{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:EOS7PJAKNMQ2UIWMVGTUPI7CHF","short_pith_number":"pith:EOS7PJAK","canonical_record":{"source":{"id":"1907.12461","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-29T14:42:30Z","cross_cats_sorted":[],"title_canon_sha256":"ff6f5dbc34a42a7836f34b04d8ac93cad5feb15925266bbc547c6582100b5393","abstract_canon_sha256":"d059e8f12eddeac035d514ba980ae6e51fbc1c00da190de8a676f1177edc5134"},"schema_version":"1.0"},"canonical_sha256":"23a5f7a40a6b21aa22cca9a747a3e23951764c0c2e45be8bb47611d57b91ece2","source":{"kind":"arxiv","id":"1907.12461","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.12461","created_at":"2026-07-05T04:46:50Z"},{"alias_kind":"arxiv_version","alias_value":"1907.12461v2","created_at":"2026-07-05T04:46:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.12461","created_at":"2026-07-05T04:46:50Z"},{"alias_kind":"pith_short_12","alias_value":"EOS7PJAKNMQ2","created_at":"2026-07-05T04:46:50Z"},{"alias_kind":"pith_short_16","alias_value":"EOS7PJAKNMQ2UIWM","created_at":"2026-07-05T04:46:50Z"},{"alias_kind":"pith_short_8","alias_value":"EOS7PJAK","created_at":"2026-07-05T04:46:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:EOS7PJAKNMQ2UIWMVGTUPI7CHF","target":"record","payload":{"canonical_record":{"source":{"id":"1907.12461","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-29T14:42:30Z","cross_cats_sorted":[],"title_canon_sha256":"ff6f5dbc34a42a7836f34b04d8ac93cad5feb15925266bbc547c6582100b5393","abstract_canon_sha256":"d059e8f12eddeac035d514ba980ae6e51fbc1c00da190de8a676f1177edc5134"},"schema_version":"1.0"},"canonical_sha256":"23a5f7a40a6b21aa22cca9a747a3e23951764c0c2e45be8bb47611d57b91ece2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:46:50.115912Z","signature_b64":"suyYYXpvMrbCax9mOVPA174PYh4+GF4DYMCfzBDZm3sBDPwiwr9L8sM9imPASgHwmOjhPV3uvITdHoL+j0YJBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23a5f7a40a6b21aa22cca9a747a3e23951764c0c2e45be8bb47611d57b91ece2","last_reissued_at":"2026-07-05T04:46:50.115551Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:46:50.115551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.12461","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":"2026-07-05T04:46:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YIz5GTa5Eyo2IViwVEkPY7lgBtHETUtuV6H6+pdK4GCVgLGC2EaakNcX4+BBAUpllC7Sop3yW6zJVHkZPuDsCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T15:16:49.814080Z"},"content_sha256":"0edef39a3273d51d8850d60ee30bd4308c7c7f590bdb89df8b0a171702a747ef","schema_version":"1.0","event_id":"sha256:0edef39a3273d51d8850d60ee30bd4308c7c7f590bdb89df8b0a171702a747ef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:EOS7PJAKNMQ2UIWMVGTUPI7CHF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Pre-trained Checkpoints for Sequence Generation Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aliaksei Severyn, Sascha Rothe, Shashi Narayan","submitted_at":"2019-07-29T14:42:30Z","abstract_excerpt":"Unsupervised pre-training of large neural models has recently revolutionized Natural Language Processing. By warm-starting from the publicly released checkpoints, NLP practitioners have pushed the state-of-the-art on multiple benchmarks while saving significant amounts of compute time. So far the focus has been mainly on the Natural Language Understanding tasks. In this paper, we demonstrate the efficacy of pre-trained checkpoints for Sequence Generation. We developed a Transformer-based sequence-to-sequence model that is compatible with publicly available pre-trained BERT, GPT-2 and RoBERTa c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.12461","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/1907.12461/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":"2026-07-05T04:46:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b0bFLYRuzaIvPtjj+69rVQqzFl2EaMbhI4JAqDX8kknrOq0TIH/lCBL0n/cckEsEC8mQeqkPCHUY12e6kDufAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T15:16:49.814411Z"},"content_sha256":"73fa2224f3aa2fa64eb7217240f13e25453deb3f60f52440ca648e9e30bb1374","schema_version":"1.0","event_id":"sha256:73fa2224f3aa2fa64eb7217240f13e25453deb3f60f52440ca648e9e30bb1374"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EOS7PJAKNMQ2UIWMVGTUPI7CHF/bundle.json","state_url":"https://pith.science