{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:3VJV7W4MTK4X7ZGLKRVT4HI3L4","short_pith_number":"pith:3VJV7W4M","canonical_record":{"source":{"id":"1807.11783","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-31T12:14:45Z","cross_cats_sorted":[],"title_canon_sha256":"eaa0000c0bb12fcb1512bc7929251ed21f669d21c92e2fbc093aa4af60ed2a5d","abstract_canon_sha256":"2567aa78f201b4260877d9058e386244422c8674f545ea1de23abe49631a016c"},"schema_version":"1.0"},"canonical_sha256":"dd535fdb8c9ab97fe4cb546b3e1d1b5f34a759da688fbe0bea326a05cb9045a4","source":{"kind":"arxiv","id":"1807.11783","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.11783","created_at":"2026-05-18T00:09:21Z"},{"alias_kind":"arxiv_version","alias_value":"1807.11783v1","created_at":"2026-05-18T00:09:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.11783","created_at":"2026-05-18T00:09:21Z"},{"alias_kind":"pith_short_12","alias_value":"3VJV7W4MTK4X","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"3VJV7W4MTK4X7ZGL","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"3VJV7W4M","created_at":"2026-05-18T12:32:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:3VJV7W4MTK4X7ZGLKRVT4HI3L4","target":"record","payload":{"canonical_record":{"source":{"id":"1807.11783","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-31T12:14:45Z","cross_cats_sorted":[],"title_canon_sha256":"eaa0000c0bb12fcb1512bc7929251ed21f669d21c92e2fbc093aa4af60ed2a5d","abstract_canon_sha256":"2567aa78f201b4260877d9058e386244422c8674f545ea1de23abe49631a016c"},"schema_version":"1.0"},"canonical_sha256":"dd535fdb8c9ab97fe4cb546b3e1d1b5f34a759da688fbe0bea326a05cb9045a4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:21.110152Z","signature_b64":"0JgmAnchasX8fi8Cu1F4bOzH0lokvjVaoaPfxlg42Ln81iBsVDQlYlDikNBZjj5//S7e9DzKX1T3zdixp8FaBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd535fdb8c9ab97fe4cb546b3e1d1b5f34a759da688fbe0bea326a05cb9045a4","last_reissued_at":"2026-05-18T00:09:21.109549Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:21.109549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.11783","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":"2026-05-18T00:09:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YpxPM2unUt1zawiMtV2yIHhOkchs0eioUhJpGRRv7ykWM9nboVcQueGNmIZKChm065UveNZdMaaGLHJe5PBMBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T18:02:14.450235Z"},"content_sha256":"6fc81ce99316311efd7bf5d2ef9ecea1d4b3cacb04e2b0cd821b3507efc18c8e","schema_version":"1.0","event_id":"sha256:6fc81ce99316311efd7bf5d2ef9ecea1d4b3cacb04e2b0cd821b3507efc18c8e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:3VJV7W4MTK4X7ZGLKRVT4HI3L4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scale equivariance in CNNs with vector fields","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Benjamin Kellenberger, Devis Tuia, Diego Marcos, Sylvain Lobry","submitted_at":"2018-07-31T12:14:45Z","abstract_excerpt":"We study the effect of injecting local scale equivariance into Convolutional Neural Networks. This is done by applying each convolutional filter at multiple scales. The output is a vector field encoding for the maximally activating scale and the scale itself, which is further processed by the following convolutional layers. This allows all the intermediate representations to be locally scale equivariant. We show that this improves the performance of the model by over $20\\%$ in the scale equivariant task of regressing the scaling factor applied to randomly scaled MNIST digits. Furthermore, we f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.11783","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":"2026-05-18T00:09:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jSwhA9G7uoZ6vwltOT9JeAaABTiOWxZF00c9TNdnBdMbRfv014ant7VzpYda9Z8Chn1WByC8S7Aguny/XGYDDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T18:02:14.450628Z"},"content_sha256":"6ae8f00eec3a15f6719b84db8af5f0bcad5014e0cc532f3ff14e0b1ee6860760","schema_version":"1.0","event_id":"sha256:6ae8f00eec3a15f6719b84db8af5f0bcad5014e0cc532f3ff14e0b1ee6860760"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3VJV7W4MTK4X7ZGLKRVT4HI3L4/bundle.json","state_url":"https://pith.science/pith/3VJV7W4MTK4X7ZGLKRVT4HI3L4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3VJV7W4MTK4X7ZGLKRVT4HI3L4/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":"2026-05-29T18:02:14Z","links":{"resolver":"https://pith.science/pith/3VJV7W4MTK4X7ZGLKRVT4HI3L4","bundle":"https://pith.science/pith/3VJV7W4MTK4X7ZGLKRVT4HI3L4/bundle.json","state":"https://pith.science/pith/3VJV7W4MTK4X7ZGLKRVT4HI3L4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3VJV7W4MTK4X7ZGLKRVT4HI3L4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:3VJV7W4MTK4X7ZGLKRVT4HI3L4","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":"2567aa78f201b4260877d9058e386244422c8674f545ea1de23abe49631a016c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-31T12:14:45Z","title_canon_sha256":"eaa0000c0bb12fcb1512bc7929251ed21f669d21c92e2fbc093aa4af60ed2a5d"},"schema_version":"1.0","source":{"id":"1807.11783","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.11783","created_at":"2026-05-18T00:09:21Z"},{"alias_kind":"arxiv_version","alias_value":"1807.11783v1","created_at":"2026-05-18T00:09:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.11783","created_at":"2026-05-18T00:09:21Z"},{"alias_kind":"pith_short_12","alias_value":"3VJV7W4MTK4X","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_16","alias_value":"3VJV7W4MTK4X7ZGL","created_at":"2026-05-18T12:32:05Z"},{"alias_kind":"pith_short_8","alias_value":"3VJV7W4M","created_at":"2026-05-18T12:32:05Z"}],"graph_snapshots":[{"event_id":"sha256:6ae8f00eec3a15f6719b84db8af5f0bcad5014e0cc532f3ff14e0b1ee6860760","target":"graph","created_at":"2026-05-18T00:09:21Z","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 study the effect of injecting local scale equivariance into Convolutional Neural Networks. This is done by applying each convolutional filter at multiple scales. The output is a vector field encoding for the maximally activating scale and the scale itself, which is further processed by the following convolutional layers. This allows all the intermediate representations to be locally scale equivariant. We show that this improves the performance of the model by over $20\\%$ in the scale equivariant task of regressing the scaling factor applied to randomly scaled MNIST digits. Furthermore, we f","authors_text":"Benjamin Kellenberger, Devis Tuia, Diego Marcos, Sylvain Lobry","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-31T12:14:45Z","title":"Scale equivariance in CNNs with vector fields"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.11783","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":"sha256:6fc81ce99316311efd7bf5d2ef9ecea1d4b3cacb04e2b0cd821b3507efc18c8e","target":"record","created_at":"2026-05-18T00:09:21Z","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":"2567aa78f201b4260877d9058e386244422c8674f545ea1de23abe49631a016c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-31T12:14:45Z","title_canon_sha256":"eaa0000c0bb12fcb1512bc7929251ed21f669d21c92e2fbc093aa4af60ed2a5d"},"schema_version":"1.0","source":{"id":"1807.11783","kind":"arxiv","version":1}},"canonical_sha256":"dd535fdb8c9ab97fe4cb546b3e1d1b5f34a759da688fbe0bea326a05cb9045a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd535fdb8c9ab97fe4cb546b3e1d1b5f34a759da688fbe0bea326a05cb9045a4","first_computed_at":"2026-05-18T00:09:21.109549Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:09:21.109549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0JgmAnchasX8fi8Cu1F4bOzH0lokvjVaoaPfxlg42Ln81iBsVDQlYlDikNBZjj5//S7e9DzKX1T3zdixp8FaBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:09:21.110152Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.11783","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6fc81ce99316311efd7bf5d2ef9ecea1d4b3cacb04e2b0cd821b3507efc18c8e","sha256:6ae8f00eec3a15f6719b84db8af5f0bcad5014e0cc532f3ff14e0b1ee6860760"],"state_sha256":"d8abcc44988130760f56bd16b568e2b64f5ee9b7e6e063d136f3e253b97777dd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YA5gqz0boxado3Y0UW2jkX/2KeakY238cn94EgE1Exm2Ej5nG2wIUz35cajaUK34VBnU8EJ4AcW+DYM6W4VTDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T18:02:14.453082Z","bundle_sha256":"bdfee053d197b711e5f8d346f56597803ec1c127bf982dc8daa6981ae8a68953"}}