{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WAKDIZUJWLU37KVVDM7VCIWHTU","short_pith_number":"pith:WAKDIZUJ","canonical_record":{"source":{"id":"2302.11054","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-21T23:15:33Z","cross_cats_sorted":[],"title_canon_sha256":"a27fdce45ca168474c7bcc0e902e1d12e859cf2b91337fec106c1e90aa4a7818","abstract_canon_sha256":"ab18b826e156ab6d1f09e5189246bed142f6cd59aa9c5bdf5ca1d2c83160e316"},"schema_version":"1.0"},"canonical_sha256":"b014346689b2e9bfaab51b3f5122c79d1b45b0009c4dfd6a7ee1fc839678c3dc","source":{"kind":"arxiv","id":"2302.11054","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.11054","created_at":"2026-07-05T05:44:29Z"},{"alias_kind":"arxiv_version","alias_value":"2302.11054v1","created_at":"2026-07-05T05:44:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.11054","created_at":"2026-07-05T05:44:29Z"},{"alias_kind":"pith_short_12","alias_value":"WAKDIZUJWLU3","created_at":"2026-07-05T05:44:29Z"},{"alias_kind":"pith_short_16","alias_value":"WAKDIZUJWLU37KVV","created_at":"2026-07-05T05:44:29Z"},{"alias_kind":"pith_short_8","alias_value":"WAKDIZUJ","created_at":"2026-07-05T05:44:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WAKDIZUJWLU37KVVDM7VCIWHTU","target":"record","payload":{"canonical_record":{"source":{"id":"2302.11054","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-21T23:15:33Z","cross_cats_sorted":[],"title_canon_sha256":"a27fdce45ca168474c7bcc0e902e1d12e859cf2b91337fec106c1e90aa4a7818","abstract_canon_sha256":"ab18b826e156ab6d1f09e5189246bed142f6cd59aa9c5bdf5ca1d2c83160e316"},"schema_version":"1.0"},"canonical_sha256":"b014346689b2e9bfaab51b3f5122c79d1b45b0009c4dfd6a7ee1fc839678c3dc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:44:29.995864Z","signature_b64":"Faf1SIhW0Kx4ATL6skFFrk+Fns1G7C2U/5Ag1tWYf3sDHrR42UWJICfrkfKQyDvCZZ/6+wk8D56qmvTBMMVsCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b014346689b2e9bfaab51b3f5122c79d1b45b0009c4dfd6a7ee1fc839678c3dc","last_reissued_at":"2026-07-05T05:44:29.995515Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:44:29.995515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.11054","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:44:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4MO2M5mzyLR1el6yrohz6dWk1TAQiyu73m+YtkA3pi35G46EPHiyiPeH44r1VfnHGcaSSNYTezUURtrJSzc8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:39:54.646394Z"},"content_sha256":"360902e2624d92421299a2fe3d2f4861800a82ecd149d3361c0637b9c2f1197b","schema_version":"1.0","event_id":"sha256:360902e2624d92421299a2fe3d2f4861800a82ecd149d3361c0637b9c2f1197b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WAKDIZUJWLU37KVVDM7VCIWHTU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Conversational Text-to-SQL: An Odyssey into State-of-the-Art and Challenges Ahead","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dilek Hakkani-Tur, Lu Zeng, Sree Hari Krishnan Parthasarathi","submitted_at":"2023-02-21T23:15:33Z","abstract_excerpt":"Conversational, multi-turn, text-to-SQL (CoSQL) tasks map natural language utterances in a dialogue to SQL queries. State-of-the-art (SOTA) systems use large, pre-trained and finetuned language models, such as the T5-family, in conjunction with constrained decoding. With multi-tasking (MT) over coherent tasks with discrete prompts during training, we improve over specialized text-to-SQL T5-family models. Based on Oracle analyses over n-best hypotheses, we apply a query plan model and a schema linking algorithm as rerankers. Combining MT and reranking, our results using T5-3B show absolute accu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.11054","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/2302.11054/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":"2026-07-05T05:44:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FXCg86mLheMtw4YGc9oYiEk4q1WMZ7F2N9kPE0aWlp1rOv9J51jkkYnWRB+ISvQXB/fTBwQ//614a0tqxxLoBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:39:54.647025Z"},"content_sha256":"8793ead7eb87766f8a6d4593dee01490bc5feae2cde4cf413a36410eb39af405","schema_version":"1.0","event_id":"sha256:8793ead7eb87766f8a6d4593dee01490bc5feae2cde4cf413a36410eb39af405"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WAKDIZUJWLU37KVVDM7VCIWHTU/bundle.json","state_url":"https://pith.science/pith/WAKDIZUJWLU