{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VIY2OGXWDUTXZXOKVYQYHTX4I7","short_pith_number":"pith:VIY2OGXW","canonical_record":{"source":{"id":"2505.18122","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T17:28:43Z","cross_cats_sorted":[],"title_canon_sha256":"67fef247103c22b52f0ce341cfe1a629defd893268f5a8b1a1714d521b27aa54","abstract_canon_sha256":"939019bdf0c2b9398c0488c3d090cd68b233614e2bb2766a57af36566a853588"},"schema_version":"1.0"},"canonical_sha256":"aa31a71af61d277cddcaae2183cefc47da7de1e771ac8c4e050104d522126ab4","source":{"kind":"arxiv","id":"2505.18122","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18122","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18122v1","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18122","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"pith_short_12","alias_value":"VIY2OGXWDUTX","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"pith_short_16","alias_value":"VIY2OGXWDUTXZXOK","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"pith_short_8","alias_value":"VIY2OGXW","created_at":"2026-07-05T11:08:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VIY2OGXWDUTXZXOKVYQYHTX4I7","target":"record","payload":{"canonical_record":{"source":{"id":"2505.18122","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T17:28:43Z","cross_cats_sorted":[],"title_canon_sha256":"67fef247103c22b52f0ce341cfe1a629defd893268f5a8b1a1714d521b27aa54","abstract_canon_sha256":"939019bdf0c2b9398c0488c3d090cd68b233614e2bb2766a57af36566a853588"},"schema_version":"1.0"},"canonical_sha256":"aa31a71af61d277cddcaae2183cefc47da7de1e771ac8c4e050104d522126ab4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:36.955589Z","signature_b64":"Wn1jnkOfRoAZmOfA+ADKN0bjgdDlz5nYxFMSEpDctsv1zKRrGRXPkVfbFMnGF22TWEFfFvRsKNXhaGplm8hDDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa31a71af61d277cddcaae2183cefc47da7de1e771ac8c4e050104d522126ab4","last_reissued_at":"2026-07-05T11:08:36.955086Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:36.955086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.18122","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":"2026-07-05T11:08:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Y/ik+11hffRlk0NeTjzaFN6EHMFVdOqK4SxqBa52Wqqc1TlGPU7NWeNA09axujIk/XMazFTz1L+jmfEm6FKDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T23:57:34.546181Z"},"content_sha256":"5793ded4aa9d091b2df8f005cedcdec9d79592776ae472482ad7ce53f3df2fe3","schema_version":"1.0","event_id":"sha256:5793ded4aa9d091b2df8f005cedcdec9d79592776ae472482ad7ce53f3df2fe3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VIY2OGXWDUTXZXOKVYQYHTX4I7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UNJOIN: Enhancing Multi-Table Text-to-SQL Generation via Schema Simplification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Roth, Poojah Ganesan, Rajat Aayush Jha, Vivek Gupta","submitted_at":"2025-05-23T17:28:43Z","abstract_excerpt":"Recent advances in large language models (LLMs) have greatly improved Text-to-SQL performance for single-table queries. But, it remains challenging in multi-table databases due to complex schema and relational operations. Existing methods often struggle with retrieving the right tables and columns, generating accurate JOINs and UNIONs, and generalizing across diverse schemas. To address these issues, we introduce UNJOIN, a two-stage framework that decouples the retrieval of schema elements from SQL logic generation. In the first stage, we merge the column names of all tables in the database in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18122","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/2505.18122/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":"2026-07-05T11:08:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jwnSjIlb3L96lDNqlvl9mXGf4Y3birlwoTdQwSosFvZv6VgLLKHl5cJHPdp4EUpRzYluvxcdy5Emb3FFYnEwBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T23:57:34.546845Z"},"content_sha256":"f8a7a3e70f306349785e3c4dbb204094029172fbacab562f79d12616ba21c98e","schema_version":"1.0","event_id":"sha256:f8a7a3e70f306349785e3c4dbb204094029172fbacab562f79d12616ba21c98e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VIY2OGXWDUTXZXOKVYQYHTX4I7/bundle.json","state_url":"https://