{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:UQGX26DDSMDSOPDG4EJRCVNSIS","short_pith_number":"pith:UQGX26DD","schema_version":"1.0","canonical_sha256":"a40d7d78639307273c66e1131155b24494cfcc69371af62349ce22177b973da5","source":{"kind":"arxiv","id":"2206.15007","version":1},"attestation_state":"computed","paper":{"title":"GSCLIP : A Framework for Explaining Distribution Shifts in Natural Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"James Zou, Weixin Liang, Zhiying Zhu","submitted_at":"2022-06-30T04:06:26Z","abstract_excerpt":"Helping end users comprehend the abstract distribution shifts can greatly facilitate AI deployment. Motivated by this, we propose a novel task, dataset explanation. Given two image data sets, dataset explanation aims to automatically point out their dataset-level distribution shifts with natural language. Current techniques for monitoring distribution shifts provide inadequate information to understand datasets with the goal of improving data quality. Therefore, we introduce GSCLIP, a training-free framework to solve the dataset explanation task. In GSCLIP, we propose the selector as the first"},"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":"2206.15007","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-30T04:06:26Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"62b40d55064253b87e5046f26adbd78396ca412f537f7132dad4445009d58f89","abstract_canon_sha256":"c7de5cbd6979f8438b9d6fb09c1a6f40d11b27eeddb44a3b83a4c6a1671ca47e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:24.078714Z","signature_b64":"fe4+SFtwYA1fFwc2O0t18qaPlLfpE29JTP2R4LI2FhMFD+z6K3jizjPjRqtiECrA8BAaVDnQjnvDUaZbaoInBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a40d7d78639307273c66e1131155b24494cfcc69371af62349ce22177b973da5","last_reissued_at":"2026-07-05T04:36:24.078285Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:24.078285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GSCLIP : A Framework for Explaining Distribution Shifts in Natural Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"James Zou, Weixin Liang, Zhiying Zhu","submitted_at":"2022-06-30T04:06:26Z","abstract_excerpt":"Helping end users comprehend the abstract distribution shifts can greatly facilitate AI deployment. Motivated by this, we propose a novel task, dataset explanation. Given two image data sets, dataset explanation aims to automatically point out their dataset-level distribution shifts with natural language. Current techniques for monitoring distribution shifts provide inadequate information to understand datasets with the goal of improving data quality. Therefore, we introduce GSCLIP, a training-free framework to solve the dataset explanation task. In GSCLIP, we propose the selector as the first"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.15007","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/2206.15007/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":"2206.15007","created_at":"2026-07-05T04:36:24.078370+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.15007v1","created_at":"2026-07-05T04:36:24.078370+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.15007","created_at":"2026-07-05T04:36:24.078370+00:00"},{"alias_kind":"pith_short_12","alias_value":"UQGX26DDSMDS","created_at":"2026-07-05T04:36:24.078370+00:00"},{"alias_kind":"pith_short_16","alias_value":"UQGX26DDSMDSOPDG","created_at":"2026-07-05T04:36:24.078370+00:00"},{"alias_kind":"pith_short_8","alias_value":"UQGX26DD","created_at":"2026-07-05T04:36:24.078370+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03808","citing_title":"Agentic-imodels: Evolving agentic interpretability tools via autoresearch","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00899","citing_title":"LatentDiff: Scaling Semantic Dataset Comparison to Millions of Images","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UQGX26DDSMDSOPDG4EJRCVNSIS","json":"https://pith.science/pith/UQGX26DDSMDSOPDG4EJRCVNSIS.json","graph_json":"https://pith.science/api/pith-number/UQGX26DDSMDSOPDG4EJRCVNSIS/graph.json","events_json":"https://pith.science/api/pith-number/UQGX26DDSMDSOPDG4EJRCVNSIS/events.json","paper":"https://pith.science/paper/UQGX26DD"},"agent_actions":{"view_html":"https://pith.science/pith/UQGX26DDSMDSOPDG4EJRCVNSIS","download_json":"https://pith.science/pith/UQGX26DDSMDSOPDG4EJRCVNSIS.json","view_paper":"https://pith.science/paper/UQGX26DD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.15007&json=true","fetch_graph":"https://pith.science/api/pith-number/UQGX26DDSMDSOPDG4EJRCVNSIS/graph.json","fetch_events":"https://pith.science/api/pith-number/UQGX26DDSMDSOPDG4EJRCVNSIS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UQGX26DDSMDSOPDG4EJRCVNSIS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UQGX26DDSMDSOPDG4EJRCVNSIS/action/storage_attestation","attest_author":"https://pith.science/pith/UQGX26DDSMDSOPDG4EJRCVNSIS/action/author_attestation","sign_citation":"https://pith.science/pith/UQGX26DDSMDSOPDG4EJRCVNSIS/action/citation_signature","submit_replication":"https://pith.science/pith/UQGX26DDSMDSOPDG4EJRCVNSIS/action/replication_record"}},"created_at":"2026-07-05T04:36:24.078370+00:00","updated_at":"2026-07-05T04:36:24.078370+00:00"}