{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RCKTNSGJBNBZQSWYQRQKBIE44H","short_pith_number":"pith:RCKTNSGJ","canonical_record":{"source":{"id":"2401.15042","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-26T18:12:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"031665ce233518e23353cc6f7f3e5a15e8f55e36b92daab0924c1d48911dfe8b","abstract_canon_sha256":"edd879024f7cdf4eb4425fa1e1d6b1928c1c6fdb4df10fe1b18ed08856f2d113"},"schema_version":"1.0"},"canonical_sha256":"889536c8c90b43984ad88460a0a09ce1dd31287ff0ea49518de7ffd518e96833","source":{"kind":"arxiv","id":"2401.15042","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.15042","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"arxiv_version","alias_value":"2401.15042v4","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.15042","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"pith_short_12","alias_value":"RCKTNSGJBNBZ","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"pith_short_16","alias_value":"RCKTNSGJBNBZQSWY","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"pith_short_8","alias_value":"RCKTNSGJ","created_at":"2026-07-05T08:27:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RCKTNSGJBNBZQSWYQRQKBIE44H","target":"record","payload":{"canonical_record":{"source":{"id":"2401.15042","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-26T18:12:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"031665ce233518e23353cc6f7f3e5a15e8f55e36b92daab0924c1d48911dfe8b","abstract_canon_sha256":"edd879024f7cdf4eb4425fa1e1d6b1928c1c6fdb4df10fe1b18ed08856f2d113"},"schema_version":"1.0"},"canonical_sha256":"889536c8c90b43984ad88460a0a09ce1dd31287ff0ea49518de7ffd518e96833","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:02.884899Z","signature_b64":"COLSC5v8ZXYiree+91qalNaRwdGN5/w0nM3vd/nkMCYkyA1Q1FrGF4FwcuLg++XXFChdOx7d1c++MNYKUf40AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"889536c8c90b43984ad88460a0a09ce1dd31287ff0ea49518de7ffd518e96833","last_reissued_at":"2026-07-05T08:27:02.884421Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:02.884421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.15042","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:27:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XZNyY4TKRFjW7hgZtjpPvBy9mwpz3wbpbyerSyC38KEGc6JITIQ0yfj5WYXGKPZ1+meJpo10/wheek0kMowOBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:53:18.465476Z"},"content_sha256":"351aaecbd446ef5b0000069b66d1612b765fd8b8deb243136abba1385dd24765","schema_version":"1.0","event_id":"sha256:351aaecbd446ef5b0000069b66d1612b765fd8b8deb243136abba1385dd24765"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RCKTNSGJBNBZQSWYQRQKBIE44H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PROXYQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haochen Tan, Lifeng Shang, Linqi Song, Lu Xu, Qun Liu, Xiaoguang Li, Yasheng Wang, Yunlong Feng, Zhan Shi, Zhijiang Guo, Zhili Liu","submitted_at":"2024-01-26T18:12:25Z","abstract_excerpt":"Large Language Models (LLMs) have succeeded remarkably in understanding long-form contents. However, exploring their capability for generating long-form contents, such as reports and articles, has been relatively unexplored and inadequately assessed by existing benchmarks. The prevalent evaluation methods, which predominantly rely on crowdsourcing, are recognized for their labor-intensive nature and lack of efficiency, whereas automated metrics, such as the ROUGE score, demonstrate discordance with human judgment criteria. In this paper, we propose ProxyQA, an innovative framework dedicated to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.15042","kind":"arxiv","version":4},"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/2401.15042/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":"2026-07-05T08:27:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9VqZ2vVW8OFCaGu49cHEcaHfVQAGRdc4vKU6Y9RWjaPnV/mxucXSlyBq7dAtZXB/lTK8AS4Srqp0Tqlih9KPDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:53:18.465960Z"},"content_sha256":"2c08b39b0f06b41120db5858b30749d85e1d2768c09b22a3e745f21f516b97be","schema_version":"1.0","event_id":"sha256:2c08b39b0f06b41120db5858b30749d85e1d2768c09b22a3e745f21f516b97be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RCKTNSGJBNBZQSWYQRQKBIE44H/bundle.json","state_url":"https://pith.science/pith/RCKTNSGJBNBZQSWYQRQKBIE44H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RCKTNSGJBNBZQSWYQRQKBIE44H/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":"2026-08-09T05:53:18Z","links":{"resolver":"https://pith.science/pith/RCKTNSGJBNBZQSWYQRQKBIE44H","bundle":"https://pith.science/pith/RCKTNSGJBNBZQSWYQRQKBIE44H/bundle.json","state":"https://pith.science/pith/RCKTNSGJBNBZQSWYQRQKBIE44H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RCKTNSGJBNBZQSWYQRQKBIE44H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RCKTNSGJBNBZQSWYQRQKBIE44H","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":"edd879024f7cdf4eb4425fa1e1d6b1928c1c6fdb4df10fe1b18ed08856f2d113","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-26T18:12:25Z","title_canon_sha256":"031665ce233518e23353cc6f7f3e5a15e8f55e36b92daab0924c1d48911dfe8b"},"schema_version":"1.0","source":{"id":"2401.15042","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.15042","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"arxiv_version","alias_value":"2401.15042v4","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.15042","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"pith_short_12","alias_value":"RCKTNSGJBNBZ","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"pith_short_16","alias_value":"RCKTNSGJBNBZQSWY","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"pith_short_8","alias_value":"RCKTNSGJ","created_at":"2026-07-05T08:27:02Z"}],"graph_snapshots":[{"event_id":"sha256:2c08b39b0f06b41120db5858b30749d85e1d2768c09b22a3e745f21f516b97be","target":"graph","created_at":"2026-07-05T08:27:02Z","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/2401.15042/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have succeeded remarkably in understanding long-form contents. However, exploring their capability for generating long-form contents, such as reports and articles, has been relatively unexplored and inadequately assessed by existing benchmarks. The prevalent evaluation methods, which predominantly rely on crowdsourcing, are recognized for their labor-intensive nature and lack of efficiency, whereas automated metrics, such as the ROUGE score, demonstrate discordance with human judgment criteria. In this paper, we propose ProxyQA, an innovative framework dedicated to","authors_text":"Haochen Tan, Lifeng Shang, Linqi Song, Lu Xu, Qun Liu, Xiaoguang Li, Yasheng Wang, Yunlong Feng, Zhan Shi, Zhijiang Guo, Zhili Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-26T18:12:25Z","title":"PROXYQA: An Alternative Framework for Evaluating Long-Form Text Generation with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.15042","kind":"arxiv","version":4},"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":"sha256:351aaecbd446ef5b0000069b66d1612b765fd8b8deb243136abba1385dd24765","target":"record","created_at":"2026-07-05T08:27:02Z","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":"edd879024f7cdf4eb4425fa1e1d6b1928c1c6fdb4df10fe1b18ed08856f2d113","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-26T18:12:25Z","title_canon_sha256":"031665ce233518e23353cc6f7f3e5a15e8f55e36b92daab0924c1d48911dfe8b"},"schema_version":"1.0","source":{"id":"2401.15042","kind":"arxiv","version":4}},"canonical_sha256":"889536c8c90b43984ad88460a0a09ce1dd31287ff0ea49518de7ffd518e96833","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"889536c8c90b43984ad88460a0a09ce1dd31287ff0ea49518de7ffd518e96833","first_computed_at":"2026-07-05T08:27:02.884421Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:02.884421Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"COLSC5v8ZXYiree+91qalNaRwdGN5/w0nM3vd/nkMCYkyA1Q1FrGF4FwcuLg++XXFChdOx7d1c++MNYKUf40AA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:02.884899Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.15042","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:351aaecbd446ef5b0000069b66d1612b765fd8b8deb243136abba1385dd24765","sha256:2c08b39b0f06b41120db5858b30749d85e1d2768c09b22a3e745f21f516b97be"],"state_sha256":"c10707576d3199928d77a7ef1fec1ced443bd290930eb9b206aad3ad7183fa61"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y3O5OO2Ye/rpc3TCBl7jaGU9IDVPZ2meDE0CC6EZVd6J6rs8L35C5yXUfAr39TLf/82iRgckPPFjzcHRDSjpDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T05:53:18.469237Z","bundle_sha256":"d4955f2ee09af95989fe85e52713ad64bb1bdcb5455e78b764ab2402220ec909"}}