37KVVDM7VCIWHTU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WAKDIZUJWLU37KVVDM7VCIWHTU/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":"2026-07-07T06:39:54Z","links":{"resolver":"https://pith.science/pith/WAKDIZUJWLU37KVVDM7VCIWHTU","bundle":"https://pith.science/pith/WAKDIZUJWLU37KVVDM7VCIWHTU/bundle.json","state":"https://pith.science/pith/WAKDIZUJWLU37KVVDM7VCIWHTU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WAKDIZUJWLU37KVVDM7VCIWHTU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WAKDIZUJWLU37KVVDM7VCIWHTU","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":"ab18b826e156ab6d1f09e5189246bed142f6cd59aa9c5bdf5ca1d2c83160e316","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-21T23:15:33Z","title_canon_sha256":"a27fdce45ca168474c7bcc0e902e1d12e859cf2b91337fec106c1e90aa4a7818"},"schema_version":"1.0","source":{"id":"2302.11054","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.11054","created_at":"2026-07-05T05:44:29Z"},{"alias_kind":"arxiv_version","alias_value":"2302.11054v1","created_at":"2026-07-05T05:44:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.11054","created_at":"2026-07-05T05:44:29Z"},{"alias_kind":"pith_short_12","alias_value":"WAKDIZUJWLU3","created_at":"2026-07-05T05:44:29Z"},{"alias_kind":"pith_short_16","alias_value":"WAKDIZUJWLU37KVV","created_at":"2026-07-05T05:44:29Z"},{"alias_kind":"pith_short_8","alias_value":"WAKDIZUJ","created_at":"2026-07-05T05:44:29Z"}],"graph_snapshots":[{"event_id":"sha256:8793ead7eb87766f8a6d4593dee01490bc5feae2cde4cf413a36410eb39af405","target":"graph","created_at":"2026-07-05T05:44:29Z","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/2302.11054/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Conversational, multi-turn, text-to-SQL (CoSQL) tasks map natural language utterances in a dialogue to SQL queries. State-of-the-art (SOTA) systems use large, pre-trained and finetuned language models, such as the T5-family, in conjunction with constrained decoding. With multi-tasking (MT) over coherent tasks with discrete prompts during training, we improve over specialized text-to-SQL T5-family models. Based on Oracle analyses over n-best hypotheses, we apply a query plan model and a schema linking algorithm as rerankers. Combining MT and reranking, our results using T5-3B show absolute accu","authors_text":"Dilek Hakkani-Tur, Lu Zeng, Sree Hari Krishnan Parthasarathi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-21T23:15:33Z","title":"Conversational Text-to-SQL: An Odyssey into State-of-the-Art and Challenges Ahead"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.11054","kind":"arxiv","version":1},"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":"sha256:360902e2624d92421299a2fe3d2f4861800a82ecd149d3361c0637b9c2f1197b","target":"record","created_at":"2026-07-05T05:44:29Z","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":"ab18b826e156ab6d1f09e5189246bed142f6cd59aa9c5bdf5ca1d2c83160e316","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-21T23:15:33Z","title_canon_sha256":"a27fdce45ca168474c7bcc0e902e1d12e859cf2b91337fec106c1e90aa4a7818"},"schema_version":"1.0","source":{"id":"2302.11054","kind":"arxiv","version":1}},"canonical_sha256":"b014346689b2e9bfaab51b3f5122c79d1b45b0009c4dfd6a7ee1fc839678c3dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b014346689b2e9bfaab51b3f5122c79d1b45b0009c4dfd6a7ee1fc839678c3dc","first_computed_at":"2026-07-05T05:44:29.995515Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:44:29.995515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Faf1SIhW0Kx4ATL6skFFrk+Fns1G7C2U/5Ag1tWYf3sDHrR42UWJICfrkfKQyDvCZZ/6+wk8D56qmvTBMMVsCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:44:29.995864Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.11054","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:360902e2624d92421299a2fe3d2f4861800a82ecd149d3361c0637b9c2f1197b","sha256:8793ead7eb87766f8a6d4593dee01490bc5feae2cde4cf413a36410eb39af405"],"state_sha256":"4d9b58546b5d8307d525c70df001c4e112979ad65193e13f3f0f3171eb9eb22d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bl1w5wBXidaHcQXyCiBpl8VOSNSsE4vvjbWGAA1LoTcxSVi2fl1n57j4SQJLUWpoq2RXvFAhTk20SCI5spurDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:39:54.650543Z","bundle_sha256":"e5c8a8431b3febbd76258eeefe7c5c2e916759fe1d8bd88c1b4902ed4a11ebb0"}}