZESQVPFVNHIS4P5WH7I6OE74W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QZESQVPFVNHIS4P5WH7I6OE74W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QZESQVPFVNHIS4P5WH7I6OE74W","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":"6c0279b2b9de04f7b35616a6e8d709acbe5de9b59aaed267048fb2e85c9cdb84","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-12T08:27:49Z","title_canon_sha256":"2a6dc8e1e37a909021df8c1e3a72cfe6b5a048143a4ee063ada168e69bdaa16d"},"schema_version":"1.0","source":{"id":"1908.08986","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.08986","created_at":"2026-07-04T23:59:35Z"},{"alias_kind":"arxiv_version","alias_value":"1908.08986v1","created_at":"2026-07-04T23:59:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.08986","created_at":"2026-07-04T23:59:35Z"},{"alias_kind":"pith_short_12","alias_value":"QZESQVPFVNHI","created_at":"2026-07-04T23:59:35Z"},{"alias_kind":"pith_short_16","alias_value":"QZESQVPFVNHIS4P5","created_at":"2026-07-04T23:59:35Z"},{"alias_kind":"pith_short_8","alias_value":"QZESQVPF","created_at":"2026-07-04T23:59:35Z"}],"graph_snapshots":[{"event_id":"sha256:bf4b750b3e757028b7c1ed3b740c64bdbcad56bdf22b205183f51c4fdccd216c","target":"graph","created_at":"2026-07-04T23:59:35Z","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/1908.08986/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Convolutional neural networks (CNNs) are commonly trained using a fixed spatial image size predetermined for a given model. Although trained on images of aspecific size, it is well established that CNNs can be used to evaluate a wide range of image sizes at test time, by adjusting the size of intermediate feature maps. In this work, we describe and evaluate a novel mixed-size training regime that mixes several image sizes at training time. We demonstrate that models trained using our method are more resilient to image size changes and generalize well even on small images. This allows faster in","authors_text":"Berry Weinstein, Daniel Soudry, Elad Hoffer, Itay Hubara, Tal Ben-Nun, Torsten Hoefler","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-12T08:27:49Z","title":"Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.08986","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":"sha256:221dbb38dfe262c1069f243145740bab6b1198c88e4355db01a890c64580ff38","target":"record","created_at":"2026-07-04T23:59:35Z","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":"6c0279b2b9de04f7b35616a6e8d709acbe5de9b59aaed267048fb2e85c9cdb84","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-12T08:27:49Z","title_canon_sha256":"2a6dc8e1e37a909021df8c1e3a72cfe6b5a048143a4ee063ada168e69bdaa16d"},"schema_version":"1.0","source":{"id":"1908.08986","kind":"arxiv","version":1}},"canonical_sha256":"86492855e5ab4e8971fdb1fe8f389fe582d76f0b70ff8d8470593ee1ebf1c7af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86492855e5ab4e8971fdb1fe8f389fe582d76f0b70ff8d8470593ee1ebf1c7af","first_computed_at":"2026-07-04T23:59:35.564633Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:59:35.564633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f4rku3aNmZNqQIXLnqa6quLpQQSxYCNaCR1TgdYGXY1lWNVTWuJ5xI+fGKXhEGAg+blJlZgF2tBlJahdmcnZDw==","signature_status":"signed_v1","signed_at":"2026-07-04T23:59:35.565103Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.08986","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:221dbb38dfe262c1069f243145740bab6b1198c88e4355db01a890c64580ff38","sha256:bf4b750b3e757028b7c1ed3b740c64bdbcad56bdf22b205183f51c4fdccd216c"],"state_sha256":"da542ae5ad6abe344c430f1f65dd9d6f40a39407c1808ed8559bdb5614c9f36c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8qknNNqMVApLUKy8eFHOMdB5Une5iwOXljWyAmLTlZwmgJlcwyH2CV/62v7w2g7i06EqFwfywTNvSiCekApxAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T15:35:58.564050Z","bundle_sha256":"9b552c08b88fe383ed22e13dd28ef00038dfaf82e6f8bf7a7e29cb3003c9b128"}}