{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MWIWZ4AUKBPYYSSRD3QHF57RWI","short_pith_number":"pith:MWIWZ4AU","schema_version":"1.0","canonical_sha256":"65916cf014505f8c4a511ee072f7f1b235b092903736dc41aef8a5b5bac594df","source":{"kind":"arxiv","id":"2110.15355","version":1},"attestation_state":"computed","paper":{"title":"Explaining Latent Representations with a Corpus of Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.LG","authors_text":"Fergus Imrie, Jonathan Crabb\\'e, Mihaela van der Schaar, Zhaozhi Qian","submitted_at":"2021-10-28T17:59:06Z","abstract_excerpt":"Modern machine learning models are complicated. Most of them rely on convoluted latent representations of their input to issue a prediction. To achieve greater transparency than a black-box that connects inputs to predictions, it is necessary to gain a deeper understanding of these latent representations. To that aim, we propose SimplEx: a user-centred method that provides example-based explanations with reference to a freely selected set of examples, called the corpus. SimplEx uses the corpus to improve the user's understanding of the latent space with post-hoc explanations answering two ques"},"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":"2110.15355","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-28T17:59:06Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"fcce58b2ad70f1b5d9ff9ce457735ccc18daf18d350c6794cd9cdf66063fdb6c","abstract_canon_sha256":"877c5cf539cb1b6d73366f5ddb429db1d5511ce81e25227c476851bf9b303c3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:54.655083Z","signature_b64":"BXT0LlO9uz5Yrbrfcrl64JC+acdlAbpYmbuYp0fcG8caZQDvCmDzdJaCMWb0N18gCxWrrRcNLu/W6SDCFwbOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65916cf014505f8c4a511ee072f7f1b235b092903736dc41aef8a5b5bac594df","last_reissued_at":"2026-07-05T03:26:54.654555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:54.654555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explaining Latent Representations with a Corpus of Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.LG","authors_text":"Fergus Imrie, Jonathan Crabb\\'e, Mihaela van der Schaar, Zhaozhi Qian","submitted_at":"2021-10-28T17:59:06Z","abstract_excerpt":"Modern machine learning models are complicated. Most of them rely on convoluted latent representations of their input to issue a prediction. To achieve greater transparency than a black-box that connects inputs to predictions, it is necessary to gain a deeper understanding of these latent representations. To that aim, we propose SimplEx: a user-centred method that provides example-based explanations with reference to a freely selected set of examples, called the corpus. SimplEx uses the corpus to improve the user's understanding of the latent space with post-hoc explanations answering two ques"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.15355","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/2110.15355/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":"2110.15355","created_at":"2026-07-05T03:26:54.654616+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.15355v1","created_at":"2026-07-05T03:26:54.654616+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.15355","created_at":"2026-07-05T03:26:54.654616+00:00"},{"alias_kind":"pith_short_12","alias_value":"MWIWZ4AUKBPY","created_at":"2026-07-05T03:26:54.654616+00:00"},{"alias_kind":"pith_short_16","alias_value":"MWIWZ4AUKBPYYSSR","created_at":"2026-07-05T03:26:54.654616+00:00"},{"alias_kind":"pith_short_8","alias_value":"MWIWZ4AU","created_at":"2026-07-05T03:26:54.654616+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/MWIWZ4AUKBPYYSSRD3QHF57RWI","json":"https://pith.science/pith/MWIWZ4AUKBPYYSSRD3QHF57RWI.json","graph_json":"https://pith.science/api/pith-number/MWIWZ4AUKBPYYSSRD3QHF57RWI/graph.json","events_json":"https://pith.science/api/pith-number/MWIWZ4AUKBPYYSSRD3QHF57RWI/events.json","paper":"https://pith.science/paper/MWIWZ4AU"},"agent_actions":{"view_html":"https://pith.science/pith/MWIWZ4AUKBPYYSSRD3QHF57RWI","download_json":"https://pith.science/pith/MWIWZ4AUKBPYYSSRD3QHF57RWI.json","view_paper":"https://pith.science/paper/MWIWZ4AU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.15355&json=true","fetch_graph":"https://pith.science/api/pith-number/MWIWZ4AUKBPYYSSRD3QHF57RWI/graph.json","fetch_events":"https://pith.science/api/pith-number/MWIWZ4AUKBPYYSSRD3QHF57RWI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MWIWZ4AUKBPYYSSRD3QHF57RWI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MWIWZ4AUKBPYYSSRD3QHF57RWI/action/storage_attestation","attest_author":"https://pith.science/pith/MWIWZ4AUKBPYYSSRD3QHF57RWI/action/author_attestation","sign_citation":"https://pith.science/pith/MWIWZ4AUKBPYYSSRD3QHF57RWI/action/citation_signature","submit_replication":"https://pith.science/pith/MWIWZ4AUKBPYYSSRD3QHF57RWI/action/replication_record"}},"created_at":"2026-07-05T03:26:54.654616+00:00","updated_at":"2026-07-05T03:26:54.654616+00:00"}