{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JCLH7FLHQTM7O553J7ZV36NY7S","short_pith_number":"pith:JCLH7FLH","canonical_record":{"source":{"id":"2608.07946","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-08-08T06:12:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cec569bc71ddff3356eb3e15f0275390916daeb1099cce8ddd6551f4bb64e422","abstract_canon_sha256":"01abae7c021ae49ebe026852d6a2ff92316cd1be7804cea7dfeef5afa5473c80"},"schema_version":"1.0"},"canonical_sha256":"48967f956784d9f777bb4ff35df9b8fc92b3c16229d7122fb566bb01c9549057","source":{"kind":"arxiv","id":"2608.07946","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.07946","created_at":"2026-08-11T01:19:05Z"},{"alias_kind":"arxiv_version","alias_value":"2608.07946v1","created_at":"2026-08-11T01:19:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07946","created_at":"2026-08-11T01:19:05Z"},{"alias_kind":"pith_short_12","alias_value":"JCLH7FLHQTM7","created_at":"2026-08-11T01:19:05Z"},{"alias_kind":"pith_short_16","alias_value":"JCLH7FLHQTM7O553","created_at":"2026-08-11T01:19:05Z"},{"alias_kind":"pith_short_8","alias_value":"JCLH7FLH","created_at":"2026-08-11T01:19:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JCLH7FLHQTM7O553J7ZV36NY7S","target":"record","payload":{"canonical_record":{"source":{"id":"2608.07946","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-08-08T06:12:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cec569bc71ddff3356eb3e15f0275390916daeb1099cce8ddd6551f4bb64e422","abstract_canon_sha256":"01abae7c021ae49ebe026852d6a2ff92316cd1be7804cea7dfeef5afa5473c80"},"schema_version":"1.0"},"canonical_sha256":"48967f956784d9f777bb4ff35df9b8fc92b3c16229d7122fb566bb01c9549057","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:19:05.578080Z","signature_b64":"Ra2xiJoDoqQyUR1M3ZQvTzZ4EBDOfZKtFnX+GPlGU5Q2hxRM65+Fi4ijf/+2kz1+llgVrHmE7mBi2FTErEtWAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48967f956784d9f777bb4ff35df9b8fc92b3c16229d7122fb566bb01c9549057","last_reissued_at":"2026-08-11T01:19:05.575622Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:19:05.575622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.07946","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":"2026-08-11T01:19:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wW/TewZHi/MkIyhmlCVWNY50uq7X8NrbAnOskblzvIBC5l0I5y32J8cl3p26mGsV1PfiV9p2ScaEXW9gmINeCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T00:14:05.714791Z"},"content_sha256":"59427332274636931a4b68c6b63da08485bc9938cae4f5c39bab1eff7df97b16","schema_version":"1.0","event_id":"sha256:59427332274636931a4b68c6b63da08485bc9938cae4f5c39bab1eff7df97b16"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JCLH7FLHQTM7O553J7ZV36NY7S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Metadata Reconstruction from Values Alone: Recovering Column Semantics in Undocumented Warehouses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Mike Helwig","submitted_at":"2026-08-08T06:12:18Z","abstract_excerpt":"Text-to-SQL benchmarks ship schemas whose column names already say what the columns mean. Production warehouses are the inverse: cryptic identifiers, partial or absent documentation. We address the problem they pose first: recovering what columns and values mean from the data itself.\n  Rosetta places a language model inside a verification harness: a deterministic profiler extracts structural evidence (value fingerprints, a 26-pattern library, checksum verdicts), the model proposes semantics conditioned on that evidence, and every fact carries provenance and a confidence bounded by its evidence"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07946","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/2608.07946/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":"2026-08-11T01:19:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w++wE+bAggPkoQWQ5YSvphsR92dcUHcIPNAqBIjLmR3vKXX3LW5KJUePj+ys3vSAZFpPTSCTtpvG6vGmP3w0Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T00:14:05.715771Z"},"content_sha256":"06bf34a88161cfc1332ab50cb51425f5f3f1f6951c3001ebb5a2ef3c9edf01cc","schema_version":"1.0","event_id":"sha256:06bf34a88161cfc1332ab50cb51425f5f3f1f6951c3001ebb5a2ef3c9edf01cc"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:JCLH7FLHQTM7O553J7ZV36NY7S","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1007/s00778-015-0389-y) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Ziawasch Abedjan, Lukasz Golab, and Felix Naumann. 