{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:55Y7NJEJ424ZW5DX3OTOLU4PNV","short_pith_number":"pith:55Y7NJEJ","canonical_record":{"source":{"id":"2210.01734","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-04T16:54:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a4f854ddc4f830db1b8cd58c947cb521a8f267f61d682b4cad30980fc132d5b6","abstract_canon_sha256":"5864fcfe72f82c3799a5ffa8154a72f6f64b9ad56493dcef2887b1e9750411e8"},"schema_version":"1.0"},"canonical_sha256":"ef71f6a489e6b99b7477dba6e5d38f6d7521900befd48b888cfb36a6a57d37a9","source":{"kind":"arxiv","id":"2210.01734","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.01734","created_at":"2026-07-05T05:03:13Z"},{"alias_kind":"arxiv_version","alias_value":"2210.01734v1","created_at":"2026-07-05T05:03:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.01734","created_at":"2026-07-05T05:03:13Z"},{"alias_kind":"pith_short_12","alias_value":"55Y7NJEJ424Z","created_at":"2026-07-05T05:03:13Z"},{"alias_kind":"pith_short_16","alias_value":"55Y7NJEJ424ZW5DX","created_at":"2026-07-05T05:03:13Z"},{"alias_kind":"pith_short_8","alias_value":"55Y7NJEJ","created_at":"2026-07-05T05:03:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:55Y7NJEJ424ZW5DX3OTOLU4PNV","target":"record","payload":{"canonical_record":{"source":{"id":"2210.01734","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-04T16:54:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a4f854ddc4f830db1b8cd58c947cb521a8f267f61d682b4cad30980fc132d5b6","abstract_canon_sha256":"5864fcfe72f82c3799a5ffa8154a72f6f64b9ad56493dcef2887b1e9750411e8"},"schema_version":"1.0"},"canonical_sha256":"ef71f6a489e6b99b7477dba6e5d38f6d7521900befd48b888cfb36a6a57d37a9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:13.566136Z","signature_b64":"T110c4fgVo//fhGPwV8/Ri/pKKTsfsYKHtlwo4xI2eesW6ectvfqYK23HFJMyO4xaUYDF4MZaJFCghXTvynZCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef71f6a489e6b99b7477dba6e5d38f6d7521900befd48b888cfb36a6a57d37a9","last_reissued_at":"2026-07-05T05:03:13.565747Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:13.565747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.01734","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":"2026-07-05T05:03:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"20mExI4KllsYNNN1LX+9ZQeMsVl2hRr37XSAjWEMGU70Gn7Vs1mVzWPosOFHJgNNz3XKyK+GwRyiz/pVO3jWAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T05:38:49.267127Z"},"content_sha256":"e7b472c9982b3d3c1697e1d7450dcd52eb47b5bbde1cbba676f08a6b092be9ab","schema_version":"1.0","event_id":"sha256:e7b472c9982b3d3c1697e1d7450dcd52eb47b5bbde1cbba676f08a6b092be9ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:55Y7NJEJ424ZW5DX3OTOLU4PNV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text Characterization Toolkit","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Daniel Simig, Dieuwke Hupkes, Khuyagbaatar Batsuren, Mona Diab, Peter Henderson, Tianlu Wang, Verna Dankers","submitted_at":"2022-10-04T16:54:11Z","abstract_excerpt":"In NLP, models are usually evaluated by reporting single-number performance scores on a number of readily available benchmarks, without much deeper analysis. Here, we argue that - especially given the well-known fact that benchmarks often contain biases, artefacts, and spurious correlations - deeper results analysis should become the de-facto standard when presenting new models or benchmarks. We present a tool that researchers can use to study properties of the dataset and the influence of those properties on their models' behaviour. Our Text Characterization Toolkit includes both an easy-to-u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.01734","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/2210.01734/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":"2026-07-05T05:03:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xZz3w57sNwlOEE69DK0QGuqADNaQvq3530ZNsp+Hm8dZclzG0QQJdvcbCinngDwzg76r+mwoslN+rnZJT1V9DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T05:38:49.267734Z"},"content_sha256":"3ba6a457bc7a9c9ca864a3b533c0562b700c5ca350fef29a9799b7d2ab9090bf","schema_version":"1.0","event_id":"sha256:3ba6a457bc7a9c9ca864a3b533c0562b700c5ca350fef29a9799b7d2ab9090bf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/55Y7NJEJ424ZW5DX3OTOLU4PNV/bundle.json","state_url":"https://