{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CNWEBXECUQXVUJO2ZGCESEN4EK","short_pith_number":"pith:CNWEBXEC","canonical_record":{"source":{"id":"2301.08881","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-21T03:57:18Z","cross_cats_sorted":[],"title_canon_sha256":"c7b344a8a6f26b614d20e1a352208ed836be532920b43bb95c69fce4bf3f4373","abstract_canon_sha256":"78617892d74c5b4512ee69f2641a8bbd8e3afdef726de83f2c0eb6a92f7587e6"},"schema_version":"1.0"},"canonical_sha256":"136c40dc82a42f5a25dac9844911bc2292ca5085a4b4382e1bebb78a926f9a95","source":{"kind":"arxiv","id":"2301.08881","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.08881","created_at":"2026-07-05T05:36:33Z"},{"alias_kind":"arxiv_version","alias_value":"2301.08881v2","created_at":"2026-07-05T05:36:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.08881","created_at":"2026-07-05T05:36:33Z"},{"alias_kind":"pith_short_12","alias_value":"CNWEBXECUQXV","created_at":"2026-07-05T05:36:33Z"},{"alias_kind":"pith_short_16","alias_value":"CNWEBXECUQXVUJO2","created_at":"2026-07-05T05:36:33Z"},{"alias_kind":"pith_short_8","alias_value":"CNWEBXEC","created_at":"2026-07-05T05:36:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CNWEBXECUQXVUJO2ZGCESEN4EK","target":"record","payload":{"canonical_record":{"source":{"id":"2301.08881","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-21T03:57:18Z","cross_cats_sorted":[],"title_canon_sha256":"c7b344a8a6f26b614d20e1a352208ed836be532920b43bb95c69fce4bf3f4373","abstract_canon_sha256":"78617892d74c5b4512ee69f2641a8bbd8e3afdef726de83f2c0eb6a92f7587e6"},"schema_version":"1.0"},"canonical_sha256":"136c40dc82a42f5a25dac9844911bc2292ca5085a4b4382e1bebb78a926f9a95","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:33.053903Z","signature_b64":"qmqGq2K8hxXzHlcqjR2k9+n/mIXTcBe2DHk0vszIdGnuAjVsYeAaLK8Sardr49eD07Zr1AyKHWFkZRIku9iiAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"136c40dc82a42f5a25dac9844911bc2292ca5085a4b4382e1bebb78a926f9a95","last_reissued_at":"2026-07-05T05:36:33.053417Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:33.053417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.08881","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":"2026-07-05T05:36:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oSUot8qdenK/O0kL07BmE4aTBUOhPIYQprj3VEXs9R6foTnIjrbxGL8FjzG8aVeNMZ5RJCKZNJyRDZrWS+4KDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T21:09:05.731648Z"},"content_sha256":"da805bb56edfe307a2e29e594a3d79f74c88b23cf917effcca5c6dcbd18e041b","schema_version":"1.0","event_id":"sha256:da805bb56edfe307a2e29e594a3d79f74c88b23cf917effcca5c6dcbd18e041b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CNWEBXECUQXVUJO2ZGCESEN4EK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Hanbo Li, Bing Xiang, Henghui Zhu, Jiarong Jiang, Joseph Lilien, Jun Wang, Lin Pan, Mingwen Dong, Patrick Ng, Sheng Zhang, Shuaichen Chang, Steve Ash, Vittorio Castelli, William Yang Wang, Wuwei Lan, Zhiguo Wang","submitted_at":"2023-01-21T03:57:18Z","abstract_excerpt":"Neural text-to-SQL models have achieved remarkable performance in translating natural language questions into SQL queries. However, recent studies reveal that text-to-SQL models are vulnerable to task-specific perturbations. Previous curated robustness test sets usually focus on individual phenomena. In this paper, we propose a comprehensive robustness benchmark based on Spider, a cross-domain text-to-SQL benchmark, to diagnose the model robustness. We design 17 perturbations on databases, natural language questions, and SQL queries to measure the robustness from different angles. In order to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.08881","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/2301.08881/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":"2026-07-05T05:36:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I8a6icAGYBFZRx89zgx4uW7jTQsx9a5WpK6kcIHxSgw0BdWf8L/e+dK4FJibHGofXg7yiggGo/tv7wHevb8zBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T21:09:05.732472Z"},"content_sha256":"ea317c099927cdd353a9eb190c71a3756f20cd9fb17f2011e982b520f1f81343","schema_version":"1.0","event_id":"sha256:ea317c099927cdd353a9eb190c71a3756f20cd9fb17f2011e982b520f1f81343"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CNWEBXECUQXVUJO2ZGCESEN4EK/bundle.json","state_url":"https://pith.science/pith/CNWEBXECUQXVUJO2ZGCESEN4EK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CNWEBXECUQXVUJO2ZGCESEN4EK/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":"2026-08-10T21:09:05Z","links":{"resolver":"https://pith.science/pith/CNWEBXECUQXVUJO2ZGCESEN4EK","bundle":"https://pith.science/pith/CNWEBXECUQXVUJO2ZGCESEN4EK/bundle.json","state":"https://pith.science/pith/CNWEBXECUQXVUJO2ZGCESEN4EK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CNWEBXECUQXVUJO2ZGCESEN4EK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CNWEBXECUQXVUJO2ZGCESEN4EK","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":"78617892d74c5b4512ee69f2641a8bbd8e3afdef726de83f2c0eb6a92f7587e6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-21T03:57:18Z","title_canon_sha256":"c7b344a8a6f26b614d20e1a352208ed836be532920b43bb95c69fce4bf3f4373"},"schema_version":"1.0","source":{"id":"2301.08881","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.08881","created_at":"2026-07-05T05:36:33Z"},{"alias_kind":"arxiv_version","alias_value":"2301.08881v2","created_at":"2026-07-05T05:36:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.08881","created_at":"2026-07-05T05:36:33Z"},{"alias_kind":"pith_short_12","alias_value":"CNWEBXECUQXV","created_at":"2026-07-05T05:36:33Z"},{"alias_kind":"pith_short_16","alias_value":"CNWEBXECUQXVUJO2","created_at":"2026-07-05T05:36:33Z"},{"alias_kind":"pith_short_8","alias_value":"CNWEBXEC","created_at":"2026-07-05T05:36:33Z"}],"graph_snapshots":[{"event_id":"sha256:ea317c099927cdd353a9eb190c71a3756f20cd9fb17f2011e982b520f1f81343","target":"graph","created_at":"2026-07-05T05:36:33Z","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/2301.08881/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural text-to-SQL models have achieved remarkable performance in translating natural language questions into SQL queries. However, recent studies reveal that text-to-SQL models are vulnerable to task-specific perturbations. Previous curated robustness test sets usually focus on individual phenomena. In this paper, we propose a comprehensive robustness benchmark based on Spider, a cross-domain text-to-SQL benchmark, to diagnose the model robustness. We design 17 perturbations on databases, natural language questions, and SQL queries to measure the robustness from different angles. In order to ","authors_text":"Alexander Hanbo Li, Bing Xiang, Henghui Zhu, Jiarong Jiang, Joseph Lilien, Jun Wang, Lin Pan, Mingwen Dong, Patrick Ng, Sheng Zhang, Shuaichen Chang, Steve Ash, Vittorio Castelli, William Yang Wang, Wuwei Lan, Zhiguo Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-21T03:57:18Z","title":"Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.08881","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:da805bb56edfe307a2e29e594a3d79f74c88b23cf917effcca5c6dcbd18e041b","target":"record","created_at":"2026-07-05T05:36:33Z","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":"78617892d74c5b4512ee69f2641a8bbd8e3afdef726de83f2c0eb6a92f7587e6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-21T03:57:18Z","title_canon_sha256":"c7b344a8a6f26b614d20e1a352208ed836be532920b43bb95c69fce4bf3f4373"},"schema_version":"1.0","source":{"id":"2301.08881","kind":"arxiv","version":2}},"canonical_sha256":"136c40dc82a42f5a25dac9844911bc2292ca5085a4b4382e1bebb78a926f9a95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"136c40dc82a42f5a25dac9844911bc2292ca5085a4b4382e1bebb78a926f9a95","first_computed_at":"2026-07-05T05:36:33.053417Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:36:33.053417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qmqGq2K8hxXzHlcqjR2k9+n/mIXTcBe2DHk0vszIdGnuAjVsYeAaLK8Sardr49eD07Zr1AyKHWFkZRIku9iiAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:36:33.053903Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.08881","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da805bb56edfe307a2e29e594a3d79f74c88b23cf917effcca5c6dcbd18e041b","sha256:ea317c099927cdd353a9eb190c71a3756f20cd9fb17f2011e982b520f1f81343"],"state_sha256":"e96dd7adf8f35b1972a65204766bd77a9dc9354dfb224bc53d91c2512af8a997"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"esftUIo57NZqDBrnlrFu0+D18Fhs1Pcd7dODv1SKgpIWS9D7b/5zA3wsnZKsxupsx/oZJnLRN64yRfmwZ2AbCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T21:09:05.738267Z","bundle_sha256":"d8597e1ee8c134a05481347b3a5b08091e8a97da1da37deb7c7ffd9e5a0db448"}}