2015. Profiling Relational Data: A Survey.The VLDB Journal24, 4 (2015), 557–581. doi:10.1007/s00778- 015-0389-y","arxiv_id":"2608.07946","detector":"doi_compliance","evidence":{"ref_index":1,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.1007/s00778-","reconstructed_doi":"10.1007/s00778-015-0389-y"},"severity":"advisory","ref_index":1,"audited_at":"2026-08-12T00:48:50.712683Z","event_type":"pith.integrity.v1","detected_doi":"10.1007/s00778-015-0389-y","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"a098ac42401f793f2687699f2ddacc7120a6afdf18c4f951bf59c389b44be203","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":19235,"payload_sha256":"7cf6db0ed37cb34d4a77777628c1caade011020987ff202e6832a43b199d8186","signature_b64":"+hyKic8pt5lu7p/9ntz02K2DZZxcwVS+rlbFSi4czQBnevfVQuejqhAStW6w29bPAMAuaz7Q63OC+KGVWUfuBA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-12T00:53:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5hSJVVq2YqSYqpZVh+YMrJERGXAoxUSHpBG0OooN+qAWB1pBmiR6/gba/7tGNDAMZVcEZ5mTQscRR76B/eDSBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T00:14:05.722234Z"},"content_sha256":"3a4efe31c5b5a768c48790f70e301d90ff8df8989432fd4d570bb9778a2f3333","schema_version":"1.0","event_id":"sha256:3a4efe31c5b5a768c48790f70e301d90ff8df8989432fd4d570bb9778a2f3333"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JCLH7FLHQTM7O553J7ZV36NY7S/bundle.json","state_url":"https://pith.science/pith/JCLH7FLHQTM7O553J7ZV36NY7S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JCLH7FLHQTM7O553J7ZV36NY7S/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":"2026-08-18T00:14:05Z","links":{"resolver":"https://pith.science/pith/JCLH7FLHQTM7O553J7ZV36NY7S","bundle":"https://pith.science/pith/JCLH7FLHQTM7O553J7ZV36NY7S/bundle.json","state":"https://pith.science/pith/JCLH7FLHQTM7O553J7ZV36NY7S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JCLH7FLHQTM7O553J7ZV36NY7S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JCLH7FLHQTM7O553J7ZV36NY7S","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"01abae7c021ae49ebe026852d6a2ff92316cd1be7804cea7dfeef5afa5473c80","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-08-08T06:12:18Z","title_canon_sha256":"cec569bc71ddff3356eb3e15f0275390916daeb1099cce8ddd6551f4bb64e422"},"schema_version":"1.0","source":{"id":"2608.07946","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.07946","created_at":"2026-08-11T01:19:05Z"},{"alias_kind":"arxiv_version","alias_value":"2608.07946v1","created_at":"2026-08-11T01:19:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07946","created_at":"2026-08-11T01:19:05Z"},{"alias_kind":"pith_short_12","alias_value":"JCLH7FLHQTM7","created_at":"2026-08-11T01:19:05Z"},{"alias_kind":"pith_short_16","alias_value":"JCLH7FLHQTM7O553","created_at":"2026-08-11T01:19:05Z"},{"alias_kind":"pith_short_8","alias_value":"JCLH7FLH","created_at":"2026-08-11T01:19:05Z"}],"graph_snapshots":[{"event_id":"sha256:06bf34a88161cfc1332ab50cb51425f5f3f1f6951c3001ebb5a2ef3c9edf01cc","target":"graph","created_at":"2026-08-11T01:19:05Z","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/2608.07946/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-SQL benchmarks ship schemas whose column names already say what the columns mean. Production warehouses are the inverse: cryptic identifiers, partial or absent documentation. We address the problem they pose first: recovering what columns and values mean from the data itself.\n  Rosetta places a language model inside a verification harness: a deterministic profiler extracts structural evidence (value fingerprints, a 26-pattern library, checksum verdicts), the model proposes semantics conditioned on that evidence, and every fact carries provenance and a confidence bounded by its evidence","authors_text":"Mike Helwig","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-08-08T06:12:18Z","title":"Metadata Reconstruction from Values Alone: Recovering Column Semantics in Undocumented Warehouses"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07946","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":"sha256:59427332274636931a4b68c6b63da08485bc9938cae4f5c39bab1eff7df97b16","target":"record","created_at":"2026-08-11T01:19:05Z","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":"01abae7c021ae49ebe026852d6a2ff92316cd1be7804cea7dfeef5afa5473c80","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-08-08T06:12:18Z","title_canon_sha256":"cec569bc71ddff3356eb3e15f0275390916daeb1099cce8ddd6551f4bb64e422"},"schema_version":"1.0","source":{"id":"2608.07946","kind":"arxiv","version":1}},"canonical_sha256":"48967f956784d9f777bb4ff35df9b8fc92b3c16229d7122fb566bb01c9549057","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48967f956784d9f777bb4ff35df9b8fc92b3c16229d7122fb566bb01c9549057","first_computed_at":"2026-08-11T01:19:05.575622Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:19:05.575622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ra2xiJoDoqQyUR1M3ZQvTzZ4EBDOfZKtFnX+GPlGU5Q2hxRM65+Fi4ijf/+2kz1+llgVrHmE7mBi2FTErEtWAQ==","signature_status":"signed_v1","signed_at":"2026-08-11T01:19:05.578080Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.07946","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59427332274636931a4b68c6b63da08485bc9938cae4f5c39bab1eff7df97b16","sha256:06bf34a88161cfc1332ab50cb51425f5f3f1f6951c3001ebb5a2ef3c9edf01cc","sha256:3a4efe31c5b5a768c48790f70e301d90ff8df8989432fd4d570bb9778a2f3333"],"state_sha256":"16b0027552b3f2efbed60e4161cfd27d6cc11dc02ff85c5388805c701bac0fa3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7x54B7fwMYNaGglSO/+DLuMwW9RcObvDiwRUfJuU5w/ZrBnh3zRPC0tX39lRKSq5Urw9KP2meWbmjRHs4/LnCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T00:14:05.726828Z","bundle_sha256":"dbea9650a968bb3a781d2f03427d8b674f6771a7fcbc7af5941b10cd5eaf08ea"}}