{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:3KE4T2S6PDTF7HYFHDTYL6I2IZ","short_pith_number":"pith:3KE4T2S6","canonical_record":{"source":{"id":"2012.00571","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-01T15:25:47Z","cross_cats_sorted":[],"title_canon_sha256":"29efb1e62e241351e08974bcc25d2f71e519b660876c6912ee5b00c85fa27d80","abstract_canon_sha256":"495cf577d339bc07ffc01076367f737ac7883751023bba620c9828ea3a5909ff"},"schema_version":"1.0"},"canonical_sha256":"da89c9ea5e78e65f9f0538e785f91a4668d404f134311cfa45890aad39396794","source":{"kind":"arxiv","id":"2012.00571","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.00571","created_at":"2026-07-05T01:56:17Z"},{"alias_kind":"arxiv_version","alias_value":"2012.00571v1","created_at":"2026-07-05T01:56:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.00571","created_at":"2026-07-05T01:56:17Z"},{"alias_kind":"pith_short_12","alias_value":"3KE4T2S6PDTF","created_at":"2026-07-05T01:56:17Z"},{"alias_kind":"pith_short_16","alias_value":"3KE4T2S6PDTF7HYF","created_at":"2026-07-05T01:56:17Z"},{"alias_kind":"pith_short_8","alias_value":"3KE4T2S6","created_at":"2026-07-05T01:56:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:3KE4T2S6PDTF7HYFHDTYL6I2IZ","target":"record","payload":{"canonical_record":{"source":{"id":"2012.00571","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-01T15:25:47Z","cross_cats_sorted":[],"title_canon_sha256":"29efb1e62e241351e08974bcc25d2f71e519b660876c6912ee5b00c85fa27d80","abstract_canon_sha256":"495cf577d339bc07ffc01076367f737ac7883751023bba620c9828ea3a5909ff"},"schema_version":"1.0"},"canonical_sha256":"da89c9ea5e78e65f9f0538e785f91a4668d404f134311cfa45890aad39396794","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:56:17.914914Z","signature_b64":"1vZ+tTgiwRTKZEgz/viustK4oylIuqQ2LoYRXCp9jqfiKL1Vdo6odFo2KN5Em6gfASJgQ1ntodknHsdzp1ZeDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da89c9ea5e78e65f9f0538e785f91a4668d404f134311cfa45890aad39396794","last_reissued_at":"2026-07-05T01:56:17.914451Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:56:17.914451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.00571","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":"2026-07-05T01:56:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vvLc4Deq8USK2HEOgZw/eL3xOOW5onMVN2a2N1MuBbpQmqbiJg7/fIQhYcWnkqxXxaJs2QLlds970wDlWbNBAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:26:33.486632Z"},"content_sha256":"3ce063adc9c18c58be4e7bbfbb6edb9742a6e89fb0be50a3b3ae83972fdae17d","schema_version":"1.0","event_id":"sha256:3ce063adc9c18c58be4e7bbfbb6edb9742a6e89fb0be50a3b3ae83972fdae17d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:3KE4T2S6PDTF7HYFHDTYL6I2IZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Denoising Pre-Training and Data Augmentation Strategies for Enhanced RDF Verbalization with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Betty Fabre, Johannes Heinecke, Lina Rojas-Barahona, Sebastien Montella, Tanguy Urvoy","submitted_at":"2020-12-01T15:25:47Z","abstract_excerpt":"The task of verbalization of RDF triples has known a growth in popularity due to the rising ubiquity of Knowledge Bases (KBs). The formalism of RDF triples is a simple and efficient way to store facts at a large scale. However, its abstract representation makes it difficult for humans to interpret. For this purpose, the WebNLG challenge aims at promoting automated RDF-to-text generation. We propose to leverage pre-trainings from augmented data with the Transformer model using a data augmentation strategy. Our experiment results show a minimum relative increases of 3.73%, 126.05% and 88.16% in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.00571","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/2012.00571/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":"2026-07-05T01:56:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QaMmKfSjEzbUA1jRS71xdz4sG4787Jw26I43jghL15zAp20KDOBuFWwUyINlanL327fwgLh/7ySeok5bwDP7Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:26:33.487001Z"},"content_sha256":"78259063e0985bbbf5ab17b8dc8709a75a30a5d5948629c0c693dd2f5dcdb479","schema_version":"1.0","event_id":"sha256:78259063e0985bbbf5ab17b8dc8709a75a30a5d5948629c0c693dd2f5dcdb479"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3KE4T2S6PDTF7HYFHDTYL6I2IZ/bundle.json","state_url":"https://pith.science