{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:NJ57ZBQA5Z5XXBB5DWXCB7Y5E4","short_pith_number":"pith:NJ57ZBQA","canonical_record":{"source":{"id":"2305.17127","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T17:50:51Z","cross_cats_sorted":[],"title_canon_sha256":"45a908a026c036db8bd18b48f84ac76ea0fee0bc7855177f0105b3df0ec2f398","abstract_canon_sha256":"3f0b708ed9985ebcf6d2eb4344489b739bd901a9513b8a943fd5918878ed8299"},"schema_version":"1.0"},"canonical_sha256":"6a7bfc8600ee7b7b843d1dae20ff1d272f54a16e86c0ecf8f719292e5a467080","source":{"kind":"arxiv","id":"2305.17127","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17127","created_at":"2026-07-05T06:14:21Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17127v1","created_at":"2026-07-05T06:14:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17127","created_at":"2026-07-05T06:14:21Z"},{"alias_kind":"pith_short_12","alias_value":"NJ57ZBQA5Z5X","created_at":"2026-07-05T06:14:21Z"},{"alias_kind":"pith_short_16","alias_value":"NJ57ZBQA5Z5XXBB5","created_at":"2026-07-05T06:14:21Z"},{"alias_kind":"pith_short_8","alias_value":"NJ57ZBQA","created_at":"2026-07-05T06:14:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:NJ57ZBQA5Z5XXBB5DWXCB7Y5E4","target":"record","payload":{"canonical_record":{"source":{"id":"2305.17127","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T17:50:51Z","cross_cats_sorted":[],"title_canon_sha256":"45a908a026c036db8bd18b48f84ac76ea0fee0bc7855177f0105b3df0ec2f398","abstract_canon_sha256":"3f0b708ed9985ebcf6d2eb4344489b739bd901a9513b8a943fd5918878ed8299"},"schema_version":"1.0"},"canonical_sha256":"6a7bfc8600ee7b7b843d1dae20ff1d272f54a16e86c0ecf8f719292e5a467080","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:21.481593Z","signature_b64":"y8LFM/ixaTSnEZNUNTXAP7gyKAwqzhiXCvyIko945xI+TE25xxdgmB1b0IOQNAUboPW5c3T8hI9Y3N1BrUbJCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a7bfc8600ee7b7b843d1dae20ff1d272f54a16e86c0ecf8f719292e5a467080","last_reissued_at":"2026-07-05T06:14:21.481125Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:21.481125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.17127","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":"2026-07-05T06:14:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xt6PvhzeNZBUxim2tcp5NkmJY/bHLn/4Lf9j82Kg9o0dFDUUbr2fa7pRsEmKkPksfiINWdKVZykJp0RXA8uoCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T08:20:21.266061Z"},"content_sha256":"7b3cb0cd6fea2db3ff23f828e30d6c2f18869e73a163d9d38cd314c81eb9d275","schema_version":"1.0","event_id":"sha256:7b3cb0cd6fea2db3ff23f828e30d6c2f18869e73a163d9d38cd314c81eb9d275"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:NJ57ZBQA5Z5XXBB5DWXCB7Y5E4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Characterizing and Measuring Linguistic Dataset Drift","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Roth, Kishaloy Halder, Miguel Ballesteros, Neha Anna John, Tyler A. Chang, Yassine Benajiba, Yogarshi Vyas","submitted_at":"2023-05-26T17:50:51Z","abstract_excerpt":"NLP models often degrade in performance when real world data distributions differ markedly from training data. However, existing dataset drift metrics in NLP have generally not considered specific dimensions of linguistic drift that affect model performance, and they have not been validated in their ability to predict model performance at the individual example level, where such metrics are often used in practice. In this paper, we propose three dimensions of linguistic dataset drift: vocabulary, structural, and semantic drift. These dimensions correspond to content word frequency divergences,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17127","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/2305.17127/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":"2026-07-05T06:14:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xHVe9s/OMecwNa+PPP7dxQHdNSw6m3jCUYmUMSjFgW2k78Kyy20eGrnQXe3Ob9iF0ouWCdVzDe1D07jP8qOtCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T08:20:21.267036Z"},"content_sha256":"fc68ee08e5a7353f16ebdbaa0c041c63070dcade809df35d007b670da4eab854","schema_version":"1.0","event_id":"sha256:fc68ee08e5a7353f16ebdbaa0c041c63070dcade809df35d007b670da4eab854"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NJ57ZBQA5Z5XXBB5DWXCB7Y5E4/bundle.json","state_url":"https://pith.science