{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KQNPUH37OGA5FVTFIJM7564V6G","short_pith_number":"pith:KQNPUH37","canonical_record":{"source":{"id":"2401.10186","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-18T18:15:46Z","cross_cats_sorted":[],"title_canon_sha256":"233e32f53730385f746a9fde4a6b86adbe3d3435ed49a42c3572dad5f330b960","abstract_canon_sha256":"e2bcc89cc753918ba1ff266edae656ab3e429ae0a7c86a47ff9c7aa05c1cb8ff"},"schema_version":"1.0"},"canonical_sha256":"541afa1f7f7181d2d6654259fefb95f1891a2efb747ed10761cdfe1cde12d81a","source":{"kind":"arxiv","id":"2401.10186","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.10186","created_at":"2026-07-05T08:28:05Z"},{"alias_kind":"arxiv_version","alias_value":"2401.10186v3","created_at":"2026-07-05T08:28:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.10186","created_at":"2026-07-05T08:28:05Z"},{"alias_kind":"pith_short_12","alias_value":"KQNPUH37OGA5","created_at":"2026-07-05T08:28:05Z"},{"alias_kind":"pith_short_16","alias_value":"KQNPUH37OGA5FVTF","created_at":"2026-07-05T08:28:05Z"},{"alias_kind":"pith_short_8","alias_value":"KQNPUH37","created_at":"2026-07-05T08:28:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KQNPUH37OGA5FVTFIJM7564V6G","target":"record","payload":{"canonical_record":{"source":{"id":"2401.10186","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-18T18:15:46Z","cross_cats_sorted":[],"title_canon_sha256":"233e32f53730385f746a9fde4a6b86adbe3d3435ed49a42c3572dad5f330b960","abstract_canon_sha256":"e2bcc89cc753918ba1ff266edae656ab3e429ae0a7c86a47ff9c7aa05c1cb8ff"},"schema_version":"1.0"},"canonical_sha256":"541afa1f7f7181d2d6654259fefb95f1891a2efb747ed10761cdfe1cde12d81a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:05.091283Z","signature_b64":"0XY+AF3qdMawjVW2xJp1gWLriCHcaJd7K7HM3G8B5/j685ENw/x1YbpLSwXIBXl2K/+5Ol5y8LryPLXEHQWBAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"541afa1f7f7181d2d6654259fefb95f1891a2efb747ed10761cdfe1cde12d81a","last_reissued_at":"2026-07-05T08:28:05.090884Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:05.090884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.10186","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:28:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VMNXNLb1k/HY4YwsRdTTKCYl1g5JV7nD5P0LIdnN7mqPVPVc4d0K6oVpVw6p2HQpG29ormHN+y7JOG747UNRAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T09:16:27.172492Z"},"content_sha256":"cfc5e5601e59819013c8e47309a360fe609c302fa23909d9b108c332e65d0c9d","schema_version":"1.0","event_id":"sha256:cfc5e5601e59819013c8e47309a360fe609c302fa23909d9b108c332e65d0c9d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KQNPUH37OGA5FVTFIJM7564V6G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Traditional Benchmarks: Analyzing Behaviors of Open LLMs on Data-to-Text Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ond\\v{r}ej Du\\v{s}ek, Zden\\v{e}k Kasner","submitted_at":"2024-01-18T18:15:46Z","abstract_excerpt":"We analyze the behaviors of open large language models (LLMs) on the task of data-to-text (D2T) generation, i.e., generating coherent and relevant text from structured data. To avoid the issue of LLM training data contamination with standard benchmarks, we design Quintd - a tool for collecting novel structured data records from public APIs. We find that open LLMs (Llama 2, Mistral, and Zephyr) can generate fluent and coherent texts in zero-shot settings from data in common formats collected with Quintd. However, we show that the semantic accuracy of the outputs is a major issue: both according"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.10186","kind":"arxiv","version":3},"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/2401.10186/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":"2026-07-05T08:28:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TfmzMX+htXp0mv5oS24UkYj9JuDL1C2HnkgREe8MkkSGjEue2gz21GXnrHYu5cexWR3UiMZk73BdPKUT6JmgCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T09:16:27.172816Z"},"content_sha256":"a40fa8e31d865fd7e09dcc8a2c16f42db965a4c5b10e8ec1be1f9513fd1cd491","schema_version":"1.0","event_id":"sha256:a40fa8e31d865fd7e09dcc8a2c16f42db965a4c5b10e8ec1be1f9513fd1cd491"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KQNPUH37OGA5FVTFIJM7564V6G/bundle.json","state_url":"https://pith.science/pith