pith.science/pith/VIY2OGXWDUTXZXOKVYQYHTX4I7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VIY2OGXWDUTXZXOKVYQYHTX4I7/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":"2026-08-20T23:57:34Z","links":{"resolver":"https://pith.science/pith/VIY2OGXWDUTXZXOKVYQYHTX4I7","bundle":"https://pith.science/pith/VIY2OGXWDUTXZXOKVYQYHTX4I7/bundle.json","state":"https://pith.science/pith/VIY2OGXWDUTXZXOKVYQYHTX4I7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VIY2OGXWDUTXZXOKVYQYHTX4I7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VIY2OGXWDUTXZXOKVYQYHTX4I7","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":"939019bdf0c2b9398c0488c3d090cd68b233614e2bb2766a57af36566a853588","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T17:28:43Z","title_canon_sha256":"67fef247103c22b52f0ce341cfe1a629defd893268f5a8b1a1714d521b27aa54"},"schema_version":"1.0","source":{"id":"2505.18122","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18122","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18122v1","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18122","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"pith_short_12","alias_value":"VIY2OGXWDUTX","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"pith_short_16","alias_value":"VIY2OGXWDUTXZXOK","created_at":"2026-07-05T11:08:36Z"},{"alias_kind":"pith_short_8","alias_value":"VIY2OGXW","created_at":"2026-07-05T11:08:36Z"}],"graph_snapshots":[{"event_id":"sha256:f8a7a3e70f306349785e3c4dbb204094029172fbacab562f79d12616ba21c98e","target":"graph","created_at":"2026-07-05T11:08:36Z","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/2505.18122/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in large language models (LLMs) have greatly improved Text-to-SQL performance for single-table queries. But, it remains challenging in multi-table databases due to complex schema and relational operations. Existing methods often struggle with retrieving the right tables and columns, generating accurate JOINs and UNIONs, and generalizing across diverse schemas. To address these issues, we introduce UNJOIN, a two-stage framework that decouples the retrieval of schema elements from SQL logic generation. In the first stage, we merge the column names of all tables in the database in","authors_text":"Dan Roth, Poojah Ganesan, Rajat Aayush Jha, Vivek Gupta","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T17:28:43Z","title":"UNJOIN: Enhancing Multi-Table Text-to-SQL Generation via Schema Simplification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18122","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":"sha256:5793ded4aa9d091b2df8f005cedcdec9d79592776ae472482ad7ce53f3df2fe3","target":"record","created_at":"2026-07-05T11:08:36Z","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":"939019bdf0c2b9398c0488c3d090cd68b233614e2bb2766a57af36566a853588","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T17:28:43Z","title_canon_sha256":"67fef247103c22b52f0ce341cfe1a629defd893268f5a8b1a1714d521b27aa54"},"schema_version":"1.0","source":{"id":"2505.18122","kind":"arxiv","version":1}},"canonical_sha256":"aa31a71af61d277cddcaae2183cefc47da7de1e771ac8c4e050104d522126ab4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa31a71af61d277cddcaae2183cefc47da7de1e771ac8c4e050104d522126ab4","first_computed_at":"2026-07-05T11:08:36.955086Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:36.955086Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Wn1jnkOfRoAZmOfA+ADKN0bjgdDlz5nYxFMSEpDctsv1zKRrGRXPkVfbFMnGF22TWEFfFvRsKNXhaGplm8hDDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:36.955589Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.18122","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5793ded4aa9d091b2df8f005cedcdec9d79592776ae472482ad7ce53f3df2fe3","sha256:f8a7a3e70f306349785e3c4dbb204094029172fbacab562f79d12616ba21c98e"],"state_sha256":"64a72d2a7656701db51097dc948e74966e9a5622f291484d969ccc913288fbc9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xtd1B7XCEDYzjdGU+QcqMH3VUlmyn6tpfDbXHruEOXz3x05dTVz5RPUWa0hz4ysVJbf7uktvJ874UdR+UzsvAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T23:57:34.551585Z","bundle_sha256":"1cc33de0e776db250ab493e8b0012a2d960cd630780613939e72259bfadffd38"}}