{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ADRRSR36OVLCA666FEQZJGXUDE","short_pith_number":"pith:ADRRSR36","canonical_record":{"source":{"id":"2305.11806","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-19T16:42:17Z","cross_cats_sorted":[],"title_canon_sha256":"75ad7f4fe9d2bc9f92d5f9fedd97f3b4e5ced75d2b288caecedd0f95f74e7dac","abstract_canon_sha256":"9970828890be0090142c8758c3ca09e2d13091f0b6b53de202e784b06023a59d"},"schema_version":"1.0"},"canonical_sha256":"00e319477e7556207bde2921949af419104bde285c648ca39b1e1db3af1a1f94","source":{"kind":"arxiv","id":"2305.11806","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.11806","created_at":"2026-07-05T06:11:51Z"},{"alias_kind":"arxiv_version","alias_value":"2305.11806v1","created_at":"2026-07-05T06:11:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11806","created_at":"2026-07-05T06:11:51Z"},{"alias_kind":"pith_short_12","alias_value":"ADRRSR36OVLC","created_at":"2026-07-05T06:11:51Z"},{"alias_kind":"pith_short_16","alias_value":"ADRRSR36OVLCA666","created_at":"2026-07-05T06:11:51Z"},{"alias_kind":"pith_short_8","alias_value":"ADRRSR36","created_at":"2026-07-05T06:11:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ADRRSR36OVLCA666FEQZJGXUDE","target":"record","payload":{"canonical_record":{"source":{"id":"2305.11806","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-19T16:42:17Z","cross_cats_sorted":[],"title_canon_sha256":"75ad7f4fe9d2bc9f92d5f9fedd97f3b4e5ced75d2b288caecedd0f95f74e7dac","abstract_canon_sha256":"9970828890be0090142c8758c3ca09e2d13091f0b6b53de202e784b06023a59d"},"schema_version":"1.0"},"canonical_sha256":"00e319477e7556207bde2921949af419104bde285c648ca39b1e1db3af1a1f94","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:51.377503Z","signature_b64":"TlMjCEB8IJ/1ujCq1Tr9WVzHQkwmyjrD6jwTthlkNn4ro4R0nSJphcAL1jELkOVJZIO+AdyQd0fGMDCbi/D1Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00e319477e7556207bde2921949af419104bde285c648ca39b1e1db3af1a1f94","last_reissued_at":"2026-07-05T06:11:51.377051Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:51.377051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.11806","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":"2026-07-05T06:11:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HPvtAgBvDMGCk1B17rgFv6ozdXvohjL1E+EFSLlAUHE9RJ1R0Sv6Ci65A+2vzcaNYfLgcQ/N6+usOvQanf5zDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:29:44.757757Z"},"content_sha256":"078f501ada453c72dee661da5863db13ae5b11639c435dfbd6fd5554c3b1982e","schema_version":"1.0","event_id":"sha256:078f501ada453c72dee661da5863db13ae5b11639c435dfbd6fd5554c3b1982e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ADRRSR36OVLCA666FEQZJGXUDE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Inside Story: Towards Better Understanding of Machine Translation Neural Evaluation Metrics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alon Lavie, Andr\\'e F.T. Martins, Luisa Coheur, Marcos Treviso, Nuno M. Guerreiro, Ricardo Rei","submitted_at":"2023-05-19T16:42:17Z","abstract_excerpt":"Neural metrics for machine translation evaluation, such as COMET, exhibit significant improvements in their correlation with human judgments, as compared to traditional metrics based on lexical overlap, such as BLEU. Yet, neural metrics are, to a great extent, \"black boxes\" returning a single sentence-level score without transparency about the decision-making process. In this work, we develop and compare several neural explainability methods and demonstrate their effectiveness for interpreting state-of-the-art fine-tuned neural metrics. Our study reveals that these metrics leverage token-level"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11806","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/2305.11806/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":"2026-07-05T06:11:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b92Xcj7WJnpidytdKYLkGGwD1VdPlHlnyrp6mWnUHcvfFCdhmoqyWqIQAjHkhcMNz6ss9feAxkOwUiM+XvhrDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:29:44.758126Z"},"content_sha256":"7e5b5eb11d5004a39a8d8caaeb2c2932218c107c9037b7915722b5f27c40e283","schema_version":"1.0","event_id":"sha256:7e5b5eb11d5004a39a8d8caaeb2c2932218c107c9037b7915722b5f27c40e283"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ADRRSR36OVLCA666FEQZJGXUDE/bundle.json","state_url":"https://pith.science