/KQNPUH37OGA5FVTFIJM7564V6G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KQNPUH37OGA5FVTFIJM7564V6G/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":"2026-08-19T09:16:27Z","links":{"resolver":"https://pith.science/pith/KQNPUH37OGA5FVTFIJM7564V6G","bundle":"https://pith.science/pith/KQNPUH37OGA5FVTFIJM7564V6G/bundle.json","state":"https://pith.science/pith/KQNPUH37OGA5FVTFIJM7564V6G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KQNPUH37OGA5FVTFIJM7564V6G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KQNPUH37OGA5FVTFIJM7564V6G","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":"e2bcc89cc753918ba1ff266edae656ab3e429ae0a7c86a47ff9c7aa05c1cb8ff","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-18T18:15:46Z","title_canon_sha256":"233e32f53730385f746a9fde4a6b86adbe3d3435ed49a42c3572dad5f330b960"},"schema_version":"1.0","source":{"id":"2401.10186","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.10186","created_at":"2026-07-05T08:28:05Z"},{"alias_kind":"arxiv_version","alias_value":"2401.10186v3","created_at":"2026-07-05T08:28:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.10186","created_at":"2026-07-05T08:28:05Z"},{"alias_kind":"pith_short_12","alias_value":"KQNPUH37OGA5","created_at":"2026-07-05T08:28:05Z"},{"alias_kind":"pith_short_16","alias_value":"KQNPUH37OGA5FVTF","created_at":"2026-07-05T08:28:05Z"},{"alias_kind":"pith_short_8","alias_value":"KQNPUH37","created_at":"2026-07-05T08:28:05Z"}],"graph_snapshots":[{"event_id":"sha256:a40fa8e31d865fd7e09dcc8a2c16f42db965a4c5b10e8ec1be1f9513fd1cd491","target":"graph","created_at":"2026-07-05T08:28:05Z","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/2401.10186/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We analyze the behaviors of open large language models (LLMs) on the task of data-to-text (D2T) generation, i.e., generating coherent and relevant text from structured data. To avoid the issue of LLM training data contamination with standard benchmarks, we design Quintd - a tool for collecting novel structured data records from public APIs. We find that open LLMs (Llama 2, Mistral, and Zephyr) can generate fluent and coherent texts in zero-shot settings from data in common formats collected with Quintd. However, we show that the semantic accuracy of the outputs is a major issue: both according","authors_text":"Ond\\v{r}ej Du\\v{s}ek, Zden\\v{e}k Kasner","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-18T18:15:46Z","title":"Beyond Traditional Benchmarks: Analyzing Behaviors of Open LLMs on Data-to-Text Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.10186","kind":"arxiv","version":3},"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:cfc5e5601e59819013c8e47309a360fe609c302fa23909d9b108c332e65d0c9d","target":"record","created_at":"2026-07-05T08:28:05Z","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":"e2bcc89cc753918ba1ff266edae656ab3e429ae0a7c86a47ff9c7aa05c1cb8ff","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-18T18:15:46Z","title_canon_sha256":"233e32f53730385f746a9fde4a6b86adbe3d3435ed49a42c3572dad5f330b960"},"schema_version":"1.0","source":{"id":"2401.10186","kind":"arxiv","version":3}},"canonical_sha256":"541afa1f7f7181d2d6654259fefb95f1891a2efb747ed10761cdfe1cde12d81a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"541afa1f7f7181d2d6654259fefb95f1891a2efb747ed10761cdfe1cde12d81a","first_computed_at":"2026-07-05T08:28:05.090884Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:05.090884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0XY+AF3qdMawjVW2xJp1gWLriCHcaJd7K7HM3G8B5/j685ENw/x1YbpLSwXIBXl2K/+5Ol5y8LryPLXEHQWBAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:05.091283Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.10186","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cfc5e5601e59819013c8e47309a360fe609c302fa23909d9b108c332e65d0c9d","sha256:a40fa8e31d865fd7e09dcc8a2c16f42db965a4c5b10e8ec1be1f9513fd1cd491"],"state_sha256":"eedda5074e9bd34ec76f7a70dc0637d808ddfe80bb73ccc2517eec7bdb051c54"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kw3wMiXbZwY+E3z8ZvFCh7PWG3x35IoHKbo0r8YTK4Gk3eMVkcp2gxuIfZ4rg2bhFRNngbnAZnD4TXfgvMU3CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T09:16:27.175764Z","bundle_sha256":"d766ddc07fc457378668f36a814a3271ef64477b048036e53abe6a61192d9191"}}