{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XL2DCD7QHPKBI7KVIAP4XWU6FW","short_pith_number":"pith:XL2DCD7Q","canonical_record":{"source":{"id":"2405.02363","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-03T05:09:54Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4968c8ca5f42d3ef29db4d2a79f891109172586445e3d462ec36b82311303024","abstract_canon_sha256":"1b11bf2b86cb73236e009c0ea13b68e09edc1d721ae545537eaef81ae6641b72"},"schema_version":"1.0"},"canonical_sha256":"baf4310ff03bd4147d55401fcbda9e2d91e8d890f7d1ef73b478bebc87de4972","source":{"kind":"arxiv","id":"2405.02363","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.02363","created_at":"2026-07-05T08:47:51Z"},{"alias_kind":"arxiv_version","alias_value":"2405.02363v2","created_at":"2026-07-05T08:47:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02363","created_at":"2026-07-05T08:47:51Z"},{"alias_kind":"pith_short_12","alias_value":"XL2DCD7QHPKB","created_at":"2026-07-05T08:47:51Z"},{"alias_kind":"pith_short_16","alias_value":"XL2DCD7QHPKBI7KV","created_at":"2026-07-05T08:47:51Z"},{"alias_kind":"pith_short_8","alias_value":"XL2DCD7Q","created_at":"2026-07-05T08:47:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XL2DCD7QHPKBI7KVIAP4XWU6FW","target":"record","payload":{"canonical_record":{"source":{"id":"2405.02363","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-03T05:09:54Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4968c8ca5f42d3ef29db4d2a79f891109172586445e3d462ec36b82311303024","abstract_canon_sha256":"1b11bf2b86cb73236e009c0ea13b68e09edc1d721ae545537eaef81ae6641b72"},"schema_version":"1.0"},"canonical_sha256":"baf4310ff03bd4147d55401fcbda9e2d91e8d890f7d1ef73b478bebc87de4972","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:47:51.883368Z","signature_b64":"hCFgxyLWyl9RtfUPQdRG2mrf0sbSONlp0DB95CseM+F0qMzzdAsFwYxphb7aDuSr7fnWoN+KR2XznYXkSHpSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"baf4310ff03bd4147d55401fcbda9e2d91e8d890f7d1ef73b478bebc87de4972","last_reissued_at":"2026-07-05T08:47:51.882879Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:47:51.882879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.02363","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:47:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5xX7DBJ6O+/PMLPHCIUyHANv+G+vk3fs71+OROD8PwQj07TTTk6WntvCseTDXe0FpJ09oLnEq0yZ71UGh9L6BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T22:14:29.623903Z"},"content_sha256":"8f31884ce8f06b51b59d5ddc0a7a7bd646e8e799cc0064d665b434ec573c2fbf","schema_version":"1.0","event_id":"sha256:8f31884ce8f06b51b59d5ddc0a7a7bd646e8e799cc0064d665b434ec573c2fbf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XL2DCD7QHPKBI7KVIAP4XWU6FW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM as Dataset Analyst: Subpopulation Structure Discovery with Large Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bocheng Zou, Jiaming Liu, Ruichuan An, Shanghang Zhang, Yiming Tang, Yulin Luo","submitted_at":"2024-05-03T05:09:54Z","abstract_excerpt":"The distribution of subpopulations is an important property hidden within a dataset. Uncovering and analyzing the subpopulation distribution within datasets provides a comprehensive understanding of the datasets, standing as a powerful tool beneficial to various downstream tasks, including Dataset Subpopulation Organization, Subpopulation Shift, and Slice Discovery. Despite its importance, there has been no work that systematically explores the subpopulation distribution of datasets to our knowledge. To address the limitation and solve all the mentioned tasks in a unified way, we introduce a n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02363","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/2405.02363/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:47:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aWD9YcX7oYwyTs8IHDaglH5SDl7F7vSaoqa6HAtZX1AdweJas9Cs99T2Lhk+oUaCmwsQO/ZPqkZ9FgSp6Kw8Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T22:14:29.624826Z"},"content_sha256":"35a26d4f71bdbfe681d6d5d34bb430c43eeb55bb3f943f3f4826f32cc294510b","schema_version":"1.0","event_id":"sha256:35a26d4f71bdbfe681d6d5d34bb430c43eeb55bb3f943f3f4826f32cc294510b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XL2DCD7QHPKBI7KVIAP4XWU6FW/bundle.json","state_url":"https://pith