{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:653U335LE7TIJLNAH5URS73ARJ","short_pith_number":"pith:653U335L","canonical_record":{"source":{"id":"2009.12452","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-25T22:06:06Z","cross_cats_sorted":[],"title_canon_sha256":"c40fe01c51edd80b1d0c2807da7d8d9bb91c75465532526bfe77fa6f2e45e6e6","abstract_canon_sha256":"6b517420079d8671faf6940ff4251254e9f90bd746883d2fe28c5c089fef13ef"},"schema_version":"1.0"},"canonical_sha256":"f7774defab27e684ada03f69197f608a51d51388ac3116412e556c40dee1a809","source":{"kind":"arxiv","id":"2009.12452","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.12452","created_at":"2026-07-05T01:38:05Z"},{"alias_kind":"arxiv_version","alias_value":"2009.12452v1","created_at":"2026-07-05T01:38:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.12452","created_at":"2026-07-05T01:38:05Z"},{"alias_kind":"pith_short_12","alias_value":"653U335LE7TI","created_at":"2026-07-05T01:38:05Z"},{"alias_kind":"pith_short_16","alias_value":"653U335LE7TIJLNA","created_at":"2026-07-05T01:38:05Z"},{"alias_kind":"pith_short_8","alias_value":"653U335L","created_at":"2026-07-05T01:38:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:653U335LE7TIJLNAH5URS73ARJ","target":"record","payload":{"canonical_record":{"source":{"id":"2009.12452","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-25T22:06:06Z","cross_cats_sorted":[],"title_canon_sha256":"c40fe01c51edd80b1d0c2807da7d8d9bb91c75465532526bfe77fa6f2e45e6e6","abstract_canon_sha256":"6b517420079d8671faf6940ff4251254e9f90bd746883d2fe28c5c089fef13ef"},"schema_version":"1.0"},"canonical_sha256":"f7774defab27e684ada03f69197f608a51d51388ac3116412e556c40dee1a809","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:38:05.058018Z","signature_b64":"GccFIA9h/zlzrfRxWk+xwLFG6eTDilZC79j59KKCik23uZEMm7jW8UsU1cqJVG9k7m9rxhTIfae3s/SOGrZXDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7774defab27e684ada03f69197f608a51d51388ac3116412e556c40dee1a809","last_reissued_at":"2026-07-05T01:38:05.057652Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:38:05.057652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.12452","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":"2026-07-05T01:38:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aPvIq1nm6/JpnbxFG3cTyinp3PwzYcm+bR6TGX0iJ444Mp5VeewG8oEW3K+ftMPzgMu55TeD+ho6uetROhVCBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:20:30.902851Z"},"content_sha256":"f98e7b0201d55493cf43b1167957aab85874fb650835f18e2cf54f60738a8f38","schema_version":"1.0","event_id":"sha256:f98e7b0201d55493cf43b1167957aab85874fb650835f18e2cf54f60738a8f38"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:653U335LE7TIJLNAH5URS73ARJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BET: A Backtranslation Approach for Easy Data Augmentation in Transformer-based Paraphrase Identification Context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hadi Abdi Ghadivel, Jean-Philippe Corbeil","submitted_at":"2020-09-25T22:06:06Z","abstract_excerpt":"Newly-introduced deep learning architectures, namely BERT, XLNet, RoBERTa and ALBERT, have been proved to be robust on several NLP tasks. However, the datasets trained on these architectures are fixed in terms of size and generalizability. To relieve this issue, we apply one of the most inexpensive solutions to update these datasets. We call this approach BET by which we analyze the backtranslation data augmentation on the transformer-based architectures. Using the Google Translate API with ten intermediary languages from ten different language families, we externally evaluate the results in t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.12452","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/2009.12452/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":"2026-07-05T01:38:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QowOS73EwM6aJ7AIw6O9wFwglKoM2pRlmjmd6ShUXMypzmEfouoF8uuiyHJTJADJDrMBJOcmTMfRFbYbT0iHDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:20:30.903333Z"},"content_sha256":"0d010311fb11410b77975b8a2b7e71926405fc0eaecec68b7437d0d795e77404","schema_version":"1.0","event_id":"sha256:0d010311fb11410b77975b8a2b7e71926405fc0eaecec68b7437d0d795e77404"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/653U335LE7TIJLNAH5URS73ARJ/bundle.json","state_url":"https://pith.science/pith/653U335LE7TIJLNAH5URS73ARJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/653U335LE7TIJLNAH5URS73ARJ/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":"2026-08-08T16:20:30Z","links":{"resolver":"https://pith.science/pith/653U335LE7TIJLNAH5URS73ARJ","bundle":"https://pith.science/pith/653U335LE7TIJLNAH5URS73ARJ/bundle.json","state":"https://pith.science/pith/653U335LE7TIJLNAH5URS73ARJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/653U335LE7TIJLNAH5URS73ARJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:653U335LE7TIJLNAH5URS73ARJ","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":"6b517420079d8671faf6940ff4251254e9f90bd746883d2fe28c5c089fef13ef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-25T22:06:06Z","title_canon_sha256":"c40fe01c51edd80b1d0c2807da7d8d9bb91c75465532526bfe77fa6f2e45e6e6"},"schema_version":"1.0","source":{"id":"2009.12452","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.12452","created_at":"2026-07-05T01:38:05Z"},{"alias_kind":"arxiv_version","alias_value":"2009.12452v1","created_at":"2026-07-05T01:38:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.12452","created_at":"2026-07-05T01:38:05Z"},{"alias_kind":"pith_short_12","alias_value":"653U335LE7TI","created_at":"2026-07-05T01:38:05Z"},{"alias_kind":"pith_short_16","alias_value":"653U335LE7TIJLNA","created_at":"2026-07-05T01:38:05Z"},{"alias_kind":"pith_short_8","alias_value":"653U335L","created_at":"2026-07-05T01:38:05Z"}],"graph_snapshots":[{"event_id":"sha256:0d010311fb11410b77975b8a2b7e71926405fc0eaecec68b7437d0d795e77404","target":"graph","created_at":"2026-07-05T01:38:05Z","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/2009.12452/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Newly-introduced deep learning architectures, namely BERT, XLNet, RoBERTa and ALBERT, have been proved to be robust on several NLP tasks. However, the datasets trained on these architectures are fixed in terms of size and generalizability. To relieve this issue, we apply one of the most inexpensive solutions to update these datasets. We call this approach BET by which we analyze the backtranslation data augmentation on the transformer-based architectures. Using the Google Translate API with ten intermediary languages from ten different language families, we externally evaluate the results in t","authors_text":"Hadi Abdi Ghadivel, Jean-Philippe Corbeil","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-25T22:06:06Z","title":"BET: A Backtranslation Approach for Easy Data Augmentation in Transformer-based Paraphrase Identification Context"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.12452","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:f98e7b0201d55493cf43b1167957aab85874fb650835f18e2cf54f60738a8f38","target":"record","created_at":"2026-07-05T01:38:05Z","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":"6b517420079d8671faf6940ff4251254e9f90bd746883d2fe28c5c089fef13ef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-25T22:06:06Z","title_canon_sha256":"c40fe01c51edd80b1d0c2807da7d8d9bb91c75465532526bfe77fa6f2e45e6e6"},"schema_version":"1.0","source":{"id":"2009.12452","kind":"arxiv","version":1}},"canonical_sha256":"f7774defab27e684ada03f69197f608a51d51388ac3116412e556c40dee1a809","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7774defab27e684ada03f69197f608a51d51388ac3116412e556c40dee1a809","first_computed_at":"2026-07-05T01:38:05.057652Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:38:05.057652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GccFIA9h/zlzrfRxWk+xwLFG6eTDilZC79j59KKCik23uZEMm7jW8UsU1cqJVG9k7m9rxhTIfae3s/SOGrZXDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:38:05.058018Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.12452","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f98e7b0201d55493cf43b1167957aab85874fb650835f18e2cf54f60738a8f38","sha256:0d010311fb11410b77975b8a2b7e71926405fc0eaecec68b7437d0d795e77404"],"state_sha256":"6707c4e18d4d7063c218cb8a0e3b51f938ac58a77d21a30bb16c3757ae53127f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jKthHA5+LLH3C1IgnNCqnWnPdpyMz2G1tpTpeqSNK5nUCwMi+VmtBRWMCV18eXOdN+MtI2S/Oz5A5RTByvCeBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:20:30.906865Z","bundle_sha256":"7921b3791c8008a5de91eb6d4fa66219aba37cbed38f914242c69916dc57e21a"}}