{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2GUWY2NU3PVY3MZL4MEKQ4P5NR","short_pith_number":"pith:2GUWY2NU","canonical_record":{"source":{"id":"2508.07353","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-10T14:08:28Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"25112ec55e51fc887992fb398a73f5b4f0a1c560b039fba467210ebd1af478ab","abstract_canon_sha256":"b87d121e8e762efa5a5fee2d959b495fdeecea7ac055e4aea9fb515011db1cee"},"schema_version":"1.0"},"canonical_sha256":"d1a96c69b4dbeb8db32be308a871fd6c5460c0d4053ebe984b7b8aaa4394761c","source":{"kind":"arxiv","id":"2508.07353","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.07353","created_at":"2026-07-05T12:07:10Z"},{"alias_kind":"arxiv_version","alias_value":"2508.07353v3","created_at":"2026-07-05T12:07:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07353","created_at":"2026-07-05T12:07:10Z"},{"alias_kind":"pith_short_12","alias_value":"2GUWY2NU3PVY","created_at":"2026-07-05T12:07:10Z"},{"alias_kind":"pith_short_16","alias_value":"2GUWY2NU3PVY3MZL","created_at":"2026-07-05T12:07:10Z"},{"alias_kind":"pith_short_8","alias_value":"2GUWY2NU","created_at":"2026-07-05T12:07:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2GUWY2NU3PVY3MZL4MEKQ4P5NR","target":"record","payload":{"canonical_record":{"source":{"id":"2508.07353","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-10T14:08:28Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"25112ec55e51fc887992fb398a73f5b4f0a1c560b039fba467210ebd1af478ab","abstract_canon_sha256":"b87d121e8e762efa5a5fee2d959b495fdeecea7ac055e4aea9fb515011db1cee"},"schema_version":"1.0"},"canonical_sha256":"d1a96c69b4dbeb8db32be308a871fd6c5460c0d4053ebe984b7b8aaa4394761c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:07:10.274191Z","signature_b64":"VTlQRldqrDGE6gKpsgDwt8ToC5eyfGyjwdI0tMI5yK0ywT6RojIn8bMEQgRkMmzA1xog8K6vy11cGfd8yf6qCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1a96c69b4dbeb8db32be308a871fd6c5460c0d4053ebe984b7b8aaa4394761c","last_reissued_at":"2026-07-05T12:07:10.273696Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:07:10.273696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.07353","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:07:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OL7It1gnZBijMM40AGe+aEgY0uteygKL+9k9h9RoaVmiOwVB4/WfgfhbSNoRc9DHXmO+1qYkBjMVSeWjQHhpDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T23:02:44.897416Z"},"content_sha256":"aee5b12693a2415f54906c13a54f877447096d399039777b7657000feb101760","schema_version":"1.0","event_id":"sha256:aee5b12693a2415f54906c13a54f877447096d399039777b7657000feb101760"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2GUWY2NU3PVY3MZL4MEKQ4P5NR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Benchmarking for Domain-Specific LLMs: A Case Study on Academia and Beyond","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Chenghua Lin, Jian Wang, Jiaxin Wu, Qing Li, Rubing Chen, Wenqi Fan, Xiao-Yong Wei, Xulu Zhang","submitted_at":"2025-08-10T14:08:28Z","abstract_excerpt":"The increasing demand for domain-specific evaluation of large language models (LLMs) has led to the development of numerous benchmarks. These efforts often adhere to the principle of data scaling, relying on large corpora or extensive question-answer (QA) sets to ensure broad coverage. However, the impact of corpus and QA set design on the precision and recall of domain-specific LLM performance remains poorly understood. In this paper, we argue that data scaling is not always the optimal principle for domain-specific benchmark construction. Instead, we introduce Comp-Comp, an iterative benchma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07353","kind":"arxiv","version":3},"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/2508.07353/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":"2026-07-05T12:07:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lwKTUgYMTGoPdrk+ZjFeh5tCbxhE9+2MWLzGYvHJJDaTybZCVP3jJoQAaArb079lDIuOdn/0+cwZLkZJm5QQAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T23:02:44.898346Z"},"content_sha256":"296e13b68e78b0179a0dff8939a3788259d4d01b80744a5992e0114718583213","schema_version":"1.0","event_id":"sha256:296e13b68e78b0179a0dff8939a3788259d4d01b80744a5992e0114718583213"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2GUWY2NU3PVY3MZL4MEKQ4P5NR/bundle.json","state_url":"https://pith.