{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:OXPDYS7IGRZN53D7XQ5XLXB67W","short_pith_number":"pith:OXPDYS7I","canonical_record":{"source":{"id":"2307.07312","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-14T12:45:03Z","cross_cats_sorted":[],"title_canon_sha256":"fa8eaa1428afe0ad1fd23bf6d06623c819f6381b6b7cfb19d7b24ddf4b0e5bc5","abstract_canon_sha256":"5a80fe93a169804c33c7dfb99ef98bcf950612bc08dbd396aa81779215906bc5"},"schema_version":"1.0"},"canonical_sha256":"75de3c4be83472deec7fbc3b75dc3efd827f9ff5a71202f1fdcdbe3643cbfc46","source":{"kind":"arxiv","id":"2307.07312","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.07312","created_at":"2026-07-05T06:43:24Z"},{"alias_kind":"arxiv_version","alias_value":"2307.07312v2","created_at":"2026-07-05T06:43:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07312","created_at":"2026-07-05T06:43:24Z"},{"alias_kind":"pith_short_12","alias_value":"OXPDYS7IGRZN","created_at":"2026-07-05T06:43:24Z"},{"alias_kind":"pith_short_16","alias_value":"OXPDYS7IGRZN53D7","created_at":"2026-07-05T06:43:24Z"},{"alias_kind":"pith_short_8","alias_value":"OXPDYS7I","created_at":"2026-07-05T06:43:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:OXPDYS7IGRZN53D7XQ5XLXB67W","target":"record","payload":{"canonical_record":{"source":{"id":"2307.07312","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-14T12:45:03Z","cross_cats_sorted":[],"title_canon_sha256":"fa8eaa1428afe0ad1fd23bf6d06623c819f6381b6b7cfb19d7b24ddf4b0e5bc5","abstract_canon_sha256":"5a80fe93a169804c33c7dfb99ef98bcf950612bc08dbd396aa81779215906bc5"},"schema_version":"1.0"},"canonical_sha256":"75de3c4be83472deec7fbc3b75dc3efd827f9ff5a71202f1fdcdbe3643cbfc46","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:43:24.216219Z","signature_b64":"/nzCoYMBtYG4ZOM9+bY0/pNNw7buz+GHJ7evw9f1R6UoSIsspJi2yzf6ekBevlJTeGBl/ZIGMKiiRMTM7akhBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75de3c4be83472deec7fbc3b75dc3efd827f9ff5a71202f1fdcdbe3643cbfc46","last_reissued_at":"2026-07-05T06:43:24.215750Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:43:24.215750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.07312","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:43:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o1mZ3XRIkf0KANm+GcB3OcRW7PXXIfMRPVTbW1EkGDAsk8io4bWK+PztB6gkUCJcSgGIJH/UUUKGYgwuhKYEAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:37:06.006207Z"},"content_sha256":"30eda81c01373692258ce555c4b4d74d6d1d5ef6174e6ccb52e52f081fc864b2","schema_version":"1.0","event_id":"sha256:30eda81c01373692258ce555c4b4d74d6d1d5ef6174e6ccb52e52f081fc864b2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:OXPDYS7IGRZN53D7XQ5XLXB67W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Using Large Language Models for Zero-Shot Natural Language Generation from Knowledge Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Agnes Axelsson, Gabriel Skantze","submitted_at":"2023-07-14T12:45:03Z","abstract_excerpt":"In any system that uses structured knowledge graph (KG) data as its underlying knowledge representation, KG-to-text generation is a useful tool for turning parts of the graph data into text that can be understood by humans. Recent work has shown that models that make use of pretraining on large amounts of text data can perform well on the KG-to-text task even with relatively small sets of training data on the specific graph-to-text task. In this paper, we build on this concept by using large language models to perform zero-shot generation based on nothing but the model's understanding of the t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07312","kind":"arxiv","version":2},"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/2307.07312/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":"2026-07-05T06:43:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ceeQ9EQ3e9wXduPP1BK56TrlpoBu09Zy/tiiFB8xjeZO0rnDkOCgbCz/+J9VQQfNaHlEK22fP1v7KQxXZAivCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T06:37:06.006733Z"},"content_sha256":"cb7367d4e6ef9ff996e790fae68b642003ecd19384d6dd502cd7728d1b36a41f","schema_version":"1.0","event_id":"sha256:cb7367d4e6ef9ff996e790fae68b642003ecd19384d6dd502cd7728d1b36a41f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OXPDYS7IGRZN53D7XQ5XLXB67W/bundle.json","state_url":"https://pith.science/pith