.science/pith/XL2DCD7QHPKBI7KVIAP4XWU6FW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XL2DCD7QHPKBI7KVIAP4XWU6FW/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-21T22:14:29Z","links":{"resolver":"https://pith.science/pith/XL2DCD7QHPKBI7KVIAP4XWU6FW","bundle":"https://pith.science/pith/XL2DCD7QHPKBI7KVIAP4XWU6FW/bundle.json","state":"https://pith.science/pith/XL2DCD7QHPKBI7KVIAP4XWU6FW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XL2DCD7QHPKBI7KVIAP4XWU6FW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XL2DCD7QHPKBI7KVIAP4XWU6FW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1b11bf2b86cb73236e009c0ea13b68e09edc1d721ae545537eaef81ae6641b72","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-03T05:09:54Z","title_canon_sha256":"4968c8ca5f42d3ef29db4d2a79f891109172586445e3d462ec36b82311303024"},"schema_version":"1.0","source":{"id":"2405.02363","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.02363","created_at":"2026-07-05T08:47:51Z"},{"alias_kind":"arxiv_version","alias_value":"2405.02363v2","created_at":"2026-07-05T08:47:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.02363","created_at":"2026-07-05T08:47:51Z"},{"alias_kind":"pith_short_12","alias_value":"XL2DCD7QHPKB","created_at":"2026-07-05T08:47:51Z"},{"alias_kind":"pith_short_16","alias_value":"XL2DCD7QHPKBI7KV","created_at":"2026-07-05T08:47:51Z"},{"alias_kind":"pith_short_8","alias_value":"XL2DCD7Q","created_at":"2026-07-05T08:47:51Z"}],"graph_snapshots":[{"event_id":"sha256:35a26d4f71bdbfe681d6d5d34bb430c43eeb55bb3f943f3f4826f32cc294510b","target":"graph","created_at":"2026-07-05T08:47:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2405.02363/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The distribution of subpopulations is an important property hidden within a dataset. Uncovering and analyzing the subpopulation distribution within datasets provides a comprehensive understanding of the datasets, standing as a powerful tool beneficial to various downstream tasks, including Dataset Subpopulation Organization, Subpopulation Shift, and Slice Discovery. Despite its importance, there has been no work that systematically explores the subpopulation distribution of datasets to our knowledge. To address the limitation and solve all the mentioned tasks in a unified way, we introduce a n","authors_text":"Bocheng Zou, Jiaming Liu, Ruichuan An, Shanghang Zhang, Yiming Tang, Yulin Luo","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-03T05:09:54Z","title":"LLM as Dataset Analyst: Subpopulation Structure Discovery with Large Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.02363","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8f31884ce8f06b51b59d5ddc0a7a7bd646e8e799cc0064d665b434ec573c2fbf","target":"record","created_at":"2026-07-05T08:47:51Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1b11bf2b86cb73236e009c0ea13b68e09edc1d721ae545537eaef81ae6641b72","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-03T05:09:54Z","title_canon_sha256":"4968c8ca5f42d3ef29db4d2a79f891109172586445e3d462ec36b82311303024"},"schema_version":"1.0","source":{"id":"2405.02363","kind":"arxiv","version":2}},"canonical_sha256":"baf4310ff03bd4147d55401fcbda9e2d91e8d890f7d1ef73b478bebc87de4972","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"baf4310ff03bd4147d55401fcbda9e2d91e8d890f7d1ef73b478bebc87de4972","first_computed_at":"2026-07-05T08:47:51.882879Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:47:51.882879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hCFgxyLWyl9RtfUPQdRG2mrf0sbSONlp0DB95CseM+F0qMzzdAsFwYxphb7aDuSr7fnWoN+KR2XznYXkSHpSAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:47:51.883368Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.02363","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f31884ce8f06b51b59d5ddc0a7a7bd646e8e799cc0064d665b434ec573c2fbf","sha256:35a26d4f71bdbfe681d6d5d34bb430c43eeb55bb3f943f3f4826f32cc294510b"],"state_sha256":"f8ff3febc49e5c1be3b29096a2c4c2a91a8a58d0ad2b5f5b95fdd2e7c21fe410"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qQYL8vAGQIjc0Wsd+aHVY5Sef8N0BAhaF8AireQlVaQ3z9TONQR5wPThr9tEsnWiWkgJtdWNOKwQpyLf3cTNBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T22:14:29.630567Z","bundle_sha256":"1af3c50453a8ef000a23a26a8da336b2bb0ab072cfa36e47a888565b603c96ba"}}