{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CXDFQKWX7ZPVMYZJ3AUSRBYVPA","short_pith_number":"pith:CXDFQKWX","canonical_record":{"source":{"id":"2504.09207","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2025-04-12T13:20:50Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"7428387746221a55a581a5cc5793c6fadbf88e40b54921fd0d8ae24960b033dc","abstract_canon_sha256":"c144d8878dc88437c7a4f8dd98edddfb9eb5195c13e00b9a375d1820e0995667"},"schema_version":"1.0"},"canonical_sha256":"15c6582ad7fe5f566329d82928871578014b14672be33cc9f76d93be42dfc435","source":{"kind":"arxiv","id":"2504.09207","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.09207","created_at":"2026-07-05T10:48:33Z"},{"alias_kind":"arxiv_version","alias_value":"2504.09207v1","created_at":"2026-07-05T10:48:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09207","created_at":"2026-07-05T10:48:33Z"},{"alias_kind":"pith_short_12","alias_value":"CXDFQKWX7ZPV","created_at":"2026-07-05T10:48:33Z"},{"alias_kind":"pith_short_16","alias_value":"CXDFQKWX7ZPVMYZJ","created_at":"2026-07-05T10:48:33Z"},{"alias_kind":"pith_short_8","alias_value":"CXDFQKWX","created_at":"2026-07-05T10:48:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CXDFQKWX7ZPVMYZJ3AUSRBYVPA","target":"record","payload":{"canonical_record":{"source":{"id":"2504.09207","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2025-04-12T13:20:50Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"7428387746221a55a581a5cc5793c6fadbf88e40b54921fd0d8ae24960b033dc","abstract_canon_sha256":"c144d8878dc88437c7a4f8dd98edddfb9eb5195c13e00b9a375d1820e0995667"},"schema_version":"1.0"},"canonical_sha256":"15c6582ad7fe5f566329d82928871578014b14672be33cc9f76d93be42dfc435","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:33.334737Z","signature_b64":"pu8BBbWQD707LnPBkO67lf+jBVTXE0SFhOFB3Dp9KHNFqzmwJXjXzFI+b440J3H/QTgCu/U7oOY9c3G94UyzBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15c6582ad7fe5f566329d82928871578014b14672be33cc9f76d93be42dfc435","last_reissued_at":"2026-07-05T10:48:33.334294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:33.334294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.09207","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":"2026-07-05T10:48:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BQHStU1BJWj9+3GryZ5vQpBjtjJWGjCFAnYEeqM7jD0Ji9okkXW/tUITx1h3Y6rELAWxsfA7s/0t53Vy13EjDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:43:16.154674Z"},"content_sha256":"d5f303600bf6c818967970825d74e080d9acf98a8372595e8ea5148128b81498","schema_version":"1.0","event_id":"sha256:d5f303600bf6c818967970825d74e080d9acf98a8372595e8ea5148128b81498"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CXDFQKWX7ZPVMYZJ3AUSRBYVPA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End System","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.DB","authors_text":"Adila Krisnadhi, David Alexander, Muhammad Imam Luthfi Balaka, Qiming Wang, Raul Castro Fernandez, Yue Gong","submitted_at":"2025-04-12T13:20:50Z","abstract_excerpt":"Finding relevant tables among databases, lakes, and repositories is the first step in extracting value from data. Such a task remains difficult because assessing whether a table is relevant to a problem does not always depend only on its content but also on the context, which is usually tribal knowledge known to the individual or team. While tools like data catalogs and academic data discovery systems target this problem, they rely on keyword search or more complex interfaces, limiting non-technical users' ability to find relevant data. The advent of large language models (LLMs) offers a uniqu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09207","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/2504.09207/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":"2026-07-05T10:48:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"et67PHufthuOL1E2VZD8tV5GqOrxPEDT4EaNNbW2ercEQ7ir4mMOg8IT/Hhcn5OpjUAO4XKHz6dY+kGPU4Q6BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:43:16.155251Z"},"content_sha256":"e7dce04b026390459be1ee97cf9d4c3c8f81625e23664cafc8dd4d064816c425","schema_version":"1.0","event_id":"sha256:e7dce04b026390459be1ee97cf9d4c3c8f81625e23664cafc8dd4d064816c425"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CXDFQKWX7ZPVMYZJ3AUSRBYVPA/bundle.json","state_url":"https://pith.science/pith/CXDFQKWX7ZPVMYZJ3AUSRBYVPA