{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7WOHODA7X536P6KCJSB4ZO65V6","short_pith_number":"pith:7WOHODA7","canonical_record":{"source":{"id":"2406.08723","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T00:59:55Z","cross_cats_sorted":[],"title_canon_sha256":"e6caeb02401b3f2de3a35ad503460c5ce711cc3a8298dc1b102482fe7dce9a43","abstract_canon_sha256":"4da76a29463b1203971d2c22b45a8c5455f4aacfb5abad7abf05f9b9ff98450d"},"schema_version":"1.0"},"canonical_sha256":"fd9c770c1fbf77e7f9424c83ccbbddafb73308b6352cc259ad22ce3acfe30f93","source":{"kind":"arxiv","id":"2406.08723","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08723","created_at":"2026-07-05T08:31:22Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08723v1","created_at":"2026-07-05T08:31:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08723","created_at":"2026-07-05T08:31:22Z"},{"alias_kind":"pith_short_12","alias_value":"7WOHODA7X536","created_at":"2026-07-05T08:31:22Z"},{"alias_kind":"pith_short_16","alias_value":"7WOHODA7X536P6KC","created_at":"2026-07-05T08:31:22Z"},{"alias_kind":"pith_short_8","alias_value":"7WOHODA7","created_at":"2026-07-05T08:31:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7WOHODA7X536P6KCJSB4ZO65V6","target":"record","payload":{"canonical_record":{"source":{"id":"2406.08723","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T00:59:55Z","cross_cats_sorted":[],"title_canon_sha256":"e6caeb02401b3f2de3a35ad503460c5ce711cc3a8298dc1b102482fe7dce9a43","abstract_canon_sha256":"4da76a29463b1203971d2c22b45a8c5455f4aacfb5abad7abf05f9b9ff98450d"},"schema_version":"1.0"},"canonical_sha256":"fd9c770c1fbf77e7f9424c83ccbbddafb73308b6352cc259ad22ce3acfe30f93","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:22.188938Z","signature_b64":"9bj/EOkQpGa3N6tmXGKAMdtUW+zzbNqwJHuUdZvpI3V8rDmr1r6h5UTG/URvTQ5Vnu+qnSvyVZwp7zH6Q8COAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd9c770c1fbf77e7f9424c83ccbbddafb73308b6352cc259ad22ce3acfe30f93","last_reissued_at":"2026-07-05T08:31:22.188467Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:22.188467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.08723","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":"2026-07-05T08:31:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PrlvBJ9cpiBxqLsFXNaX3XKngJp1p4yWoW7gMjheimImeN6Oc08TKuNWxcADEdu0k6i9j2JwoWFXe8nXab9wBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T07:05:20.801084Z"},"content_sha256":"d5fa577b5e99e6835fc8346aad3db012f97b9e1bf8ee34323c5cd111510cd589","schema_version":"1.0","event_id":"sha256:d5fa577b5e99e6835fc8346aad3db012f97b9e1bf8ee34323c5cd111510cd589"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7WOHODA7X536P6KCJSB4ZO65V6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ECBD: Evidence-Centered Benchmark Design for NLP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandra Olteanu, Jackie Chi Kit Cheung, Q. Vera Liao, Su Lin Blodgett, Yu Lu Liu, Ziang Xiao","submitted_at":"2024-06-13T00:59:55Z","abstract_excerpt":"Benchmarking is seen as critical to assessing progress in NLP. However, creating a benchmark involves many design decisions (e.g., which datasets to include, which metrics to use) that often rely on tacit, untested assumptions about what the benchmark is intended to measure or is actually measuring. There is currently no principled way of analyzing these decisions and how they impact the validity of the benchmark's measurements. To address this gap, we draw on evidence-centered design in educational assessments and propose Evidence-Centered Benchmark Design (ECBD), a framework which formalizes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08723","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/2406.08723/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":"2026-07-05T08:31:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Tgv4zCbUCFU09jhOQHKHvZIkLmC7OncU2QVe7uwtFEv9rgLAkAgo99tvwmUr3RPRIsfbyO/9FjV3ez8jSRdBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T07:05:20.801633Z"},"content_sha256":"575d3ff46e3a49628f0fe01ea8799c084567d999b0c7d924df9f01446afa36be","schema_version":"1.0","event_id":"sha256:575d3ff46e3a49628f0fe01ea8799c084567d999b0c7d924df9f01446afa36be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7WOHODA7X536P6KCJSB4ZO65V6/bundle.json","state_url":"https://pith.