/pith/EOS7PJAKNMQ2UIWMVGTUPI7CHF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EOS7PJAKNMQ2UIWMVGTUPI7CHF/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":"2026-07-31T15:16:49Z","links":{"resolver":"https://pith.science/pith/EOS7PJAKNMQ2UIWMVGTUPI7CHF","bundle":"https://pith.science/pith/EOS7PJAKNMQ2UIWMVGTUPI7CHF/bundle.json","state":"https://pith.science/pith/EOS7PJAKNMQ2UIWMVGTUPI7CHF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EOS7PJAKNMQ2UIWMVGTUPI7CHF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:EOS7PJAKNMQ2UIWMVGTUPI7CHF","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":"d059e8f12eddeac035d514ba980ae6e51fbc1c00da190de8a676f1177edc5134","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-29T14:42:30Z","title_canon_sha256":"ff6f5dbc34a42a7836f34b04d8ac93cad5feb15925266bbc547c6582100b5393"},"schema_version":"1.0","source":{"id":"1907.12461","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.12461","created_at":"2026-07-05T04:46:50Z"},{"alias_kind":"arxiv_version","alias_value":"1907.12461v2","created_at":"2026-07-05T04:46:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.12461","created_at":"2026-07-05T04:46:50Z"},{"alias_kind":"pith_short_12","alias_value":"EOS7PJAKNMQ2","created_at":"2026-07-05T04:46:50Z"},{"alias_kind":"pith_short_16","alias_value":"EOS7PJAKNMQ2UIWM","created_at":"2026-07-05T04:46:50Z"},{"alias_kind":"pith_short_8","alias_value":"EOS7PJAK","created_at":"2026-07-05T04:46:50Z"}],"graph_snapshots":[{"event_id":"sha256:73fa2224f3aa2fa64eb7217240f13e25453deb3f60f52440ca648e9e30bb1374","target":"graph","created_at":"2026-07-05T04:46:50Z","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/1907.12461/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unsupervised pre-training of large neural models has recently revolutionized Natural Language Processing. By warm-starting from the publicly released checkpoints, NLP practitioners have pushed the state-of-the-art on multiple benchmarks while saving significant amounts of compute time. So far the focus has been mainly on the Natural Language Understanding tasks. In this paper, we demonstrate the efficacy of pre-trained checkpoints for Sequence Generation. We developed a Transformer-based sequence-to-sequence model that is compatible with publicly available pre-trained BERT, GPT-2 and RoBERTa c","authors_text":"Aliaksei Severyn, Sascha Rothe, Shashi Narayan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-29T14:42:30Z","title":"Leveraging Pre-trained Checkpoints for Sequence Generation Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.12461","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":"sha256:0edef39a3273d51d8850d60ee30bd4308c7c7f590bdb89df8b0a171702a747ef","target":"record","created_at":"2026-07-05T04:46:50Z","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":"d059e8f12eddeac035d514ba980ae6e51fbc1c00da190de8a676f1177edc5134","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-29T14:42:30Z","title_canon_sha256":"ff6f5dbc34a42a7836f34b04d8ac93cad5feb15925266bbc547c6582100b5393"},"schema_version":"1.0","source":{"id":"1907.12461","kind":"arxiv","version":2}},"canonical_sha256":"23a5f7a40a6b21aa22cca9a747a3e23951764c0c2e45be8bb47611d57b91ece2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23a5f7a40a6b21aa22cca9a747a3e23951764c0c2e45be8bb47611d57b91ece2","first_computed_at":"2026-07-05T04:46:50.115551Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:46:50.115551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"suyYYXpvMrbCax9mOVPA174PYh4+GF4DYMCfzBDZm3sBDPwiwr9L8sM9imPASgHwmOjhPV3uvITdHoL+j0YJBw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:46:50.115912Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.12461","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0edef39a3273d51d8850d60ee30bd4308c7c7f590bdb89df8b0a171702a747ef","sha256:73fa2224f3aa2fa64eb7217240f13e25453deb3f60f52440ca648e9e30bb1374"],"state_sha256":"c6456e664899c420e119029ad3c7e77a5a4c63a124c2a6c694c2801a25dd326a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BRf1dW4L446UC+ubl9sZLlsg67monVto0SBRis8SiUP6NstX+LrW21L8NA3/4RSJg/BlOOPlS653iTGqMYRmCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T15:16:49.817469Z","bundle_sha256":"9da42b28ed072eb0d848d8351ca4d7149792f344ef274e09edffd29d88b89efd"}}