{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:JQEGE3S2X4QDPZUCJGFNPPE6YF","short_pith_number":"pith:JQEGE3S2","canonical_record":{"source":{"id":"1707.03172","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-11T08:33:55Z","cross_cats_sorted":[],"title_canon_sha256":"5e3325775770e98853d5c9f4bca3853dc2063f817b550d9b2b42cdca25f6cc30","abstract_canon_sha256":"48ef18f063bc7d95f2fdb273e711cc4dda800ac8d219685c1f250f7af33a442e"},"schema_version":"1.0"},"canonical_sha256":"4c08626e5abf2037e682498ad7bc9ec14242382f99228391011f9b5fa80adf32","source":{"kind":"arxiv","id":"1707.03172","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.03172","created_at":"2026-05-17T23:58:54Z"},{"alias_kind":"arxiv_version","alias_value":"1707.03172v1","created_at":"2026-05-17T23:58:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.03172","created_at":"2026-05-17T23:58:54Z"},{"alias_kind":"pith_short_12","alias_value":"JQEGE3S2X4QD","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"JQEGE3S2X4QDPZUC","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"JQEGE3S2","created_at":"2026-05-18T12:31:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:JQEGE3S2X4QDPZUCJGFNPPE6YF","target":"record","payload":{"canonical_record":{"source":{"id":"1707.03172","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-11T08:33:55Z","cross_cats_sorted":[],"title_canon_sha256":"5e3325775770e98853d5c9f4bca3853dc2063f817b550d9b2b42cdca25f6cc30","abstract_canon_sha256":"48ef18f063bc7d95f2fdb273e711cc4dda800ac8d219685c1f250f7af33a442e"},"schema_version":"1.0"},"canonical_sha256":"4c08626e5abf2037e682498ad7bc9ec14242382f99228391011f9b5fa80adf32","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:54.722445Z","signature_b64":"fvWzcF8rzkOv/0CftsU/Wk/7OyHzsBYLUdac6pJ6+XFTuSHEo2edv4uyDGghd9nwUowQ1kWHlOds0t/BbKPABg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c08626e5abf2037e682498ad7bc9ec14242382f99228391011f9b5fa80adf32","last_reissued_at":"2026-05-17T23:58:54.722032Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:54.722032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.03172","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":"2026-05-17T23:58:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HBUd4SMuitNJ6BHjcP9O+ndIE//a6aRi+SsUGBS6kcgBi4vs1cmBc+y23cNYX/lkl82Rm3HJUs9Xt+3Ng8i/DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T08:27:04.709433Z"},"content_sha256":"da1567ddab47a7b1e30d50a6baba384973f545e2343920b48ce066ead1b96eff","schema_version":"1.0","event_id":"sha256:da1567ddab47a7b1e30d50a6baba384973f545e2343920b48ce066ead1b96eff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:JQEGE3S2X4QDPZUCJGFNPPE6YF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dataset for a Neural Natural Language Interface for Databases (NNLIDB)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Florin Brad, Ionel Hosu, Radu Iacob, Traian Rebedea","submitted_at":"2017-07-11T08:33:55Z","abstract_excerpt":"Progress in natural language interfaces to databases (NLIDB) has been slow mainly due to linguistic issues (such as language ambiguity) and domain portability. Moreover, the lack of a large corpus to be used as a standard benchmark has made data-driven approaches difficult to develop and compare. In this paper, we revisit the problem of NLIDBs and recast it as a sequence translation problem. To this end, we introduce a large dataset extracted from the Stack Exchange Data Explorer website, which can be used for training neural natural language interfaces for databases. We also report encouragin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.03172","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":""},"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":"2026-05-17T23:58:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PtIbKp6WbDvEYzi5w7opz8XsWuPje7TBlEzhem7ph2QJFigYgBstTRvHoUoVkyOaxGuXUojYFjNG1r8v4HXNDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T08:27:04.710073Z"},"content_sha256":"1d559120140ffbd82ac6d53839075faaf7d8bac047f54a28cb91dbdff8f822bb","schema_version":"1.0","event_id":"sha256:1d559120140ffbd82ac6d53839075faaf7d8bac047f54a28cb91dbdff8f822bb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JQEGE3S2X4QDPZUCJGFNPPE6YF/bundle.json","state_url