/OXPDYS7IGRZN53D7XQ5XLXB67W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OXPDYS7IGRZN53D7XQ5XLXB67W/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":"2026-08-09T06:37:06Z","links":{"resolver":"https://pith.science/pith/OXPDYS7IGRZN53D7XQ5XLXB67W","bundle":"https://pith.science/pith/OXPDYS7IGRZN53D7XQ5XLXB67W/bundle.json","state":"https://pith.science/pith/OXPDYS7IGRZN53D7XQ5XLXB67W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OXPDYS7IGRZN53D7XQ5XLXB67W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OXPDYS7IGRZN53D7XQ5XLXB67W","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":"5a80fe93a169804c33c7dfb99ef98bcf950612bc08dbd396aa81779215906bc5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-14T12:45:03Z","title_canon_sha256":"fa8eaa1428afe0ad1fd23bf6d06623c819f6381b6b7cfb19d7b24ddf4b0e5bc5"},"schema_version":"1.0","source":{"id":"2307.07312","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.07312","created_at":"2026-07-05T06:43:24Z"},{"alias_kind":"arxiv_version","alias_value":"2307.07312v2","created_at":"2026-07-05T06:43:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07312","created_at":"2026-07-05T06:43:24Z"},{"alias_kind":"pith_short_12","alias_value":"OXPDYS7IGRZN","created_at":"2026-07-05T06:43:24Z"},{"alias_kind":"pith_short_16","alias_value":"OXPDYS7IGRZN53D7","created_at":"2026-07-05T06:43:24Z"},{"alias_kind":"pith_short_8","alias_value":"OXPDYS7I","created_at":"2026-07-05T06:43:24Z"}],"graph_snapshots":[{"event_id":"sha256:cb7367d4e6ef9ff996e790fae68b642003ecd19384d6dd502cd7728d1b36a41f","target":"graph","created_at":"2026-07-05T06:43:24Z","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/2307.07312/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In any system that uses structured knowledge graph (KG) data as its underlying knowledge representation, KG-to-text generation is a useful tool for turning parts of the graph data into text that can be understood by humans. Recent work has shown that models that make use of pretraining on large amounts of text data can perform well on the KG-to-text task even with relatively small sets of training data on the specific graph-to-text task. In this paper, we build on this concept by using large language models to perform zero-shot generation based on nothing but the model's understanding of the t","authors_text":"Agnes Axelsson, Gabriel Skantze","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-14T12:45:03Z","title":"Using Large Language Models for Zero-Shot Natural Language Generation from Knowledge Graphs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07312","kind":"arxiv","version":2},"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":"sha256:30eda81c01373692258ce555c4b4d74d6d1d5ef6174e6ccb52e52f081fc864b2","target":"record","created_at":"2026-07-05T06:43:24Z","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":"5a80fe93a169804c33c7dfb99ef98bcf950612bc08dbd396aa81779215906bc5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-14T12:45:03Z","title_canon_sha256":"fa8eaa1428afe0ad1fd23bf6d06623c819f6381b6b7cfb19d7b24ddf4b0e5bc5"},"schema_version":"1.0","source":{"id":"2307.07312","kind":"arxiv","version":2}},"canonical_sha256":"75de3c4be83472deec7fbc3b75dc3efd827f9ff5a71202f1fdcdbe3643cbfc46","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75de3c4be83472deec7fbc3b75dc3efd827f9ff5a71202f1fdcdbe3643cbfc46","first_computed_at":"2026-07-05T06:43:24.215750Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:43:24.215750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/nzCoYMBtYG4ZOM9+bY0/pNNw7buz+GHJ7evw9f1R6UoSIsspJi2yzf6ekBevlJTeGBl/ZIGMKiiRMTM7akhBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:43:24.216219Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.07312","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30eda81c01373692258ce555c4b4d74d6d1d5ef6174e6ccb52e52f081fc864b2","sha256:cb7367d4e6ef9ff996e790fae68b642003ecd19384d6dd502cd7728d1b36a41f"],"state_sha256":"60e83f233c58a1c6b6a774459a543a4af45a0af2f771a8f15a32f45015416a8c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IvSRU+HfF2FGaxi7faOHI/rIYl3bjuQGAZwLvjxA/YS4jcmbWzfLjxpEERixCHL8MaJc8rqkRZuT608UKdX8AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T06:37:06.012877Z","bundle_sha256":"164b0372ef4c50c50f90602e56962cbb3215d5a341e3cc99c9d622c7f0b27cb1"}}