pith.science/pith/55Y7NJEJ424ZW5DX3OTOLU4PNV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/55Y7NJEJ424ZW5DX3OTOLU4PNV/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":"2026-08-01T05:38:49Z","links":{"resolver":"https://pith.science/pith/55Y7NJEJ424ZW5DX3OTOLU4PNV","bundle":"https://pith.science/pith/55Y7NJEJ424ZW5DX3OTOLU4PNV/bundle.json","state":"https://pith.science/pith/55Y7NJEJ424ZW5DX3OTOLU4PNV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/55Y7NJEJ424ZW5DX3OTOLU4PNV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:55Y7NJEJ424ZW5DX3OTOLU4PNV","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":"5864fcfe72f82c3799a5ffa8154a72f6f64b9ad56493dcef2887b1e9750411e8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-04T16:54:11Z","title_canon_sha256":"a4f854ddc4f830db1b8cd58c947cb521a8f267f61d682b4cad30980fc132d5b6"},"schema_version":"1.0","source":{"id":"2210.01734","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.01734","created_at":"2026-07-05T05:03:13Z"},{"alias_kind":"arxiv_version","alias_value":"2210.01734v1","created_at":"2026-07-05T05:03:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.01734","created_at":"2026-07-05T05:03:13Z"},{"alias_kind":"pith_short_12","alias_value":"55Y7NJEJ424Z","created_at":"2026-07-05T05:03:13Z"},{"alias_kind":"pith_short_16","alias_value":"55Y7NJEJ424ZW5DX","created_at":"2026-07-05T05:03:13Z"},{"alias_kind":"pith_short_8","alias_value":"55Y7NJEJ","created_at":"2026-07-05T05:03:13Z"}],"graph_snapshots":[{"event_id":"sha256:3ba6a457bc7a9c9ca864a3b533c0562b700c5ca350fef29a9799b7d2ab9090bf","target":"graph","created_at":"2026-07-05T05:03:13Z","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/2210.01734/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In NLP, models are usually evaluated by reporting single-number performance scores on a number of readily available benchmarks, without much deeper analysis. Here, we argue that - especially given the well-known fact that benchmarks often contain biases, artefacts, and spurious correlations - deeper results analysis should become the de-facto standard when presenting new models or benchmarks. We present a tool that researchers can use to study properties of the dataset and the influence of those properties on their models' behaviour. Our Text Characterization Toolkit includes both an easy-to-u","authors_text":"Daniel Simig, Dieuwke Hupkes, Khuyagbaatar Batsuren, Mona Diab, Peter Henderson, Tianlu Wang, Verna Dankers","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-04T16:54:11Z","title":"Text Characterization Toolkit"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.01734","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:e7b472c9982b3d3c1697e1d7450dcd52eb47b5bbde1cbba676f08a6b092be9ab","target":"record","created_at":"2026-07-05T05:03:13Z","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":"5864fcfe72f82c3799a5ffa8154a72f6f64b9ad56493dcef2887b1e9750411e8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-04T16:54:11Z","title_canon_sha256":"a4f854ddc4f830db1b8cd58c947cb521a8f267f61d682b4cad30980fc132d5b6"},"schema_version":"1.0","source":{"id":"2210.01734","kind":"arxiv","version":1}},"canonical_sha256":"ef71f6a489e6b99b7477dba6e5d38f6d7521900befd48b888cfb36a6a57d37a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef71f6a489e6b99b7477dba6e5d38f6d7521900befd48b888cfb36a6a57d37a9","first_computed_at":"2026-07-05T05:03:13.565747Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:03:13.565747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T110c4fgVo//fhGPwV8/Ri/pKKTsfsYKHtlwo4xI2eesW6ectvfqYK23HFJMyO4xaUYDF4MZaJFCghXTvynZCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:03:13.566136Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.01734","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7b472c9982b3d3c1697e1d7450dcd52eb47b5bbde1cbba676f08a6b092be9ab","sha256:3ba6a457bc7a9c9ca864a3b533c0562b700c5ca350fef29a9799b7d2ab9090bf"],"state_sha256":"f26cc89c3e437961446d6cf444786e52ecde5f4d53411be358250cf86db01812"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lz4M3PJZkOSx8ehewOEnRohdXA9w15TB2bXah8NZWo7AMRaTTS8f3vr/BcQacLrEtTO8grtojGRZ8SrtMtbQCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T05:38:49.279089Z","bundle_sha256":"486aa8881ecacfecd9af73d2168c7e24ea75372f625c090fd221022fab51aaf2"}}