{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KCLJHE2MS4LKHZJSXI2VP4ABX7","short_pith_number":"pith:KCLJHE2M","schema_version":"1.0","canonical_sha256":"509693934c9716a3e532ba3557f001bfd8f59aa2d484ffc9319f9401f1577d07","source":{"kind":"arxiv","id":"2106.02733","version":2},"attestation_state":"computed","paper":{"title":"DISCO: accurate Discrete Scale Convolutions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arnold Smeulders, Artem Moskalev, Ivan Sosnovik","submitted_at":"2021-06-04T21:48:09Z","abstract_excerpt":"Scale is often seen as a given, disturbing factor in many vision tasks. When doing so it is one of the factors why we need more data during learning. In recent work scale equivariance was added to convolutional neural networks. It was shown to be effective for a range of tasks. We aim for accurate scale-equivariant convolutional neural networks (SE-CNNs) applicable for problems where high granularity of scale and small kernel sizes are required. Current SE-CNNs rely on weight sharing and kernel rescaling, the latter of which is accurate for integer scales only. To reach accurate scale equivari"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2106.02733","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-04T21:48:09Z","cross_cats_sorted":[],"title_canon_sha256":"a7d8371c938bdef0f05315fddcdfb459b322737e7bd1d525e8c2f2e93244abb7","abstract_canon_sha256":"96a925f58516097bb08cfb0388730e6125f336aaf296802d9979f814022b956b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:27:32.233164Z","signature_b64":"fRkyFpb0y2foh7uGfZfHE6FjfrbmUT2LXL7mfWHgI34Qle4ty3CS09tbkd8p/PweYW2TItSnlHt0L22uNfZgCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"509693934c9716a3e532ba3557f001bfd8f59aa2d484ffc9319f9401f1577d07","last_reissued_at":"2026-07-05T03:27:32.231562Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:27:32.231562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DISCO: accurate Discrete Scale Convolutions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arnold Smeulders, Artem Moskalev, Ivan Sosnovik","submitted_at":"2021-06-04T21:48:09Z","abstract_excerpt":"Scale is often seen as a given, disturbing factor in many vision tasks. When doing so it is one of the factors why we need more data during learning. In recent work scale equivariance was added to convolutional neural networks. It was shown to be effective for a range of tasks. We aim for accurate scale-equivariant convolutional neural networks (SE-CNNs) applicable for problems where high granularity of scale and small kernel sizes are required. Current SE-CNNs rely on weight sharing and kernel rescaling, the latter of which is accurate for integer scales only. To reach accurate scale equivari"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.02733","kind":"arxiv","version":2},"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/2106.02733/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2106.02733","created_at":"2026-07-05T03:27:32.231622+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.02733v2","created_at":"2026-07-05T03:27:32.231622+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.02733","created_at":"2026-07-05T03:27:32.231622+00:00"},{"alias_kind":"pith_short_12","alias_value":"KCLJHE2MS4LK","created_at":"2026-07-05T03:27:32.231622+00:00"},{"alias_kind":"pith_short_16","alias_value":"KCLJHE2MS4LKHZJS","created_at":"2026-07-05T03:27:32.231622+00:00"},{"alias_kind":"pith_short_8","alias_value":"KCLJHE2M","created_at":"2026-07-05T03:27:32.231622+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18389","citing_title":"Spherical Harmonic Optimal Transport: Application to Climate Models Comparisons","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2509.02139","citing_title":"On sources to variabilities of simple cells in the primary visual cortex: A principled theory for the interaction between geometric image transformations and receptive field responses","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10723","citing_title":"Generalized Spherical Neural Operators: Green's Function Formulation","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KCLJHE2MS4LKHZJSXI2VP4ABX7","json":"https://pith.science/pith/KCLJHE2MS4LKHZJSXI2VP4ABX7.json","graph_json":"https://pith.science/api/pith-number/KCLJHE2MS4LKHZJSXI2VP4ABX7/graph.json","events_json":"https://pith.science/api/pith-number/KCLJHE2MS4LKHZJSXI2VP4ABX7/events.json","paper":"https://pith.science/paper/KCLJHE2M"},"agent_actions":{"view_html":"https://pith.science/pith/KCLJHE2MS4LKHZJSXI2VP4ABX7","download_json":"https://pith.science/pith/KCLJHE2MS4LKHZJSXI2VP4ABX7.json","view_paper":"https://pith.science/paper/KCLJHE2M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.02733&json=true","fetch_graph":"https://pith.science/api/pith-number/KCLJHE2MS4LKHZJSXI2VP4ABX7/graph.json","fetch_events":"https://pith.science/api/pith-number/KCLJHE2MS4LKHZJSXI2VP4ABX7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KCLJHE2MS4LKHZJSXI2VP4ABX7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KCLJHE2MS4LKHZJSXI2VP4ABX7/action/storage_attestation","attest_author":"https://pith.science/pith/KCLJHE2MS4LKHZJSXI2VP4ABX7/action/author_attestation","sign_citation":"https://pith.science/pith/KCLJHE2MS4LKHZJSXI2VP4ABX7/action/citation_signature","submit_replication":"https://pith.science/pith/KCLJHE2MS4LKHZJSXI2VP4ABX7/action/replication_record"}},"created_at":"2026-07-05T03:27:32.231622+00:00","updated_at":"2026-07-05T03:27:32.231622+00:00"}