{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:FIVRQXXVV2CDRI4QLIOX6CTLL7","short_pith_number":"pith:FIVRQXXV","canonical_record":{"source":{"id":"2106.02208","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-04T02:13:59Z","cross_cats_sorted":[],"title_canon_sha256":"12221bf63e02c863999fbd4d638627262270dc9b5deeff39cc052ef2baab564d","abstract_canon_sha256":"9e4687c7960fab006610cd447c04a3540459176243234de6e1f495404ab717a4"},"schema_version":"1.0"},"canonical_sha256":"2a2b185ef5ae8438a3905a1d7f0a6b5feb74345b590b2841070a6c86185b044d","source":{"kind":"arxiv","id":"2106.02208","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.02208","created_at":"2026-07-05T02:46:16Z"},{"alias_kind":"arxiv_version","alias_value":"2106.02208v1","created_at":"2026-07-05T02:46:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.02208","created_at":"2026-07-05T02:46:16Z"},{"alias_kind":"pith_short_12","alias_value":"FIVRQXXVV2CD","created_at":"2026-07-05T02:46:16Z"},{"alias_kind":"pith_short_16","alias_value":"FIVRQXXVV2CDRI4Q","created_at":"2026-07-05T02:46:16Z"},{"alias_kind":"pith_short_8","alias_value":"FIVRQXXV","created_at":"2026-07-05T02:46:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:FIVRQXXVV2CDRI4QLIOX6CTLL7","target":"record","payload":{"canonical_record":{"source":{"id":"2106.02208","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-04T02:13:59Z","cross_cats_sorted":[],"title_canon_sha256":"12221bf63e02c863999fbd4d638627262270dc9b5deeff39cc052ef2baab564d","abstract_canon_sha256":"9e4687c7960fab006610cd447c04a3540459176243234de6e1f495404ab717a4"},"schema_version":"1.0"},"canonical_sha256":"2a2b185ef5ae8438a3905a1d7f0a6b5feb74345b590b2841070a6c86185b044d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:16.689913Z","signature_b64":"j4K2LfGpG54WB6VvMY52/vx3H0SaiTyDobizaq9SlHqYEqUFwE3gSKuZPibtirKGNf+G8RKr4dwSfON8/lFtCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a2b185ef5ae8438a3905a1d7f0a6b5feb74345b590b2841070a6c86185b044d","last_reissued_at":"2026-07-05T02:46:16.689446Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:16.689446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.02208","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":"2026-07-05T02:46:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SjUxgYIG/m+xBlP+ZuWK+6rpIC2H21i4CHVPlDvLh28YqsggtPNjeD2OTcIIqoKMwFlCDm36QS7p4RXnZzL8Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:45:28.386023Z"},"content_sha256":"3e3dac20bd482407db82c1908dc2fae7f24eb12f0b9c526bdf6f51e3cf2c0c1c","schema_version":"1.0","event_id":"sha256:3e3dac20bd482407db82c1908dc2fae7f24eb12f0b9c526bdf6f51e3cf2c0c1c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:FIVRQXXVV2CDRI4QLIOX6CTLL7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BERTTune: Fine-Tuning Neural Machine Translation with BERTScore","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Inigo Jauregi Unanue, Jacob Parnell, Massimo Piccardi","submitted_at":"2021-06-04T02:13:59Z","abstract_excerpt":"Neural machine translation models are often biased toward the limited translation references seen during training. To amend this form of overfitting, in this paper we propose fine-tuning the models with a novel training objective based on the recently-proposed BERTScore evaluation metric. BERTScore is a scoring function based on contextual embeddings that overcomes the typical limitations of n-gram-based metrics (e.g. synonyms, paraphrases), allowing translations that are different from the references, yet close in the contextual embedding space, to be treated as substantially correct. To be a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.02208","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/2106.02208/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":"2026-07-05T02:46:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vywxS3OTc+qPa2zOC6g+ZTuF1iR8IrNq9wVZChkV/fCC3XcGx7v16GmKf4nR0JgZcf8bK4tNQSp03wOu/dbnDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:45:28.386536Z"},"content_sha256":"0e98fd3a40fe041b7cae832ad9233a367e233bbee0808bc7ebba62015277a34c","schema_version":"1.0","event_id":"sha256:0e98fd3a40fe041b7cae832ad9233a367e233bbee0808bc7ebba62015277a34c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FIVRQXXVV2CDRI4QLIOX6CTLL7/bundle.json","state_url":"https://pith.science