science/pith/2GUWY2NU3PVY3MZL4MEKQ4P5NR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2GUWY2NU3PVY3MZL4MEKQ4P5NR/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":"2026-08-06T23:02:44Z","links":{"resolver":"https://pith.science/pith/2GUWY2NU3PVY3MZL4MEKQ4P5NR","bundle":"https://pith.science/pith/2GUWY2NU3PVY3MZL4MEKQ4P5NR/bundle.json","state":"https://pith.science/pith/2GUWY2NU3PVY3MZL4MEKQ4P5NR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2GUWY2NU3PVY3MZL4MEKQ4P5NR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2GUWY2NU3PVY3MZL4MEKQ4P5NR","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":"b87d121e8e762efa5a5fee2d959b495fdeecea7ac055e4aea9fb515011db1cee","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-10T14:08:28Z","title_canon_sha256":"25112ec55e51fc887992fb398a73f5b4f0a1c560b039fba467210ebd1af478ab"},"schema_version":"1.0","source":{"id":"2508.07353","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.07353","created_at":"2026-07-05T12:07:10Z"},{"alias_kind":"arxiv_version","alias_value":"2508.07353v3","created_at":"2026-07-05T12:07:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07353","created_at":"2026-07-05T12:07:10Z"},{"alias_kind":"pith_short_12","alias_value":"2GUWY2NU3PVY","created_at":"2026-07-05T12:07:10Z"},{"alias_kind":"pith_short_16","alias_value":"2GUWY2NU3PVY3MZL","created_at":"2026-07-05T12:07:10Z"},{"alias_kind":"pith_short_8","alias_value":"2GUWY2NU","created_at":"2026-07-05T12:07:10Z"}],"graph_snapshots":[{"event_id":"sha256:296e13b68e78b0179a0dff8939a3788259d4d01b80744a5992e0114718583213","target":"graph","created_at":"2026-07-05T12:07:10Z","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/2508.07353/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The increasing demand for domain-specific evaluation of large language models (LLMs) has led to the development of numerous benchmarks. These efforts often adhere to the principle of data scaling, relying on large corpora or extensive question-answer (QA) sets to ensure broad coverage. However, the impact of corpus and QA set design on the precision and recall of domain-specific LLM performance remains poorly understood. In this paper, we argue that data scaling is not always the optimal principle for domain-specific benchmark construction. Instead, we introduce Comp-Comp, an iterative benchma","authors_text":"Chenghua Lin, Jian Wang, Jiaxin Wu, Qing Li, Rubing Chen, Wenqi Fan, Xiao-Yong Wei, Xulu Zhang","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-10T14:08:28Z","title":"Benchmarking for Domain-Specific LLMs: A Case Study on Academia and Beyond"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07353","kind":"arxiv","version":3},"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:aee5b12693a2415f54906c13a54f877447096d399039777b7657000feb101760","target":"record","created_at":"2026-07-05T12:07:10Z","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":"b87d121e8e762efa5a5fee2d959b495fdeecea7ac055e4aea9fb515011db1cee","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-10T14:08:28Z","title_canon_sha256":"25112ec55e51fc887992fb398a73f5b4f0a1c560b039fba467210ebd1af478ab"},"schema_version":"1.0","source":{"id":"2508.07353","kind":"arxiv","version":3}},"canonical_sha256":"d1a96c69b4dbeb8db32be308a871fd6c5460c0d4053ebe984b7b8aaa4394761c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1a96c69b4dbeb8db32be308a871fd6c5460c0d4053ebe984b7b8aaa4394761c","first_computed_at":"2026-07-05T12:07:10.273696Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:07:10.273696Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VTlQRldqrDGE6gKpsgDwt8ToC5eyfGyjwdI0tMI5yK0ywT6RojIn8bMEQgRkMmzA1xog8K6vy11cGfd8yf6qCw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:07:10.274191Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.07353","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aee5b12693a2415f54906c13a54f877447096d399039777b7657000feb101760","sha256:296e13b68e78b0179a0dff8939a3788259d4d01b80744a5992e0114718583213"],"state_sha256":"e5935c78e811b9df1cc526c10b90c70b8787bec0ee3b2d31fe75115730af8b18"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kyhf6k/uOOxOJtedV+9QReD/aBd1iS4P7b+oLm3Fi8qFVSUFFjd7te6tkJDbsAkIpugiCOfkLwp+lIhp7IsZDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T23:02:44.905445Z","bundle_sha256":"474eb5d791fc70d7fd602c5e4d0aca86c9d88f0f1e41390f9bade24f11778d64"}}