{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:VMJXILSISBZJTF4B4C76SBQO2H","short_pith_number":"pith:VMJXILSI","schema_version":"1.0","canonical_sha256":"ab13742e489072999781e0bfe9060ed1f858775e418e4f6ae2f2ae199cbea99c","source":{"kind":"arxiv","id":"2202.02641","version":2},"attestation_state":"computed","paper":{"title":"Emblaze: Illuminating Machine Learning Representations through Interactive Comparison of Embedding Spaces","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.HC","authors_text":"Adam Perer, Venkatesh Sivaraman, Yiwei Wu","submitted_at":"2022-02-05T21:01:49Z","abstract_excerpt":"Modern machine learning techniques commonly rely on complex, high-dimensional embedding representations to capture underlying structure in the data and improve performance. In order to characterize model flaws and choose a desirable representation, model builders often need to compare across multiple embedding spaces, a challenging analytical task supported by few existing tools. We first interviewed nine embedding experts in a variety of fields to characterize the diverse challenges they face and techniques they use when analyzing embedding spaces. Informed by these perspectives, we developed"},"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":"2202.02641","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2022-02-05T21:01:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b5ab39a3ab0ae4c535613fa799fdb77fd4ad3f9b269bb4158cabbae26a8e7144","abstract_canon_sha256":"399433e30ac1a1e176b609fcaf8b2426da7c7bb7141d7708b68229f28070ed1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:57:43.677576Z","signature_b64":"Oo9TnP97NRWvPciH4ncqKsSlZw1WDA2+YHqsDQz8PAZ1ftnAmAmsCTsed6eyeJgEZV8TeoyolqFd5vsBQh40CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab13742e489072999781e0bfe9060ed1f858775e418e4f6ae2f2ae199cbea99c","last_reissued_at":"2026-07-05T03:57:43.677022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:57:43.677022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Emblaze: Illuminating Machine Learning Representations through Interactive Comparison of Embedding Spaces","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.HC","authors_text":"Adam Perer, Venkatesh Sivaraman, Yiwei Wu","submitted_at":"2022-02-05T21:01:49Z","abstract_excerpt":"Modern machine learning techniques commonly rely on complex, high-dimensional embedding representations to capture underlying structure in the data and improve performance. In order to characterize model flaws and choose a desirable representation, model builders often need to compare across multiple embedding spaces, a challenging analytical task supported by few existing tools. We first interviewed nine embedding experts in a variety of fields to characterize the diverse challenges they face and techniques they use when analyzing embedding spaces. Informed by these perspectives, we developed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.02641","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/2202.02641/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":"2202.02641","created_at":"2026-07-05T03:57:43.677080+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.02641v2","created_at":"2026-07-05T03:57:43.677080+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.02641","created_at":"2026-07-05T03:57:43.677080+00:00"},{"alias_kind":"pith_short_12","alias_value":"VMJXILSISBZJ","created_at":"2026-07-05T03:57:43.677080+00:00"},{"alias_kind":"pith_short_16","alias_value":"VMJXILSISBZJTF4B","created_at":"2026-07-05T03:57:43.677080+00:00"},{"alias_kind":"pith_short_8","alias_value":"VMJXILSI","created_at":"2026-07-05T03:57:43.677080+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/VMJXILSISBZJTF4B4C76SBQO2H","json":"https://pith.science/pith/VMJXILSISBZJTF4B4C76SBQO2H.json","graph_json":"https://pith.science/api/pith-number/VMJXILSISBZJTF4B4C76SBQO2H/graph.json","events_json":"https://pith.science/api/pith-number/VMJXILSISBZJTF4B4C76SBQO2H/events.json","paper":"https://pith.science/paper/VMJXILSI"},"agent_actions":{"view_html":"https://pith.science/pith/VMJXILSISBZJTF4B4C76SBQO2H","download_json":"https://pith.science/pith/VMJXILSISBZJTF4B4C76SBQO2H.json","view_paper":"https://pith.science/paper/VMJXILSI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.02641&json=true","fetch_graph":"https://pith.science/api/pith-number/VMJXILSISBZJTF4B4C76SBQO2H/graph.json","fetch_events":"https://pith.science/api/pith-number/VMJXILSISBZJTF4B4C76SBQO2H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VMJXILSISBZJTF4B4C76SBQO2H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VMJXILSISBZJTF4B4C76SBQO2H/action/storage_attestation","attest_author":"https://pith.science/pith/VMJXILSISBZJTF4B4C76SBQO2H/action/author_attestation","sign_citation":"https://pith.science/pith/VMJXILSISBZJTF4B4C76SBQO2H/action/citation_signature","submit_replication":"https://pith.science/pith/VMJXILSISBZJTF4B4C76SBQO2H/action/replication_record"}},"created_at":"2026-07-05T03:57:43.677080+00:00","updated_at":"2026-07-05T03:57:43.677080+00:00"}