{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:D42YRUKWNSG75VNEUGE3BAGJKM","short_pith_number":"pith:D42YRUKW","canonical_record":{"source":{"id":"2502.14748","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T17:19:41Z","cross_cats_sorted":[],"title_canon_sha256":"b795085fa91198dba6b975b25f68ebf4459a8826efb85f3322d36cc00272be1a","abstract_canon_sha256":"8e2ad141c8f4dee1209ad9e3dd0180e2a49d2ce7b4418ee0140a1ab56b909d79"},"schema_version":"1.0"},"canonical_sha256":"1f3588d1566c8dfed5a4a189b080c9532b1b521adf82a5b5bcadd626a3820cc5","source":{"kind":"arxiv","id":"2502.14748","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14748","created_at":"2026-07-05T11:15:43Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14748v2","created_at":"2026-07-05T11:15:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14748","created_at":"2026-07-05T11:15:43Z"},{"alias_kind":"pith_short_12","alias_value":"D42YRUKWNSG7","created_at":"2026-07-05T11:15:43Z"},{"alias_kind":"pith_short_16","alias_value":"D42YRUKWNSG75VNE","created_at":"2026-07-05T11:15:43Z"},{"alias_kind":"pith_short_8","alias_value":"D42YRUKW","created_at":"2026-07-05T11:15:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:D42YRUKWNSG75VNEUGE3BAGJKM","target":"record","payload":{"canonical_record":{"source":{"id":"2502.14748","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T17:19:41Z","cross_cats_sorted":[],"title_canon_sha256":"b795085fa91198dba6b975b25f68ebf4459a8826efb85f3322d36cc00272be1a","abstract_canon_sha256":"8e2ad141c8f4dee1209ad9e3dd0180e2a49d2ce7b4418ee0140a1ab56b909d79"},"schema_version":"1.0"},"canonical_sha256":"1f3588d1566c8dfed5a4a189b080c9532b1b521adf82a5b5bcadd626a3820cc5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:43.099335Z","signature_b64":"r+gjbjfjZlZey1xjWKzDbN6v361tFAXMb1Nb2x0S2EGwYL4m8TKxaP/rl41OVu7mzKK1qGPPl8lXAyQOEGrrAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f3588d1566c8dfed5a4a189b080c9532b1b521adf82a5b5bcadd626a3820cc5","last_reissued_at":"2026-07-05T11:15:43.098763Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:43.098763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.14748","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":"2026-07-05T11:15:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RRi6u6MSDMV5NipygS1u2xzQCLeuaazSm+KbOILuUcqXPpruaKNZT/AsExYG8cy/MGpxu3lJFf7WU49NjhS8Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:18:02.186406Z"},"content_sha256":"148e35df7011c90208c656e01cfcf75d6f0f1b19b078805a36e716c88b6d0960","schema_version":"1.0","event_id":"sha256:148e35df7011c90208c656e01cfcf75d6f0f1b19b078805a36e716c88b6d0960"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:D42YRUKWNSG75VNEUGE3BAGJKM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Models Struggle to Describe the Haystack without Human Help: Human-in-the-loop Evaluation of Topic Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alden Dima, Alexander Hoyle, Jordan Boyd-Graber, Juan Francisco Fung, Lorena Calvo-Bartolom\\'e, Paiheng Xu, Zongxia Li","submitted_at":"2025-02-20T17:19:41Z","abstract_excerpt":"A common use of NLP is to facilitate the understanding of large document collections, with a shift from using traditional topic models to Large Language Models. Yet the effectiveness of using LLM for large corpus understanding in real-world applications remains under-explored. This study measures the knowledge users acquire with unsupervised, supervised LLM-based exploratory approaches or traditional topic models on two datasets. While LLM-based methods generate more human-readable topics and show higher average win probabilities than traditional models for data exploration, they produce overl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14748","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/2502.14748/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":"2026-07-05T11:15:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fIf5njRWo1hb8Jafjbe5fxl29v1jZy4YKe0ntxYIvpGDuMr3UUtDfP3EsMdi4HYGMp4OeaOZmvmN80Df5f26BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:18:02.186927Z"},"content_sha256":"c22190738354385c0c0a02b1f7f6fda731be679743d07af9ae5238cbbe6f64c4","schema_version":"1.0","event_id":"sha256:c22190738354385c0c0a02b1f7f6fda731be679743d07af9ae5238cbbe6f64c4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D42YRUKWNSG75VNEUGE3BAGJKM/bundle.json","state_url":"https://pith.science/pith/D42YRUKWNSG75VNEUGE3BAGJKM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D42YRUKWNSG75VNEUGE3BAGJKM/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":"2026-08-05T02:18:02Z","links":{"resolver":"https://pith.science/pith/D42YRUKWNSG75VNEUGE3BAGJKM","bundle":"https://pith.science/pith/D42YRUKWNSG75VNEUGE3BAGJKM/bundle.json","state":"https://pith.science/pith/D42YRUKWNSG75VNEUGE3BAGJKM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D42YRUKWNSG75VNEUGE3BAGJKM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:D42YRUKWNSG75VNEUGE3BAGJKM","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":"8e2ad141c8f4dee1209ad9e3dd0180e2a49d2ce7b4418ee0140a1ab56b909d79","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T17:19:41Z","title_canon_sha256":"b795085fa91198dba6b975b25f68ebf4459a8826efb85f3322d36cc00272be1a"},"schema_version":"1.0","source":{"id":"2502.14748","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14748","created_at":"2026-07-05T11:15:43Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14748v2","created_at":"2026-07-05T11:15:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14748","created_at":"2026-07-05T11:15:43Z"},{"alias_kind":"pith_short_12","alias_value":"D42YRUKWNSG7","created_at":"2026-07-05T11:15:43Z"},{"alias_kind":"pith_short_16","alias_value":"D42YRUKWNSG75VNE","created_at":"2026-07-05T11:15:43Z"},{"alias_kind":"pith_short_8","alias_value":"D42YRUKW","created_at":"2026-07-05T11:15:43Z"}],"graph_snapshots":[{"event_id":"sha256:c22190738354385c0c0a02b1f7f6fda731be679743d07af9ae5238cbbe6f64c4","target":"graph","created_at":"2026-07-05T11:15:43Z","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/2502.14748/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A common use of NLP is to facilitate the understanding of large document collections, with a shift from using traditional topic models to Large Language Models. Yet the effectiveness of using LLM for large corpus understanding in real-world applications remains under-explored. This study measures the knowledge users acquire with unsupervised, supervised LLM-based exploratory approaches or traditional topic models on two datasets. While LLM-based methods generate more human-readable topics and show higher average win probabilities than traditional models for data exploration, they produce overl","authors_text":"Alden Dima, Alexander Hoyle, Jordan Boyd-Graber, Juan Francisco Fung, Lorena Calvo-Bartolom\\'e, Paiheng Xu, Zongxia Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T17:19:41Z","title":"Large Language Models Struggle to Describe the Haystack without Human Help: Human-in-the-loop Evaluation of Topic Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14748","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":"sha256:148e35df7011c90208c656e01cfcf75d6f0f1b19b078805a36e716c88b6d0960","target":"record","created_at":"2026-07-05T11:15:43Z","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":"8e2ad141c8f4dee1209ad9e3dd0180e2a49d2ce7b4418ee0140a1ab56b909d79","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T17:19:41Z","title_canon_sha256":"b795085fa91198dba6b975b25f68ebf4459a8826efb85f3322d36cc00272be1a"},"schema_version":"1.0","source":{"id":"2502.14748","kind":"arxiv","version":2}},"canonical_sha256":"1f3588d1566c8dfed5a4a189b080c9532b1b521adf82a5b5bcadd626a3820cc5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f3588d1566c8dfed5a4a189b080c9532b1b521adf82a5b5bcadd626a3820cc5","first_computed_at":"2026-07-05T11:15:43.098763Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:43.098763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r+gjbjfjZlZey1xjWKzDbN6v361tFAXMb1Nb2x0S2EGwYL4m8TKxaP/rl41OVu7mzKK1qGPPl8lXAyQOEGrrAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:43.099335Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.14748","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:148e35df7011c90208c656e01cfcf75d6f0f1b19b078805a36e716c88b6d0960","sha256:c22190738354385c0c0a02b1f7f6fda731be679743d07af9ae5238cbbe6f64c4"],"state_sha256":"febaaff3b11247c196126b2b60982a61102514a71364e16f054b23c55f95539e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z3+ve4+2tEW6rXrbw3YI6KrnWFaWxyaS4OqXQ6zq12CUttng1RTXTIPtnbQjAFItMraqbk3733oJ8TVMXsJWCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T02:18:02.190656Z","bundle_sha256":"6c92f9438cfb33640051977ba953a489256e569b0010bfe1e0a602f82f06061a"}}