{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PBYGUDTAOFPDYVFYEPYVSPRF7K","short_pith_number":"pith:PBYGUDTA","canonical_record":{"source":{"id":"2408.03573","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-08-07T06:17:48Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c269fa9b2cc09080506cb8103053ab3baed4192f84a4cee4189a2c137a848a03","abstract_canon_sha256":"592a122fb679272e2205009cd56b305ac2dd21d64862f1d1ddfd4b64a0c55e75"},"schema_version":"1.0"},"canonical_sha256":"78706a0e60715e3c54b823f1593e25fa9fbc45550cd4a678278f8d0662e84ae9","source":{"kind":"arxiv","id":"2408.03573","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.03573","created_at":"2026-07-05T11:19:20Z"},{"alias_kind":"arxiv_version","alias_value":"2408.03573v2","created_at":"2026-07-05T11:19:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.03573","created_at":"2026-07-05T11:19:20Z"},{"alias_kind":"pith_short_12","alias_value":"PBYGUDTAOFPD","created_at":"2026-07-05T11:19:20Z"},{"alias_kind":"pith_short_16","alias_value":"PBYGUDTAOFPDYVFY","created_at":"2026-07-05T11:19:20Z"},{"alias_kind":"pith_short_8","alias_value":"PBYGUDTA","created_at":"2026-07-05T11:19:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PBYGUDTAOFPDYVFYEPYVSPRF7K","target":"record","payload":{"canonical_record":{"source":{"id":"2408.03573","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-08-07T06:17:48Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"c269fa9b2cc09080506cb8103053ab3baed4192f84a4cee4189a2c137a848a03","abstract_canon_sha256":"592a122fb679272e2205009cd56b305ac2dd21d64862f1d1ddfd4b64a0c55e75"},"schema_version":"1.0"},"canonical_sha256":"78706a0e60715e3c54b823f1593e25fa9fbc45550cd4a678278f8d0662e84ae9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:20.450457Z","signature_b64":"WE2VEpCqmol0fhOzWFAO471IBtXMzb0bXJoIJ42mLujGAv+Daqn4qfFyxh2fEjOiVBMJ8ggQJOGFPQbyWAENBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78706a0e60715e3c54b823f1593e25fa9fbc45550cd4a678278f8d0662e84ae9","last_reissued_at":"2026-07-05T11:19:20.449918Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:20.449918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.03573","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":"2026-07-05T11:19:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ew3PgW8nvJFSYcAOEAXihj6mpirP03HDq4LY/QptA/N/VT9JA2rmFt2UQb4pbH+dQrGJxZHcKophpAXxbYklAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:21:53.626926Z"},"content_sha256":"1e648e4b71e73f0b0f2550c07c3c43cef43358929dfb17d8e3d015f1d9e26b8d","schema_version":"1.0","event_id":"sha256:1e648e4b71e73f0b0f2550c07c3c43cef43358929dfb17d8e3d015f1d9e26b8d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PBYGUDTAOFPDYVFYEPYVSPRF7K","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AcTracer: Active Testing of Large Language Model via Multi-Stage Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Felix Juefei-Xu, Jiayang Song, Lei Ma, Qiang Hu, Yuheng Huang","submitted_at":"2024-08-07T06:17:48Z","abstract_excerpt":"Performance evaluation plays a crucial role in the development life cycle of large language models (LLMs). It estimates the model's capability, elucidates behavior characteristics, and facilitates the identification of potential issues and limitations, thereby guiding further improvement. Given that LLMs' diverse task-handling abilities stem from large volumes of training data, a comprehensive evaluation also necessitates abundant, well-annotated, and representative test data to assess LLM performance across various downstream tasks. However, the demand for high-quality test data often entails"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.03573","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/2408.03573/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":"2026-07-05T11:19:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cNsQGKoEhv+gDV9dwAYd0HskqQJPhN1sIeh9kyJsvzRVQVjjGWrVbBBaKI5u7WSrbW5qxWNnGYvOPkqPTqwcBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:21:53.627808Z"},"content_sha256":"a90a2c167f84ca7da3c198222996097f2166b43293f0776df4f02ef727ee7f70","schema_version":"1.0","event_id":"sha256:a90a2c167f84ca7da3c198222996097f2166b43293f0776df4f02ef727ee7f70"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PBYGUDTAOFPDYVFYEPYVSPRF7K/bundle.json","state_url":"https://pith.science