/pith/NJ57ZBQA5Z5XXBB5DWXCB7Y5E4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NJ57ZBQA5Z5XXBB5DWXCB7Y5E4/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":"2026-08-19T08:20:21Z","links":{"resolver":"https://pith.science/pith/NJ57ZBQA5Z5XXBB5DWXCB7Y5E4","bundle":"https://pith.science/pith/NJ57ZBQA5Z5XXBB5DWXCB7Y5E4/bundle.json","state":"https://pith.science/pith/NJ57ZBQA5Z5XXBB5DWXCB7Y5E4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NJ57ZBQA5Z5XXBB5DWXCB7Y5E4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NJ57ZBQA5Z5XXBB5DWXCB7Y5E4","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":"3f0b708ed9985ebcf6d2eb4344489b739bd901a9513b8a943fd5918878ed8299","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T17:50:51Z","title_canon_sha256":"45a908a026c036db8bd18b48f84ac76ea0fee0bc7855177f0105b3df0ec2f398"},"schema_version":"1.0","source":{"id":"2305.17127","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17127","created_at":"2026-07-05T06:14:21Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17127v1","created_at":"2026-07-05T06:14:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17127","created_at":"2026-07-05T06:14:21Z"},{"alias_kind":"pith_short_12","alias_value":"NJ57ZBQA5Z5X","created_at":"2026-07-05T06:14:21Z"},{"alias_kind":"pith_short_16","alias_value":"NJ57ZBQA5Z5XXBB5","created_at":"2026-07-05T06:14:21Z"},{"alias_kind":"pith_short_8","alias_value":"NJ57ZBQA","created_at":"2026-07-05T06:14:21Z"}],"graph_snapshots":[{"event_id":"sha256:fc68ee08e5a7353f16ebdbaa0c041c63070dcade809df35d007b670da4eab854","target":"graph","created_at":"2026-07-05T06:14:21Z","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/2305.17127/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"NLP models often degrade in performance when real world data distributions differ markedly from training data. However, existing dataset drift metrics in NLP have generally not considered specific dimensions of linguistic drift that affect model performance, and they have not been validated in their ability to predict model performance at the individual example level, where such metrics are often used in practice. In this paper, we propose three dimensions of linguistic dataset drift: vocabulary, structural, and semantic drift. These dimensions correspond to content word frequency divergences,","authors_text":"Dan Roth, Kishaloy Halder, Miguel Ballesteros, Neha Anna John, Tyler A. Chang, Yassine Benajiba, Yogarshi Vyas","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T17:50:51Z","title":"Characterizing and Measuring Linguistic Dataset Drift"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17127","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":"sha256:7b3cb0cd6fea2db3ff23f828e30d6c2f18869e73a163d9d38cd314c81eb9d275","target":"record","created_at":"2026-07-05T06:14:21Z","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":"3f0b708ed9985ebcf6d2eb4344489b739bd901a9513b8a943fd5918878ed8299","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T17:50:51Z","title_canon_sha256":"45a908a026c036db8bd18b48f84ac76ea0fee0bc7855177f0105b3df0ec2f398"},"schema_version":"1.0","source":{"id":"2305.17127","kind":"arxiv","version":1}},"canonical_sha256":"6a7bfc8600ee7b7b843d1dae20ff1d272f54a16e86c0ecf8f719292e5a467080","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a7bfc8600ee7b7b843d1dae20ff1d272f54a16e86c0ecf8f719292e5a467080","first_computed_at":"2026-07-05T06:14:21.481125Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:21.481125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y8LFM/ixaTSnEZNUNTXAP7gyKAwqzhiXCvyIko945xI+TE25xxdgmB1b0IOQNAUboPW5c3T8hI9Y3N1BrUbJCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:21.481593Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.17127","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7b3cb0cd6fea2db3ff23f828e30d6c2f18869e73a163d9d38cd314c81eb9d275","sha256:fc68ee08e5a7353f16ebdbaa0c041c63070dcade809df35d007b670da4eab854"],"state_sha256":"07060ee1b82eedbd9c4b71dc9f795a6b0ea39ebc4397d0826db1564e73c942cf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KbXXtmtGxXw3EKp80FkrY03nMHigqm3r6qk+B97VVWVxgg0xH2FCEtPbpOO2LKgKjCaPol4aUurquCqMATLjBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T08:20:21.275149Z","bundle_sha256":"0ecad84edc6e2830ec1b4e00b6fab680ab1c5ed03bcf006c3792ac91e976048e"}}