/pith/FIVRQXXVV2CDRI4QLIOX6CTLL7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FIVRQXXVV2CDRI4QLIOX6CTLL7/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":"2026-08-08T02:45:28Z","links":{"resolver":"https://pith.science/pith/FIVRQXXVV2CDRI4QLIOX6CTLL7","bundle":"https://pith.science/pith/FIVRQXXVV2CDRI4QLIOX6CTLL7/bundle.json","state":"https://pith.science/pith/FIVRQXXVV2CDRI4QLIOX6CTLL7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FIVRQXXVV2CDRI4QLIOX6CTLL7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FIVRQXXVV2CDRI4QLIOX6CTLL7","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":"9e4687c7960fab006610cd447c04a3540459176243234de6e1f495404ab717a4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-04T02:13:59Z","title_canon_sha256":"12221bf63e02c863999fbd4d638627262270dc9b5deeff39cc052ef2baab564d"},"schema_version":"1.0","source":{"id":"2106.02208","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.02208","created_at":"2026-07-05T02:46:16Z"},{"alias_kind":"arxiv_version","alias_value":"2106.02208v1","created_at":"2026-07-05T02:46:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.02208","created_at":"2026-07-05T02:46:16Z"},{"alias_kind":"pith_short_12","alias_value":"FIVRQXXVV2CD","created_at":"2026-07-05T02:46:16Z"},{"alias_kind":"pith_short_16","alias_value":"FIVRQXXVV2CDRI4Q","created_at":"2026-07-05T02:46:16Z"},{"alias_kind":"pith_short_8","alias_value":"FIVRQXXV","created_at":"2026-07-05T02:46:16Z"}],"graph_snapshots":[{"event_id":"sha256:0e98fd3a40fe041b7cae832ad9233a367e233bbee0808bc7ebba62015277a34c","target":"graph","created_at":"2026-07-05T02:46:16Z","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/2106.02208/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural machine translation models are often biased toward the limited translation references seen during training. To amend this form of overfitting, in this paper we propose fine-tuning the models with a novel training objective based on the recently-proposed BERTScore evaluation metric. BERTScore is a scoring function based on contextual embeddings that overcomes the typical limitations of n-gram-based metrics (e.g. synonyms, paraphrases), allowing translations that are different from the references, yet close in the contextual embedding space, to be treated as substantially correct. To be a","authors_text":"Inigo Jauregi Unanue, Jacob Parnell, Massimo Piccardi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-04T02:13:59Z","title":"BERTTune: Fine-Tuning Neural Machine Translation with BERTScore"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.02208","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":"sha256:3e3dac20bd482407db82c1908dc2fae7f24eb12f0b9c526bdf6f51e3cf2c0c1c","target":"record","created_at":"2026-07-05T02:46:16Z","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":"9e4687c7960fab006610cd447c04a3540459176243234de6e1f495404ab717a4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-04T02:13:59Z","title_canon_sha256":"12221bf63e02c863999fbd4d638627262270dc9b5deeff39cc052ef2baab564d"},"schema_version":"1.0","source":{"id":"2106.02208","kind":"arxiv","version":1}},"canonical_sha256":"2a2b185ef5ae8438a3905a1d7f0a6b5feb74345b590b2841070a6c86185b044d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a2b185ef5ae8438a3905a1d7f0a6b5feb74345b590b2841070a6c86185b044d","first_computed_at":"2026-07-05T02:46:16.689446Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:46:16.689446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j4K2LfGpG54WB6VvMY52/vx3H0SaiTyDobizaq9SlHqYEqUFwE3gSKuZPibtirKGNf+G8RKr4dwSfON8/lFtCg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:46:16.689913Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.02208","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e3dac20bd482407db82c1908dc2fae7f24eb12f0b9c526bdf6f51e3cf2c0c1c","sha256:0e98fd3a40fe041b7cae832ad9233a367e233bbee0808bc7ebba62015277a34c"],"state_sha256":"377e8c80ce870334013604dd5dd3a159dcc72a5f72948f688085b16958cbf785"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K04lQU0ftGWCmI7Sa9DAtYskEFvsWD18Fkw7qXhtjY7xye50k60wLqFwWMcqQ+l5FedVgHEZ/P4wE3ulc1Z4Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T02:45:28.396167Z","bundle_sha256":"6b99fbb352411da6e4cab56cbb80310fc2b88911b1dd9f08aad7bd4c743e372c"}}