{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:DZPNGNVLOJZAL4I3UWHZ5AN5NT","short_pith_number":"pith:DZPNGNVL","canonical_record":{"source":{"id":"2104.05700","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-12T17:57:42Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b0f80fe3180ac9026f2b1194f038298cdada79c9591b1dd5fb73de70fbdf91f6","abstract_canon_sha256":"a7f3140a78e6afcf78dc59aa53172af6baec9b113d1f4808b391443d6948a0b0"},"schema_version":"1.0"},"canonical_sha256":"1e5ed336ab727205f11ba58f9e81bd6ce8aa8d8d965077b4fc3b619b3f0b2794","source":{"kind":"arxiv","id":"2104.05700","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.05700","created_at":"2026-07-05T04:57:42Z"},{"alias_kind":"arxiv_version","alias_value":"2104.05700v1","created_at":"2026-07-05T04:57:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.05700","created_at":"2026-07-05T04:57:42Z"},{"alias_kind":"pith_short_12","alias_value":"DZPNGNVLOJZA","created_at":"2026-07-05T04:57:42Z"},{"alias_kind":"pith_short_16","alias_value":"DZPNGNVLOJZAL4I3","created_at":"2026-07-05T04:57:42Z"},{"alias_kind":"pith_short_8","alias_value":"DZPNGNVL","created_at":"2026-07-05T04:57:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:DZPNGNVLOJZAL4I3UWHZ5AN5NT","target":"record","payload":{"canonical_record":{"source":{"id":"2104.05700","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-12T17:57:42Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b0f80fe3180ac9026f2b1194f038298cdada79c9591b1dd5fb73de70fbdf91f6","abstract_canon_sha256":"a7f3140a78e6afcf78dc59aa53172af6baec9b113d1f4808b391443d6948a0b0"},"schema_version":"1.0"},"canonical_sha256":"1e5ed336ab727205f11ba58f9e81bd6ce8aa8d8d965077b4fc3b619b3f0b2794","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:57:42.165598Z","signature_b64":"h4g7HjMIAiSEbvNent7IHVpqex3WrwDxuJFM4OSaCz0rNH70GraJAJP4+B3mu5uxqnczSghkRW3at8yxUoe3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e5ed336ab727205f11ba58f9e81bd6ce8aa8d8d965077b4fc3b619b3f0b2794","last_reissued_at":"2026-07-05T04:57:42.165133Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:57:42.165133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.05700","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":"2026-07-05T04:57:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y81HrbU5EaVJVtstB0JTMf5Mv8c0VMkx7ZH/aEw7mqmD0TTFTpZRY7EfoqluAufLs89/3wBxrq15F3DXtQQPDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-28T10:52:23.506969Z"},"content_sha256":"43647b0a07040dea8f64f15631ebd58ae0f049cce8512c9fc90dd17f85f82dae","schema_version":"1.0","event_id":"sha256:43647b0a07040dea8f64f15631ebd58ae0f049cce8512c9fc90dd17f85f82dae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:DZPNGNVLOJZAL4I3UWHZ5AN5NT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Macro-Average: Rare Types Are Important Too","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Constantine Lignos, Jonathan May, Thamme Gowda, Weiqiu You","submitted_at":"2021-04-12T17:57:42Z","abstract_excerpt":"While traditional corpus-level evaluation metrics for machine translation (MT) correlate well with fluency, they struggle to reflect adequacy. Model-based MT metrics trained on segment-level human judgments have emerged as an attractive replacement due to strong correlation results. These models, however, require potentially expensive re-training for new domains and languages. Furthermore, their decisions are inherently non-transparent and appear to reflect unwelcome biases. We explore the simple type-based classifier metric, MacroF1, and study its applicability to MT evaluation. We find that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.05700","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/2104.05700/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":"2026-07-05T04:57:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VfrtrSMcSART8ofPg41gZrVwMX6BsbpQ9b9YuhGL/8+yFUm5Au9RTs9rS7lDU04Ty1oSsYRBghSY7A0TED6LDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-28T10:52:23.507362Z"},"content_sha256":"77ae96e9d351449e590d220fee040a0b9a3e10cd9d1aba5483f05ef5693b2edf","schema_version":"1.0","event_id":"sha256:77ae96e9d351449e590d220fee040a0b9a3e10cd9d1aba5483f05ef5693b2edf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DZPNGNVLOJZAL4I3UWHZ5AN5NT/bundle.json","state_url":"https://