":"https://pith.science/pith/JQEGE3S2X4QDPZUCJGFNPPE6YF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JQEGE3S2X4QDPZUCJGFNPPE6YF/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":"2026-06-06T08:27:04Z","links":{"resolver":"https://pith.science/pith/JQEGE3S2X4QDPZUCJGFNPPE6YF","bundle":"https://pith.science/pith/JQEGE3S2X4QDPZUCJGFNPPE6YF/bundle.json","state":"https://pith.science/pith/JQEGE3S2X4QDPZUCJGFNPPE6YF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JQEGE3S2X4QDPZUCJGFNPPE6YF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:JQEGE3S2X4QDPZUCJGFNPPE6YF","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":"48ef18f063bc7d95f2fdb273e711cc4dda800ac8d219685c1f250f7af33a442e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-11T08:33:55Z","title_canon_sha256":"5e3325775770e98853d5c9f4bca3853dc2063f817b550d9b2b42cdca25f6cc30"},"schema_version":"1.0","source":{"id":"1707.03172","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.03172","created_at":"2026-05-17T23:58:54Z"},{"alias_kind":"arxiv_version","alias_value":"1707.03172v1","created_at":"2026-05-17T23:58:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.03172","created_at":"2026-05-17T23:58:54Z"},{"alias_kind":"pith_short_12","alias_value":"JQEGE3S2X4QD","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"JQEGE3S2X4QDPZUC","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"JQEGE3S2","created_at":"2026-05-18T12:31:24Z"}],"graph_snapshots":[{"event_id":"sha256:1d559120140ffbd82ac6d53839075faaf7d8bac047f54a28cb91dbdff8f822bb","target":"graph","created_at":"2026-05-17T23:58:54Z","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"},"paper":{"abstract_excerpt":"Progress in natural language interfaces to databases (NLIDB) has been slow mainly due to linguistic issues (such as language ambiguity) and domain portability. Moreover, the lack of a large corpus to be used as a standard benchmark has made data-driven approaches difficult to develop and compare. In this paper, we revisit the problem of NLIDBs and recast it as a sequence translation problem. To this end, we introduce a large dataset extracted from the Stack Exchange Data Explorer website, which can be used for training neural natural language interfaces for databases. We also report encouragin","authors_text":"Florin Brad, Ionel Hosu, Radu Iacob, Traian Rebedea","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-11T08:33:55Z","title":"Dataset for a Neural Natural Language Interface for Databases (NNLIDB)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.03172","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:da1567ddab47a7b1e30d50a6baba384973f545e2343920b48ce066ead1b96eff","target":"record","created_at":"2026-05-17T23:58:54Z","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":"48ef18f063bc7d95f2fdb273e711cc4dda800ac8d219685c1f250f7af33a442e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-11T08:33:55Z","title_canon_sha256":"5e3325775770e98853d5c9f4bca3853dc2063f817b550d9b2b42cdca25f6cc30"},"schema_version":"1.0","source":{"id":"1707.03172","kind":"arxiv","version":1}},"canonical_sha256":"4c08626e5abf2037e682498ad7bc9ec14242382f99228391011f9b5fa80adf32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c08626e5abf2037e682498ad7bc9ec14242382f99228391011f9b5fa80adf32","first_computed_at":"2026-05-17T23:58:54.722032Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:58:54.722032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fvWzcF8rzkOv/0CftsU/Wk/7OyHzsBYLUdac6pJ6+XFTuSHEo2edv4uyDGghd9nwUowQ1kWHlOds0t/BbKPABg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:58:54.722445Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.03172","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da1567ddab47a7b1e30d50a6baba384973f545e2343920b48ce066ead1b96eff","sha256:1d559120140ffbd82ac6d53839075faaf7d8bac047f54a28cb91dbdff8f822bb"],"state_sha256":"5303ab170f86065bee2bd11b2264306de7fb3acf37ddc2de83be71d61769c30c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4BxJHVobhjNY60xIMMox7JaUD+UFDQvA8fCEYo3Fxi4bDcuQuUtajdTk+ZDOwo/XyEVTJey5vBR2/bIY8v9QAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T08:27:04.713874Z","bundle_sha256":"c0dbaba0d0b70dfd577f9f2812e5f553155e4027bbac7adccd7a7b903531a018"}}