/pith/PBYGUDTAOFPDYVFYEPYVSPRF7K/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PBYGUDTAOFPDYVFYEPYVSPRF7K/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":"2026-08-15T17:21:53Z","links":{"resolver":"https://pith.science/pith/PBYGUDTAOFPDYVFYEPYVSPRF7K","bundle":"https://pith.science/pith/PBYGUDTAOFPDYVFYEPYVSPRF7K/bundle.json","state":"https://pith.science/pith/PBYGUDTAOFPDYVFYEPYVSPRF7K/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PBYGUDTAOFPDYVFYEPYVSPRF7K/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PBYGUDTAOFPDYVFYEPYVSPRF7K","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":"592a122fb679272e2205009cd56b305ac2dd21d64862f1d1ddfd4b64a0c55e75","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-08-07T06:17:48Z","title_canon_sha256":"c269fa9b2cc09080506cb8103053ab3baed4192f84a4cee4189a2c137a848a03"},"schema_version":"1.0","source":{"id":"2408.03573","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.03573","created_at":"2026-07-05T11:19:20Z"},{"alias_kind":"arxiv_version","alias_value":"2408.03573v2","created_at":"2026-07-05T11:19:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.03573","created_at":"2026-07-05T11:19:20Z"},{"alias_kind":"pith_short_12","alias_value":"PBYGUDTAOFPD","created_at":"2026-07-05T11:19:20Z"},{"alias_kind":"pith_short_16","alias_value":"PBYGUDTAOFPDYVFY","created_at":"2026-07-05T11:19:20Z"},{"alias_kind":"pith_short_8","alias_value":"PBYGUDTA","created_at":"2026-07-05T11:19:20Z"}],"graph_snapshots":[{"event_id":"sha256:a90a2c167f84ca7da3c198222996097f2166b43293f0776df4f02ef727ee7f70","target":"graph","created_at":"2026-07-05T11:19:20Z","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/2408.03573/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Performance evaluation plays a crucial role in the development life cycle of large language models (LLMs). It estimates the model's capability, elucidates behavior characteristics, and facilitates the identification of potential issues and limitations, thereby guiding further improvement. Given that LLMs' diverse task-handling abilities stem from large volumes of training data, a comprehensive evaluation also necessitates abundant, well-annotated, and representative test data to assess LLM performance across various downstream tasks. However, the demand for high-quality test data often entails","authors_text":"Felix Juefei-Xu, Jiayang Song, Lei Ma, Qiang Hu, Yuheng Huang","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-08-07T06:17:48Z","title":"AcTracer: Active Testing of Large Language Model via Multi-Stage Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.03573","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":"sha256:1e648e4b71e73f0b0f2550c07c3c43cef43358929dfb17d8e3d015f1d9e26b8d","target":"record","created_at":"2026-07-05T11:19:20Z","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":"592a122fb679272e2205009cd56b305ac2dd21d64862f1d1ddfd4b64a0c55e75","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-08-07T06:17:48Z","title_canon_sha256":"c269fa9b2cc09080506cb8103053ab3baed4192f84a4cee4189a2c137a848a03"},"schema_version":"1.0","source":{"id":"2408.03573","kind":"arxiv","version":2}},"canonical_sha256":"78706a0e60715e3c54b823f1593e25fa9fbc45550cd4a678278f8d0662e84ae9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78706a0e60715e3c54b823f1593e25fa9fbc45550cd4a678278f8d0662e84ae9","first_computed_at":"2026-07-05T11:19:20.449918Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:20.449918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WE2VEpCqmol0fhOzWFAO471IBtXMzb0bXJoIJ42mLujGAv+Daqn4qfFyxh2fEjOiVBMJ8ggQJOGFPQbyWAENBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:20.450457Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.03573","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e648e4b71e73f0b0f2550c07c3c43cef43358929dfb17d8e3d015f1d9e26b8d","sha256:a90a2c167f84ca7da3c198222996097f2166b43293f0776df4f02ef727ee7f70"],"state_sha256":"e1e1ff4e5a2b7f0aa923658cef46023cd1c67876f13c69c2575a98df06013960"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XNiQ3p2hFKqfk+fl90YZHIL6YiYc7ghK5e/EcmS8uLtucEtdYlPriYrMpFq3OrJzWXXmaxQ9Uh+hypx3K+ZNAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T17:21:53.634137Z","bundle_sha256":"b23073259bd7908080e2f8da39b3bdde88b77db8dd3cb64ade795411caa04012"}}