science/pith/7WOHODA7X536P6KCJSB4ZO65V6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7WOHODA7X536P6KCJSB4ZO65V6/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":"2026-08-14T07:05:20Z","links":{"resolver":"https://pith.science/pith/7WOHODA7X536P6KCJSB4ZO65V6","bundle":"https://pith.science/pith/7WOHODA7X536P6KCJSB4ZO65V6/bundle.json","state":"https://pith.science/pith/7WOHODA7X536P6KCJSB4ZO65V6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7WOHODA7X536P6KCJSB4ZO65V6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7WOHODA7X536P6KCJSB4ZO65V6","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":"4da76a29463b1203971d2c22b45a8c5455f4aacfb5abad7abf05f9b9ff98450d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T00:59:55Z","title_canon_sha256":"e6caeb02401b3f2de3a35ad503460c5ce711cc3a8298dc1b102482fe7dce9a43"},"schema_version":"1.0","source":{"id":"2406.08723","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08723","created_at":"2026-07-05T08:31:22Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08723v1","created_at":"2026-07-05T08:31:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08723","created_at":"2026-07-05T08:31:22Z"},{"alias_kind":"pith_short_12","alias_value":"7WOHODA7X536","created_at":"2026-07-05T08:31:22Z"},{"alias_kind":"pith_short_16","alias_value":"7WOHODA7X536P6KC","created_at":"2026-07-05T08:31:22Z"},{"alias_kind":"pith_short_8","alias_value":"7WOHODA7","created_at":"2026-07-05T08:31:22Z"}],"graph_snapshots":[{"event_id":"sha256:575d3ff46e3a49628f0fe01ea8799c084567d999b0c7d924df9f01446afa36be","target":"graph","created_at":"2026-07-05T08:31:22Z","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/2406.08723/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Benchmarking is seen as critical to assessing progress in NLP. However, creating a benchmark involves many design decisions (e.g., which datasets to include, which metrics to use) that often rely on tacit, untested assumptions about what the benchmark is intended to measure or is actually measuring. There is currently no principled way of analyzing these decisions and how they impact the validity of the benchmark's measurements. To address this gap, we draw on evidence-centered design in educational assessments and propose Evidence-Centered Benchmark Design (ECBD), a framework which formalizes","authors_text":"Alexandra Olteanu, Jackie Chi Kit Cheung, Q. Vera Liao, Su Lin Blodgett, Yu Lu Liu, Ziang Xiao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T00:59:55Z","title":"ECBD: Evidence-Centered Benchmark Design for NLP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08723","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:d5fa577b5e99e6835fc8346aad3db012f97b9e1bf8ee34323c5cd111510cd589","target":"record","created_at":"2026-07-05T08:31:22Z","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":"4da76a29463b1203971d2c22b45a8c5455f4aacfb5abad7abf05f9b9ff98450d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-13T00:59:55Z","title_canon_sha256":"e6caeb02401b3f2de3a35ad503460c5ce711cc3a8298dc1b102482fe7dce9a43"},"schema_version":"1.0","source":{"id":"2406.08723","kind":"arxiv","version":1}},"canonical_sha256":"fd9c770c1fbf77e7f9424c83ccbbddafb73308b6352cc259ad22ce3acfe30f93","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd9c770c1fbf77e7f9424c83ccbbddafb73308b6352cc259ad22ce3acfe30f93","first_computed_at":"2026-07-05T08:31:22.188467Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:31:22.188467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9bj/EOkQpGa3N6tmXGKAMdtUW+zzbNqwJHuUdZvpI3V8rDmr1r6h5UTG/URvTQ5Vnu+qnSvyVZwp7zH6Q8COAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:31:22.188938Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.08723","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5fa577b5e99e6835fc8346aad3db012f97b9e1bf8ee34323c5cd111510cd589","sha256:575d3ff46e3a49628f0fe01ea8799c084567d999b0c7d924df9f01446afa36be"],"state_sha256":"83dfb54fc9e49e989d2b5d4f9adf4378b92c4c6c1de315274979195aa2fb8247"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6U6KLnMPrELUX1BmB96ZenlmAEfaS2628xwIQgeeFeXP2b7kiSFn0FjckW3608wRGJ+fZI1oluLzRa+n+JkmBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T07:05:20.806934Z","bundle_sha256":"6a7321f9cc1f7c9cb86e8077ab73fedc5f74e56d4247afcd451c7872bb50e1ff"}}