{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ES5H65KEHE4MZ3N3523S6WXSNK","short_pith_number":"pith:ES5H65KE","canonical_record":{"source":{"id":"2401.03038","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-01-05T19:27:58Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"1bd2a2b45a7172895566a71d92bbff37d1aa647acdc7098c38f9eafa9c752b31","abstract_canon_sha256":"78c047b1840e4d8c69fb4f1beaf61ecfab357b6d3e403576ff37039a02329b79"},"schema_version":"1.0"},"canonical_sha256":"24ba7f75443938ccedbbeeb72f5af26a855d80e993b30e3d9edccadc53fc40d9","source":{"kind":"arxiv","id":"2401.03038","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.03038","created_at":"2026-07-05T08:02:50Z"},{"alias_kind":"arxiv_version","alias_value":"2401.03038v2","created_at":"2026-07-05T08:02:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.03038","created_at":"2026-07-05T08:02:50Z"},{"alias_kind":"pith_short_12","alias_value":"ES5H65KEHE4M","created_at":"2026-07-05T08:02:50Z"},{"alias_kind":"pith_short_16","alias_value":"ES5H65KEHE4MZ3N3","created_at":"2026-07-05T08:02:50Z"},{"alias_kind":"pith_short_8","alias_value":"ES5H65KE","created_at":"2026-07-05T08:02:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ES5H65KEHE4MZ3N3523S6WXSNK","target":"record","payload":{"canonical_record":{"source":{"id":"2401.03038","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-01-05T19:27:58Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"1bd2a2b45a7172895566a71d92bbff37d1aa647acdc7098c38f9eafa9c752b31","abstract_canon_sha256":"78c047b1840e4d8c69fb4f1beaf61ecfab357b6d3e403576ff37039a02329b79"},"schema_version":"1.0"},"canonical_sha256":"24ba7f75443938ccedbbeeb72f5af26a855d80e993b30e3d9edccadc53fc40d9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:50.085908Z","signature_b64":"MB1EVFAZVijmg3syhmpxeUL7EX3PF7lKNFYNuCGCyht3JDcHLtLy1uFWXKIfTxsqbOmREvm/88fKdpbdkDzIBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24ba7f75443938ccedbbeeb72f5af26a855d80e993b30e3d9edccadc53fc40d9","last_reissued_at":"2026-07-05T08:02:50.085482Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:50.085482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.03038","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":"2026-07-05T08:02:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kjyUKjVG5JpJq0bVQDhRLx4/FQWNMbLMlShWslX6iGG9nHFOBHFZ89jkcWYFxxyqNKoFCPQuBKuGHXH89wYmCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T04:55:29.757458Z"},"content_sha256":"a0b6d46978da84ca020c6379a18682b80cabd66538ccaf0b3b742d0c511d4d6c","schema_version":"1.0","event_id":"sha256:a0b6d46978da84ca020c6379a18682b80cabd66538ccaf0b3b742d0c511d4d6c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ES5H65KEHE4MZ3N3523S6WXSNK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SPADE: Synthesizing Data Quality Assertions for Large Language Model Pipelines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.DB","authors_text":"Aditya G. Parameswaran, Eugene Wu, Haotian Li, Harrison Chase, J.D. Zamfirescu-Pereira, Madelon Hulsebos, Parth Asawa, Shreya Shankar, Will Fu-Hinthorn, Yiming Lin","submitted_at":"2024-01-05T19:27:58Z","abstract_excerpt":"Large language models (LLMs) are being increasingly deployed as part of pipelines that repeatedly process or generate data of some sort. However, a common barrier to deployment are the frequent and often unpredictable errors that plague LLMs. Acknowledging the inevitability of these errors, we propose {\\em data quality assertions} to identify when LLMs may be making mistakes. We present SPADE, a method for automatically synthesizing data quality assertions that identify bad LLM outputs. We make the observation that developers often identify data quality issues during prototyping prior to deplo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.03038","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/2401.03038/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":"2026-07-05T08:02:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pfP1IIxyC7waJpI2iteevQ6W+r427Ax8Qt6pUWsSgxjElLELzCRdflmkxMFr3zyCCODFYpu5JE/KFmTB1DorBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T04:55:29.758091Z"},"content_sha256":"5c7565f40722c217aca04caef74e7655b8e4d4700251d416d723e0f44550d645","schema_version":"1.0","event_id":"sha256:5c7565f40722c217aca04caef74e7655b8e4d4700251d416d723e0f44550d645"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ES5H65KEHE4MZ3N3523S6WXSNK/bundle.json","state