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CXDFQKWX7ZPVMYZJ3AUSRBYVPA/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":"2026-08-10T11:43:16Z","links":{"resolver":"https://pith.science/pith/CXDFQKWX7ZPVMYZJ3AUSRBYVPA","bundle":"https://pith.science/pith/CXDFQKWX7ZPVMYZJ3AUSRBYVPA/bundle.json","state":"https://pith.science/pith/CXDFQKWX7ZPVMYZJ3AUSRBYVPA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CXDFQKWX7ZPVMYZJ3AUSRBYVPA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CXDFQKWX7ZPVMYZJ3AUSRBYVPA","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":"c144d8878dc88437c7a4f8dd98edddfb9eb5195c13e00b9a375d1820e0995667","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2025-04-12T13:20:50Z","title_canon_sha256":"7428387746221a55a581a5cc5793c6fadbf88e40b54921fd0d8ae24960b033dc"},"schema_version":"1.0","source":{"id":"2504.09207","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.09207","created_at":"2026-07-05T10:48:33Z"},{"alias_kind":"arxiv_version","alias_value":"2504.09207v1","created_at":"2026-07-05T10:48:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09207","created_at":"2026-07-05T10:48:33Z"},{"alias_kind":"pith_short_12","alias_value":"CXDFQKWX7ZPV","created_at":"2026-07-05T10:48:33Z"},{"alias_kind":"pith_short_16","alias_value":"CXDFQKWX7ZPVMYZJ","created_at":"2026-07-05T10:48:33Z"},{"alias_kind":"pith_short_8","alias_value":"CXDFQKWX","created_at":"2026-07-05T10:48:33Z"}],"graph_snapshots":[{"event_id":"sha256:e7dce04b026390459be1ee97cf9d4c3c8f81625e23664cafc8dd4d064816c425","target":"graph","created_at":"2026-07-05T10:48:33Z","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/2504.09207/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Finding relevant tables among databases, lakes, and repositories is the first step in extracting value from data. Such a task remains difficult because assessing whether a table is relevant to a problem does not always depend only on its content but also on the context, which is usually tribal knowledge known to the individual or team. While tools like data catalogs and academic data discovery systems target this problem, they rely on keyword search or more complex interfaces, limiting non-technical users' ability to find relevant data. The advent of large language models (LLMs) offers a uniqu","authors_text":"Adila Krisnadhi, David Alexander, Muhammad Imam Luthfi Balaka, Qiming Wang, Raul Castro Fernandez, Yue Gong","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2025-04-12T13:20:50Z","title":"Pneuma: Leveraging LLMs for Tabular Data Representation and Retrieval in an End-to-End System"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09207","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:d5f303600bf6c818967970825d74e080d9acf98a8372595e8ea5148128b81498","target":"record","created_at":"2026-07-05T10:48:33Z","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":"c144d8878dc88437c7a4f8dd98edddfb9eb5195c13e00b9a375d1820e0995667","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DB","submitted_at":"2025-04-12T13:20:50Z","title_canon_sha256":"7428387746221a55a581a5cc5793c6fadbf88e40b54921fd0d8ae24960b033dc"},"schema_version":"1.0","source":{"id":"2504.09207","kind":"arxiv","version":1}},"canonical_sha256":"15c6582ad7fe5f566329d82928871578014b14672be33cc9f76d93be42dfc435","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15c6582ad7fe5f566329d82928871578014b14672be33cc9f76d93be42dfc435","first_computed_at":"2026-07-05T10:48:33.334294Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:48:33.334294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pu8BBbWQD707LnPBkO67lf+jBVTXE0SFhOFB3Dp9KHNFqzmwJXjXzFI+b440J3H/QTgCu/U7oOY9c3G94UyzBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:48:33.334737Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.09207","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5f303600bf6c818967970825d74e080d9acf98a8372595e8ea5148128b81498","sha256:e7dce04b026390459be1ee97cf9d4c3c8f81625e23664cafc8dd4d064816c425"],"state_sha256":"a13011e6f0eebd426b94e273c345ebb6d2a65d10856f1e28ccad0181f6c137ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j88ORd8ZbdXhH9PCDT9e805VCVrEhKa+jR4ofm+lQHIsw8TD0U2ggNA3z6BfJzqkVrNXyM4bIX3vt09FQb+DCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T11:43:16.162272Z","bundle_sha256":"46df6b4a5c5769b551715dad69760da17c1638a7cd451a179b275d8eb14c3d75"}}