pith.science/pith/DZPNGNVLOJZAL4I3UWHZ5AN5NT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DZPNGNVLOJZAL4I3UWHZ5AN5NT/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":"2026-07-28T10:52:23Z","links":{"resolver":"https://pith.science/pith/DZPNGNVLOJZAL4I3UWHZ5AN5NT","bundle":"https://pith.science/pith/DZPNGNVLOJZAL4I3UWHZ5AN5NT/bundle.json","state":"https://pith.science/pith/DZPNGNVLOJZAL4I3UWHZ5AN5NT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DZPNGNVLOJZAL4I3UWHZ5AN5NT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:DZPNGNVLOJZAL4I3UWHZ5AN5NT","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":"a7f3140a78e6afcf78dc59aa53172af6baec9b113d1f4808b391443d6948a0b0","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-12T17:57:42Z","title_canon_sha256":"b0f80fe3180ac9026f2b1194f038298cdada79c9591b1dd5fb73de70fbdf91f6"},"schema_version":"1.0","source":{"id":"2104.05700","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.05700","created_at":"2026-07-05T04:57:42Z"},{"alias_kind":"arxiv_version","alias_value":"2104.05700v1","created_at":"2026-07-05T04:57:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.05700","created_at":"2026-07-05T04:57:42Z"},{"alias_kind":"pith_short_12","alias_value":"DZPNGNVLOJZA","created_at":"2026-07-05T04:57:42Z"},{"alias_kind":"pith_short_16","alias_value":"DZPNGNVLOJZAL4I3","created_at":"2026-07-05T04:57:42Z"},{"alias_kind":"pith_short_8","alias_value":"DZPNGNVL","created_at":"2026-07-05T04:57:42Z"}],"graph_snapshots":[{"event_id":"sha256:77ae96e9d351449e590d220fee040a0b9a3e10cd9d1aba5483f05ef5693b2edf","target":"graph","created_at":"2026-07-05T04:57:42Z","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/2104.05700/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While traditional corpus-level evaluation metrics for machine translation (MT) correlate well with fluency, they struggle to reflect adequacy. Model-based MT metrics trained on segment-level human judgments have emerged as an attractive replacement due to strong correlation results. These models, however, require potentially expensive re-training for new domains and languages. Furthermore, their decisions are inherently non-transparent and appear to reflect unwelcome biases. We explore the simple type-based classifier metric, MacroF1, and study its applicability to MT evaluation. We find that ","authors_text":"Constantine Lignos, Jonathan May, Thamme Gowda, Weiqiu You","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-12T17:57:42Z","title":"Macro-Average: Rare Types Are Important Too"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.05700","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":"sha256:43647b0a07040dea8f64f15631ebd58ae0f049cce8512c9fc90dd17f85f82dae","target":"record","created_at":"2026-07-05T04:57:42Z","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":"a7f3140a78e6afcf78dc59aa53172af6baec9b113d1f4808b391443d6948a0b0","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-12T17:57:42Z","title_canon_sha256":"b0f80fe3180ac9026f2b1194f038298cdada79c9591b1dd5fb73de70fbdf91f6"},"schema_version":"1.0","source":{"id":"2104.05700","kind":"arxiv","version":1}},"canonical_sha256":"1e5ed336ab727205f11ba58f9e81bd6ce8aa8d8d965077b4fc3b619b3f0b2794","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e5ed336ab727205f11ba58f9e81bd6ce8aa8d8d965077b4fc3b619b3f0b2794","first_computed_at":"2026-07-05T04:57:42.165133Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:57:42.165133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h4g7HjMIAiSEbvNent7IHVpqex3WrwDxuJFM4OSaCz0rNH70GraJAJP4+B3mu5uxqnczSghkRW3at8yxUoe3AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:57:42.165598Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.05700","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43647b0a07040dea8f64f15631ebd58ae0f049cce8512c9fc90dd17f85f82dae","sha256:77ae96e9d351449e590d220fee040a0b9a3e10cd9d1aba5483f05ef5693b2edf"],"state_sha256":"23c171d1e7d210af151e97d416e1b8ab680d4d13286687e7b57a409219a75a3d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5di77QMLBAUnsyajdgA2MwaMyA1xtrHq/Jv4s4SaXB3o44penUkrSjCR3LUzTen+iEZ1V22BMEEFvfVqNQQ/Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-28T10:52:23.509531Z","bundle_sha256":"c2d9949249da191bee35d3bed8f7488d5efe6985ead613cc6177140629b08027"}}