{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:O7ASTMNZG6YULOMXGGIDJEPVVS","short_pith_number":"pith:O7ASTMNZ","schema_version":"1.0","canonical_sha256":"77c129b1b937b145b99731903491f5aca968a7a4466ed66d570e47252bc6bafd","source":{"kind":"arxiv","id":"2410.23107","version":1},"attestation_state":"computed","paper":{"title":"Decoupling Semantic Similarity from Spatial Alignment for Neural Networks","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Constantin Ulrich, David Zimmerer, Fabian Isensee, Gregor K\\\"ohler, Klaus H. Maier-Hein, Michael Baumgartner, Priyank Jaini, Stefan Denner, Tassilo Wald","submitted_at":"2024-10-30T15:17:58Z","abstract_excerpt":"What representation do deep neural networks learn? How similar are images to each other for neural networks? Despite the overwhelming success of deep learning methods key questions about their internal workings still remain largely unanswered, due to their internal high dimensionality and complexity. To address this, one approach is to measure the similarity of activation responses to various inputs. Representational Similarity Matrices (RSMs) distill this similarity into scalar values for each input pair. These matrices encapsulate the entire similarity structure of a system, indicating which"},"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":"2410.23107","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-30T15:17:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"30eecae337154e539335fb18981b161482ca1c189f3bcb822798f18adf76632a","abstract_canon_sha256":"7b3878b7b2b2c88a30e6cb097ef2c5d3da71999121ab531ce6c561200508960a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:41.138513Z","signature_b64":"uJ0S6Ztc246uC3bR8SqScGW1lZvPLDaUzsbRR8T6niwKFhjJbShLChPTz+MaB3+wxFNxm6KuZvWbXKH3tQxFDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77c129b1b937b145b99731903491f5aca968a7a4466ed66d570e47252bc6bafd","last_reissued_at":"2026-07-05T09:28:41.137978Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:41.137978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoupling Semantic Similarity from Spatial Alignment for Neural Networks","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Constantin Ulrich, David Zimmerer, Fabian Isensee, Gregor K\\\"ohler, Klaus H. Maier-Hein, Michael Baumgartner, Priyank Jaini, Stefan Denner, Tassilo Wald","submitted_at":"2024-10-30T15:17:58Z","abstract_excerpt":"What representation do deep neural networks learn? How similar are images to each other for neural networks? Despite the overwhelming success of deep learning methods key questions about their internal workings still remain largely unanswered, due to their internal high dimensionality and complexity. To address this, one approach is to measure the similarity of activation responses to various inputs. Representational Similarity Matrices (RSMs) distill this similarity into scalar values for each input pair. These matrices encapsulate the entire similarity structure of a system, indicating which"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23107","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/2410.23107/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":"2410.23107","created_at":"2026-07-05T09:28:41.138043+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.23107v1","created_at":"2026-07-05T09:28:41.138043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23107","created_at":"2026-07-05T09:28:41.138043+00:00"},{"alias_kind":"pith_short_12","alias_value":"O7ASTMNZG6YU","created_at":"2026-07-05T09:28:41.138043+00:00"},{"alias_kind":"pith_short_16","alias_value":"O7ASTMNZG6YULOMX","created_at":"2026-07-05T09:28:41.138043+00:00"},{"alias_kind":"pith_short_8","alias_value":"O7ASTMNZ","created_at":"2026-07-05T09:28:41.138043+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O7ASTMNZG6YULOMXGGIDJEPVVS","json":"https://pith.science/pith/O7ASTMNZG6YULOMXGGIDJEPVVS.json","graph_json":"https://pith.science/api/pith-number/O7ASTMNZG6YULOMXGGIDJEPVVS/graph.json","events_json":"https://pith.science/api/pith-number/O7ASTMNZG6YULOMXGGIDJEPVVS/events.json","paper":"https://pith.science/paper/O7ASTMNZ"},"agent_actions":{"view_html":"https://pith.science/pith/O7ASTMNZG6YULOMXGGIDJEPVVS","download_json":"https://pith.science/pith/O7ASTMNZG6YULOMXGGIDJEPVVS.json","view_paper":"https://pith.science/paper/O7ASTMNZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.23107&json=true","fetch_graph":"https://pith.science/api/pith-number/O7ASTMNZG6YULOMXGGIDJEPVVS/graph.json","fetch_events":"https://pith.science/api/pith-number/O7ASTMNZG6YULOMXGGIDJEPVVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O7ASTMNZG6YULOMXGGIDJEPVVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O7ASTMNZG6YULOMXGGIDJEPVVS/action/storage_attestation","attest_author":"https://pith.science/pith/O7ASTMNZG6YULOMXGGIDJEPVVS/action/author_attestation","sign_citation":"https://pith.science/pith/O7ASTMNZG6YULOMXGGIDJEPVVS/action/citation_signature","submit_replication":"https://pith.science/pith/O7ASTMNZG6YULOMXGGIDJEPVVS/action/replication_record"}},"created_at":"2026-07-05T09:28:41.138043+00:00","updated_at":"2026-07-05T09:28:41.138043+00:00"}