/pith/3KE4T2S6PDTF7HYFHDTYL6I2IZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3KE4T2S6PDTF7HYFHDTYL6I2IZ/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":"2026-07-06T17:26:33Z","links":{"resolver":"https://pith.science/pith/3KE4T2S6PDTF7HYFHDTYL6I2IZ","bundle":"https://pith.science/pith/3KE4T2S6PDTF7HYFHDTYL6I2IZ/bundle.json","state":"https://pith.science/pith/3KE4T2S6PDTF7HYFHDTYL6I2IZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3KE4T2S6PDTF7HYFHDTYL6I2IZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:3KE4T2S6PDTF7HYFHDTYL6I2IZ","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":"495cf577d339bc07ffc01076367f737ac7883751023bba620c9828ea3a5909ff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-01T15:25:47Z","title_canon_sha256":"29efb1e62e241351e08974bcc25d2f71e519b660876c6912ee5b00c85fa27d80"},"schema_version":"1.0","source":{"id":"2012.00571","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.00571","created_at":"2026-07-05T01:56:17Z"},{"alias_kind":"arxiv_version","alias_value":"2012.00571v1","created_at":"2026-07-05T01:56:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.00571","created_at":"2026-07-05T01:56:17Z"},{"alias_kind":"pith_short_12","alias_value":"3KE4T2S6PDTF","created_at":"2026-07-05T01:56:17Z"},{"alias_kind":"pith_short_16","alias_value":"3KE4T2S6PDTF7HYF","created_at":"2026-07-05T01:56:17Z"},{"alias_kind":"pith_short_8","alias_value":"3KE4T2S6","created_at":"2026-07-05T01:56:17Z"}],"graph_snapshots":[{"event_id":"sha256:78259063e0985bbbf5ab17b8dc8709a75a30a5d5948629c0c693dd2f5dcdb479","target":"graph","created_at":"2026-07-05T01:56:17Z","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/2012.00571/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The task of verbalization of RDF triples has known a growth in popularity due to the rising ubiquity of Knowledge Bases (KBs). The formalism of RDF triples is a simple and efficient way to store facts at a large scale. However, its abstract representation makes it difficult for humans to interpret. For this purpose, the WebNLG challenge aims at promoting automated RDF-to-text generation. We propose to leverage pre-trainings from augmented data with the Transformer model using a data augmentation strategy. Our experiment results show a minimum relative increases of 3.73%, 126.05% and 88.16% in ","authors_text":"Betty Fabre, Johannes Heinecke, Lina Rojas-Barahona, Sebastien Montella, Tanguy Urvoy","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-01T15:25:47Z","title":"Denoising Pre-Training and Data Augmentation Strategies for Enhanced RDF Verbalization with Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.00571","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":"sha256:3ce063adc9c18c58be4e7bbfbb6edb9742a6e89fb0be50a3b3ae83972fdae17d","target":"record","created_at":"2026-07-05T01:56:17Z","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":"495cf577d339bc07ffc01076367f737ac7883751023bba620c9828ea3a5909ff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-01T15:25:47Z","title_canon_sha256":"29efb1e62e241351e08974bcc25d2f71e519b660876c6912ee5b00c85fa27d80"},"schema_version":"1.0","source":{"id":"2012.00571","kind":"arxiv","version":1}},"canonical_sha256":"da89c9ea5e78e65f9f0538e785f91a4668d404f134311cfa45890aad39396794","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da89c9ea5e78e65f9f0538e785f91a4668d404f134311cfa45890aad39396794","first_computed_at":"2026-07-05T01:56:17.914451Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:56:17.914451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1vZ+tTgiwRTKZEgz/viustK4oylIuqQ2LoYRXCp9jqfiKL1Vdo6odFo2KN5Em6gfASJgQ1ntodknHsdzp1ZeDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:56:17.914914Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.00571","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ce063adc9c18c58be4e7bbfbb6edb9742a6e89fb0be50a3b3ae83972fdae17d","sha256:78259063e0985bbbf5ab17b8dc8709a75a30a5d5948629c0c693dd2f5dcdb479"],"state_sha256":"1e9d1036c260fe8754336748ac4ade968e4d500641770175af81a59898a52582"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L1RcFA+1ulNQjYhyPqyjg7nyhWkfttVc1YR9uhPL6Hilpgi5uDyUqTAynXaD7iNWDLHu3tD/RHYTHb26oDEYAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T17:26:33.489033Z","bundle_sha256":"acd8e54917d38e3d7134323d6e0fbc587f50197cb76be6da90f7c05c02c05e55"}}