{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3WJR2RI56JIBLVQHI4FSJLB6DV","short_pith_number":"pith:3WJR2RI5","schema_version":"1.0","canonical_sha256":"dd931d451df25015d607470b24ac3e1d69bbbad95193ad04b832155a4af2d202","source":{"kind":"arxiv","id":"2411.04512","version":1},"attestation_state":"computed","paper":{"title":"Normalized Space Alignment: A Versatile Metric for Representation Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aditya Gulati, Ambuj Singh, Danish Ebadulla","submitted_at":"2024-11-07T08:10:28Z","abstract_excerpt":"We introduce a manifold analysis technique for neural network representations. Normalized Space Alignment (NSA) compares pairwise distances between two point clouds derived from the same source and having the same size, while potentially possessing differing dimensionalities. NSA can act as both an analytical tool and a differentiable loss function, providing a robust means of comparing and aligning representations across different layers and models. It satisfies the criteria necessary for both a similarity metric and a neural network loss function. We showcase NSA's versatility by illustratin"},"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":"2411.04512","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-07T08:10:28Z","cross_cats_sorted":[],"title_canon_sha256":"c8dcaf376cb0c1d0d1d78bbeffa95730a7dced80b13946e94ea0c1f526c1085c","abstract_canon_sha256":"2027a349d6ef6901a5501e174ba42c4517dfc7d7877ff394c1126c501a41489e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:32:20.815796Z","signature_b64":"oRkZhEAnHzt7ikID42IgBEf9mXZntN8C9BVDGueQjnRZFwcu3Q/6XJFXmPcMH5/xVGJ4A2w/fmwvKJvQfpA9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd931d451df25015d607470b24ac3e1d69bbbad95193ad04b832155a4af2d202","last_reissued_at":"2026-07-05T09:32:20.815333Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:32:20.815333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Normalized Space Alignment: A Versatile Metric for Representation Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aditya Gulati, Ambuj Singh, Danish Ebadulla","submitted_at":"2024-11-07T08:10:28Z","abstract_excerpt":"We introduce a manifold analysis technique for neural network representations. Normalized Space Alignment (NSA) compares pairwise distances between two point clouds derived from the same source and having the same size, while potentially possessing differing dimensionalities. NSA can act as both an analytical tool and a differentiable loss function, providing a robust means of comparing and aligning representations across different layers and models. It satisfies the criteria necessary for both a similarity metric and a neural network loss function. We showcase NSA's versatility by illustratin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04512","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/2411.04512/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":"2411.04512","created_at":"2026-07-05T09:32:20.815393+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.04512v1","created_at":"2026-07-05T09:32:20.815393+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04512","created_at":"2026-07-05T09:32:20.815393+00:00"},{"alias_kind":"pith_short_12","alias_value":"3WJR2RI56JIB","created_at":"2026-07-05T09:32:20.815393+00:00"},{"alias_kind":"pith_short_16","alias_value":"3WJR2RI56JIBLVQH","created_at":"2026-07-05T09:32:20.815393+00:00"},{"alias_kind":"pith_short_8","alias_value":"3WJR2RI5","created_at":"2026-07-05T09:32:20.815393+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/3WJR2RI56JIBLVQHI4FSJLB6DV","json":"https://pith.science/pith/3WJR2RI56JIBLVQHI4FSJLB6DV.json","graph_json":"https://pith.science/api/pith-number/3WJR2RI56JIBLVQHI4FSJLB6DV/graph.json","events_json":"https://pith.science/api/pith-number/3WJR2RI56JIBLVQHI4FSJLB6DV/events.json","paper":"https://pith.science/paper/3WJR2RI5"},"agent_actions":{"view_html":"https://pith.science/pith/3WJR2RI56JIBLVQHI4FSJLB6DV","download_json":"https://pith.science/pith/3WJR2RI56JIBLVQHI4FSJLB6DV.json","view_paper":"https://pith.science/paper/3WJR2RI5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.04512&json=true","fetch_graph":"https://pith.science/api/pith-number/3WJR2RI56JIBLVQHI4FSJLB6DV/graph.json","fetch_events":"https://pith.science/api/pith-number/3WJR2RI56JIBLVQHI4FSJLB6DV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3WJR2RI56JIBLVQHI4FSJLB6DV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3WJR2RI56JIBLVQHI4FSJLB6DV/action/storage_attestation","attest_author":"https://pith.science/pith/3WJR2RI56JIBLVQHI4FSJLB6DV/action/author_attestation","sign_citation":"https://pith.science/pith/3WJR2RI56JIBLVQHI4FSJLB6DV/action/citation_signature","submit_replication":"https://pith.science/pith/3WJR2RI56JIBLVQHI4FSJLB6DV/action/replication_record"}},"created_at":"2026-07-05T09:32:20.815393+00:00","updated_at":"2026-07-05T09:32:20.815393+00:00"}