{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HCHZHEO4NX37WJLD4PCPHEJPEM","short_pith_number":"pith:HCHZHEO4","schema_version":"1.0","canonical_sha256":"388f9391dc6df7fb2563e3c4f3912f23348f3529cba28707a4edbcdc99373393","source":{"kind":"arxiv","id":"2211.16960","version":2},"attestation_state":"computed","paper":{"title":"BASiS: Batch Aligned Spectral Embedding Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.SP"],"primary_cat":"cs.CV","authors_text":"Guy Gilboa, Ido Cohen, Or Streicher","submitted_at":"2022-11-30T13:07:59Z","abstract_excerpt":"Graph is a highly generic and diverse representation, suitable for almost any data processing problem. Spectral graph theory has been shown to provide powerful algorithms, backed by solid linear algebra theory. It thus can be extremely instrumental to design deep network building blocks with spectral graph characteristics. For instance, such a network allows the design of optimal graphs for certain tasks or obtaining a canonical orthogonal low-dimensional embedding of the data. Recent attempts to solve this problem were based on minimizing Rayleigh-quotient type losses. We propose a different "},"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":"2211.16960","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-30T13:07:59Z","cross_cats_sorted":["cs.LG","eess.SP"],"title_canon_sha256":"b7affd0dda518e4ea6a50d35598a4d3cb046eb9c97a1fc9958c6b8619a9cac68","abstract_canon_sha256":"b4e234f985fbe42d15ac318de1694aee7e080bca26824a564bb99a65fca7497b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:02:31.255881Z","signature_b64":"1LuXj0TUXClbHuidejfsnk8OLl+T9UqEEx+U4F25s0koy4dcKt97GL/1Vducfa/QKD6S/9uvojs+BAd9XmuxCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"388f9391dc6df7fb2563e3c4f3912f23348f3529cba28707a4edbcdc99373393","last_reissued_at":"2026-07-05T06:02:31.255415Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:02:31.255415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BASiS: Batch Aligned Spectral Embedding Space","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.SP"],"primary_cat":"cs.CV","authors_text":"Guy Gilboa, Ido Cohen, Or Streicher","submitted_at":"2022-11-30T13:07:59Z","abstract_excerpt":"Graph is a highly generic and diverse representation, suitable for almost any data processing problem. Spectral graph theory has been shown to provide powerful algorithms, backed by solid linear algebra theory. It thus can be extremely instrumental to design deep network building blocks with spectral graph characteristics. For instance, such a network allows the design of optimal graphs for certain tasks or obtaining a canonical orthogonal low-dimensional embedding of the data. Recent attempts to solve this problem were based on minimizing Rayleigh-quotient type losses. We propose a different "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.16960","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/2211.16960/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":"2211.16960","created_at":"2026-07-05T06:02:31.255480+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.16960v2","created_at":"2026-07-05T06:02:31.255480+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.16960","created_at":"2026-07-05T06:02:31.255480+00:00"},{"alias_kind":"pith_short_12","alias_value":"HCHZHEO4NX37","created_at":"2026-07-05T06:02:31.255480+00:00"},{"alias_kind":"pith_short_16","alias_value":"HCHZHEO4NX37WJLD","created_at":"2026-07-05T06:02:31.255480+00:00"},{"alias_kind":"pith_short_8","alias_value":"HCHZHEO4","created_at":"2026-07-05T06:02:31.255480+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.11305","citing_title":"Generalizable Spectral Embedding with an Application to UMAP","ref_index":56,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HCHZHEO4NX37WJLD4PCPHEJPEM","json":"https://pith.science/pith/HCHZHEO4NX37WJLD4PCPHEJPEM.json","graph_json":"https://pith.science/api/pith-number/HCHZHEO4NX37WJLD4PCPHEJPEM/graph.json","events_json":"https://pith.science/api/pith-number/HCHZHEO4NX37WJLD4PCPHEJPEM/events.json","paper":"https://pith.science/paper/HCHZHEO4"},"agent_actions":{"view_html":"https://pith.science/pith/HCHZHEO4NX37WJLD4PCPHEJPEM","download_json":"https://pith.science/pith/HCHZHEO4NX37WJLD4PCPHEJPEM.json","view_paper":"https://pith.science/paper/HCHZHEO4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.16960&json=true","fetch_graph":"https://pith.science/api/pith-number/HCHZHEO4NX37WJLD4PCPHEJPEM/graph.json","fetch_events":"https://pith.science/api/pith-number/HCHZHEO4NX37WJLD4PCPHEJPEM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HCHZHEO4NX37WJLD4PCPHEJPEM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HCHZHEO4NX37WJLD4PCPHEJPEM/action/storage_attestation","attest_author":"https://pith.science/pith/HCHZHEO4NX37WJLD4PCPHEJPEM/action/author_attestation","sign_citation":"https://pith.science/pith/HCHZHEO4NX37WJLD4PCPHEJPEM/action/citation_signature","submit_replication":"https://pith.science/pith/HCHZHEO4NX37WJLD4PCPHEJPEM/action/replication_record"}},"created_at":"2026-07-05T06:02:31.255480+00:00","updated_at":"2026-07-05T06:02:31.255480+00:00"}