{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GBLYHK7HBCEBEXULPFOFFUGAZ7","short_pith_number":"pith:GBLYHK7H","schema_version":"1.0","canonical_sha256":"305783abe70888125e8b795c52d0c0cfe33e70fa90f523972c0f2159d2c59d82","source":{"kind":"arxiv","id":"2508.11310","version":1},"attestation_state":"computed","paper":{"title":"SGSimEval: A Comprehensive Multifaceted and Similarity-Enhanced Benchmark for Automatic Survey Generation Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Beichen Guo, Jiaxing Shen, Peng Gao, Ruosong Yang, Yu Yang, Zhiyuan Wen","submitted_at":"2025-08-15T08:27:58Z","abstract_excerpt":"The growing interest in automatic survey generation (ASG), a task that traditionally required considerable time and effort, has been spurred by recent advances in large language models (LLMs). With advancements in retrieval-augmented generation (RAG) and the rising popularity of multi-agent systems (MASs), synthesizing academic surveys using LLMs has become a viable approach, thereby elevating the need for robust evaluation methods in this domain. However, existing evaluation methods suffer from several limitations, including biased metrics, a lack of human preference, and an over-reliance on "},"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":"2508.11310","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-15T08:27:58Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"bb0cd5d5ce8b1ad717b2ec59004902255bd6d3b133b52b17d1d9d507035b7a89","abstract_canon_sha256":"4603ca70a50dacf97f1462383bbb6fba83ea2839c63c5dd10916174c7ed88a9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:22.439686Z","signature_b64":"STwoqGfiT5SHUr1TmEEol2KXnXOBizxAFjGRPzoYagU7XpoXDfTeeZX4ktVag+8G2kGGb3cONtchMbxYyv4cCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"305783abe70888125e8b795c52d0c0cfe33e70fa90f523972c0f2159d2c59d82","last_reissued_at":"2026-07-05T11:54:22.439259Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:22.439259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SGSimEval: A Comprehensive Multifaceted and Similarity-Enhanced Benchmark for Automatic Survey Generation Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Beichen Guo, Jiaxing Shen, Peng Gao, Ruosong Yang, Yu Yang, Zhiyuan Wen","submitted_at":"2025-08-15T08:27:58Z","abstract_excerpt":"The growing interest in automatic survey generation (ASG), a task that traditionally required considerable time and effort, has been spurred by recent advances in large language models (LLMs). With advancements in retrieval-augmented generation (RAG) and the rising popularity of multi-agent systems (MASs), synthesizing academic surveys using LLMs has become a viable approach, thereby elevating the need for robust evaluation methods in this domain. However, existing evaluation methods suffer from several limitations, including biased metrics, a lack of human preference, and an over-reliance on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11310","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/2508.11310/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":"2508.11310","created_at":"2026-07-05T11:54:22.439325+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.11310v1","created_at":"2026-07-05T11:54:22.439325+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11310","created_at":"2026-07-05T11:54:22.439325+00:00"},{"alias_kind":"pith_short_12","alias_value":"GBLYHK7HBCEB","created_at":"2026-07-05T11:54:22.439325+00:00"},{"alias_kind":"pith_short_16","alias_value":"GBLYHK7HBCEBEXUL","created_at":"2026-07-05T11:54:22.439325+00:00"},{"alias_kind":"pith_short_8","alias_value":"GBLYHK7H","created_at":"2026-07-05T11:54:22.439325+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/GBLYHK7HBCEBEXULPFOFFUGAZ7","json":"https://pith.science/pith/GBLYHK7HBCEBEXULPFOFFUGAZ7.json","graph_json":"https://pith.science/api/pith-number/GBLYHK7HBCEBEXULPFOFFUGAZ7/graph.json","events_json":"https://pith.science/api/pith-number/GBLYHK7HBCEBEXULPFOFFUGAZ7/events.json","paper":"https://pith.science/paper/GBLYHK7H"},"agent_actions":{"view_html":"https://pith.science/pith/GBLYHK7HBCEBEXULPFOFFUGAZ7","download_json":"https://pith.science/pith/GBLYHK7HBCEBEXULPFOFFUGAZ7.json","view_paper":"https://pith.science/paper/GBLYHK7H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.11310&json=true","fetch_graph":"https://pith.science/api/pith-number/GBLYHK7HBCEBEXULPFOFFUGAZ7/graph.json","fetch_events":"https://pith.science/api/pith-number/GBLYHK7HBCEBEXULPFOFFUGAZ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GBLYHK7HBCEBEXULPFOFFUGAZ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GBLYHK7HBCEBEXULPFOFFUGAZ7/action/storage_attestation","attest_author":"https://pith.science/pith/GBLYHK7HBCEBEXULPFOFFUGAZ7/action/author_attestation","sign_citation":"https://pith.science/pith/GBLYHK7HBCEBEXULPFOFFUGAZ7/action/citation_signature","submit_replication":"https://pith.science/pith/GBLYHK7HBCEBEXULPFOFFUGAZ7/action/replication_record"}},"created_at":"2026-07-05T11:54:22.439325+00:00","updated_at":"2026-07-05T11:54:22.439325+00:00"}