/pith/ADRRSR36OVLCA666FEQZJGXUDE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ADRRSR36OVLCA666FEQZJGXUDE/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":"2026-07-07T12:29:44Z","links":{"resolver":"https://pith.science/pith/ADRRSR36OVLCA666FEQZJGXUDE","bundle":"https://pith.science/pith/ADRRSR36OVLCA666FEQZJGXUDE/bundle.json","state":"https://pith.science/pith/ADRRSR36OVLCA666FEQZJGXUDE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ADRRSR36OVLCA666FEQZJGXUDE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ADRRSR36OVLCA666FEQZJGXUDE","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":"9970828890be0090142c8758c3ca09e2d13091f0b6b53de202e784b06023a59d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-19T16:42:17Z","title_canon_sha256":"75ad7f4fe9d2bc9f92d5f9fedd97f3b4e5ced75d2b288caecedd0f95f74e7dac"},"schema_version":"1.0","source":{"id":"2305.11806","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.11806","created_at":"2026-07-05T06:11:51Z"},{"alias_kind":"arxiv_version","alias_value":"2305.11806v1","created_at":"2026-07-05T06:11:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11806","created_at":"2026-07-05T06:11:51Z"},{"alias_kind":"pith_short_12","alias_value":"ADRRSR36OVLC","created_at":"2026-07-05T06:11:51Z"},{"alias_kind":"pith_short_16","alias_value":"ADRRSR36OVLCA666","created_at":"2026-07-05T06:11:51Z"},{"alias_kind":"pith_short_8","alias_value":"ADRRSR36","created_at":"2026-07-05T06:11:51Z"}],"graph_snapshots":[{"event_id":"sha256:7e5b5eb11d5004a39a8d8caaeb2c2932218c107c9037b7915722b5f27c40e283","target":"graph","created_at":"2026-07-05T06:11:51Z","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/2305.11806/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural metrics for machine translation evaluation, such as COMET, exhibit significant improvements in their correlation with human judgments, as compared to traditional metrics based on lexical overlap, such as BLEU. Yet, neural metrics are, to a great extent, \"black boxes\" returning a single sentence-level score without transparency about the decision-making process. In this work, we develop and compare several neural explainability methods and demonstrate their effectiveness for interpreting state-of-the-art fine-tuned neural metrics. Our study reveals that these metrics leverage token-level","authors_text":"Alon Lavie, Andr\\'e F.T. Martins, Luisa Coheur, Marcos Treviso, Nuno M. Guerreiro, Ricardo Rei","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-19T16:42:17Z","title":"The Inside Story: Towards Better Understanding of Machine Translation Neural Evaluation Metrics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11806","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":"sha256:078f501ada453c72dee661da5863db13ae5b11639c435dfbd6fd5554c3b1982e","target":"record","created_at":"2026-07-05T06:11:51Z","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":"9970828890be0090142c8758c3ca09e2d13091f0b6b53de202e784b06023a59d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-19T16:42:17Z","title_canon_sha256":"75ad7f4fe9d2bc9f92d5f9fedd97f3b4e5ced75d2b288caecedd0f95f74e7dac"},"schema_version":"1.0","source":{"id":"2305.11806","kind":"arxiv","version":1}},"canonical_sha256":"00e319477e7556207bde2921949af419104bde285c648ca39b1e1db3af1a1f94","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00e319477e7556207bde2921949af419104bde285c648ca39b1e1db3af1a1f94","first_computed_at":"2026-07-05T06:11:51.377051Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:11:51.377051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TlMjCEB8IJ/1ujCq1Tr9WVzHQkwmyjrD6jwTthlkNn4ro4R0nSJphcAL1jELkOVJZIO+AdyQd0fGMDCbi/D1Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:11:51.377503Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.11806","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:078f501ada453c72dee661da5863db13ae5b11639c435dfbd6fd5554c3b1982e","sha256:7e5b5eb11d5004a39a8d8caaeb2c2932218c107c9037b7915722b5f27c40e283"],"state_sha256":"59023f6dd136a720785ca9b8fd2f79b747b93041357ed5c0b7fa17e289c6a062"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UYMfkIlgZOMWuI2DDgqcptpeBdM2dWIs0HH5lEChRKwnLSLqKCbZurZ0MrMb622+IWSGQ50Ns9CwSnP43B5WDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:29:44.760095Z","bundle_sha256":"31db4270e6310fb0c3892fdc1fe5423fbb6ef2d6dec979686219c36983bba472"}}