_url":"https://pith.science/pith/ES5H65KEHE4MZ3N3523S6WXSNK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ES5H65KEHE4MZ3N3523S6WXSNK/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":"2026-08-18T04:55:29Z","links":{"resolver":"https://pith.science/pith/ES5H65KEHE4MZ3N3523S6WXSNK","bundle":"https://pith.science/pith/ES5H65KEHE4MZ3N3523S6WXSNK/bundle.json","state":"https://pith.science/pith/ES5H65KEHE4MZ3N3523S6WXSNK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ES5H65KEHE4MZ3N3523S6WXSNK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ES5H65KEHE4MZ3N3523S6WXSNK","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":"78c047b1840e4d8c69fb4f1beaf61ecfab357b6d3e403576ff37039a02329b79","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-01-05T19:27:58Z","title_canon_sha256":"1bd2a2b45a7172895566a71d92bbff37d1aa647acdc7098c38f9eafa9c752b31"},"schema_version":"1.0","source":{"id":"2401.03038","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.03038","created_at":"2026-07-05T08:02:50Z"},{"alias_kind":"arxiv_version","alias_value":"2401.03038v2","created_at":"2026-07-05T08:02:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.03038","created_at":"2026-07-05T08:02:50Z"},{"alias_kind":"pith_short_12","alias_value":"ES5H65KEHE4M","created_at":"2026-07-05T08:02:50Z"},{"alias_kind":"pith_short_16","alias_value":"ES5H65KEHE4MZ3N3","created_at":"2026-07-05T08:02:50Z"},{"alias_kind":"pith_short_8","alias_value":"ES5H65KE","created_at":"2026-07-05T08:02:50Z"}],"graph_snapshots":[{"event_id":"sha256:5c7565f40722c217aca04caef74e7655b8e4d4700251d416d723e0f44550d645","target":"graph","created_at":"2026-07-05T08:02:50Z","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/2401.03038/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are being increasingly deployed as part of pipelines that repeatedly process or generate data of some sort. However, a common barrier to deployment are the frequent and often unpredictable errors that plague LLMs. Acknowledging the inevitability of these errors, we propose {\\em data quality assertions} to identify when LLMs may be making mistakes. We present SPADE, a method for automatically synthesizing data quality assertions that identify bad LLM outputs. We make the observation that developers often identify data quality issues during prototyping prior to deplo","authors_text":"Aditya G. Parameswaran, Eugene Wu, Haotian Li, Harrison Chase, J.D. Zamfirescu-Pereira, Madelon Hulsebos, Parth Asawa, Shreya Shankar, Will Fu-Hinthorn, Yiming Lin","cross_cats":["cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-01-05T19:27:58Z","title":"SPADE: Synthesizing Data Quality Assertions for Large Language Model Pipelines"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.03038","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:a0b6d46978da84ca020c6379a18682b80cabd66538ccaf0b3b742d0c511d4d6c","target":"record","created_at":"2026-07-05T08:02:50Z","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":"78c047b1840e4d8c69fb4f1beaf61ecfab357b6d3e403576ff37039a02329b79","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-01-05T19:27:58Z","title_canon_sha256":"1bd2a2b45a7172895566a71d92bbff37d1aa647acdc7098c38f9eafa9c752b31"},"schema_version":"1.0","source":{"id":"2401.03038","kind":"arxiv","version":2}},"canonical_sha256":"24ba7f75443938ccedbbeeb72f5af26a855d80e993b30e3d9edccadc53fc40d9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24ba7f75443938ccedbbeeb72f5af26a855d80e993b30e3d9edccadc53fc40d9","first_computed_at":"2026-07-05T08:02:50.085482Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:50.085482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MB1EVFAZVijmg3syhmpxeUL7EX3PF7lKNFYNuCGCyht3JDcHLtLy1uFWXKIfTxsqbOmREvm/88fKdpbdkDzIBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:50.085908Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.03038","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0b6d46978da84ca020c6379a18682b80cabd66538ccaf0b3b742d0c511d4d6c","sha256:5c7565f40722c217aca04caef74e7655b8e4d4700251d416d723e0f44550d645"],"state_sha256":"241600cd45d7b0641593854d15f13874ef057d1d9d607e03b6f926326ecc9ee6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GhVgvThjc+WMDVJudhlagTpuGYOS63e/yJ/3tipC97j5CjG3y8o+B9OVscShvxvsmLenF5LzLCmVbXDIne8HBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T04:55:29.763885Z","bundle_sha256":"d5b9b4eecfdce5445cd0f726ebdfbbd8dea1427c5fe7548613bd80dfa59337a8"}}