{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:U56H2C2MWNDCNGLUZ4EEHXVDED","short_pith_number":"pith:U56H2C2M","canonical_record":{"source":{"id":"2309.08638","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-14T17:45:51Z","cross_cats_sorted":[],"title_canon_sha256":"09b59c981e23ba376eea83cb961b0543eb98ffcec4d0cea265c6af5c4b6c8eb6","abstract_canon_sha256":"5e5bae534aadd1ca8ed012253dcadf1e0f4d2e77024961efa5bff84d54336bf5"},"schema_version":"1.0"},"canonical_sha256":"a77c7d0b4cb346269974cf0843dea320fdd81680341f9d3636eea664b7e97bfd","source":{"kind":"arxiv","id":"2309.08638","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.08638","created_at":"2026-07-05T07:46:22Z"},{"alias_kind":"arxiv_version","alias_value":"2309.08638v2","created_at":"2026-07-05T07:46:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08638","created_at":"2026-07-05T07:46:22Z"},{"alias_kind":"pith_short_12","alias_value":"U56H2C2MWNDC","created_at":"2026-07-05T07:46:22Z"},{"alias_kind":"pith_short_16","alias_value":"U56H2C2MWNDCNGLU","created_at":"2026-07-05T07:46:22Z"},{"alias_kind":"pith_short_8","alias_value":"U56H2C2M","created_at":"2026-07-05T07:46:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:U56H2C2MWNDCNGLUZ4EEHXVDED","target":"record","payload":{"canonical_record":{"source":{"id":"2309.08638","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-14T17:45:51Z","cross_cats_sorted":[],"title_canon_sha256":"09b59c981e23ba376eea83cb961b0543eb98ffcec4d0cea265c6af5c4b6c8eb6","abstract_canon_sha256":"5e5bae534aadd1ca8ed012253dcadf1e0f4d2e77024961efa5bff84d54336bf5"},"schema_version":"1.0"},"canonical_sha256":"a77c7d0b4cb346269974cf0843dea320fdd81680341f9d3636eea664b7e97bfd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:22.685677Z","signature_b64":"Wf8hVqBz1cH4RGcTkNQic1EQbrYxGkKQQMp6101wg4yKSUos7fOY5ZPE28ds7LKVR4X9cWtpJr+3e5PifXLoBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a77c7d0b4cb346269974cf0843dea320fdd81680341f9d3636eea664b7e97bfd","last_reissued_at":"2026-07-05T07:46:22.685148Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:22.685148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.08638","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:46:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zy6Os1KbcnZvoFye8k2tE5jCESfstdtVyQyh45KLlyilaLZcHhGzmBxeLbkmdHVS1Ehh1FXpLqYXzQxPJFeWBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:21:40.958288Z"},"content_sha256":"5c8b04a6c1156216188ac86672e39f1f285c883269cf5f1cf89df3cf57fffd71","schema_version":"1.0","event_id":"sha256:5c8b04a6c1156216188ac86672e39f1f285c883269cf5f1cf89df3cf57fffd71"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:U56H2C2MWNDCNGLUZ4EEHXVDED","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Anchor Points: Benchmarking Models with Much Fewer Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Diyi Yang, Douwe Kiela, Kawin Ethayarajh, Rajan Vivek","submitted_at":"2023-09-14T17:45:51Z","abstract_excerpt":"Modern language models often exhibit powerful but brittle behavior, leading to the development of larger and more diverse benchmarks to reliably assess their behavior. Here, we suggest that model performance can be benchmarked and elucidated with much smaller evaluation sets. We first show that in six popular language classification benchmarks, model confidence in the correct class on many pairs of points is strongly correlated across models. We build upon this phenomenon to propose Anchor Point Selection, a technique to select small subsets of datasets that capture model behavior across the e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08638","kind":"arxiv","version":2},"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/2309.08638/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":"2026-07-05T07:46:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"olnkOm348taU1KAIKTGgkJL81GtsqhhA8ok4F/vVKQtBcKDlzaLGxRsBNca4hlac1/pN6bS6ps7vxsQlfLRGCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:21:40.958874Z"},"content_sha256":"9ed3f41b58994d1d8305f89b85355629be4cd7de7678fa63345b23819789b229","schema_version":"1.0","event_id":"sha256:9ed3f41b58994d1d8305f89b85355629be4cd7de7678fa63345b23819789b229"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U56H2C2MWNDCNGLUZ4EEHXVDED/bundle.json","state_url":"https://pith.science/pith/U56H2C2MWNDCNGLUZ4EEHXVDED/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U56H2C2MWNDCNGLUZ4EEHXVDED/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":"2026-08-08T19:21:40Z","links":{"resolver":"https://pith.science/pith/U56H2C2MWNDCNGLUZ4EEHXVDED","bundle":"https://pith.science/pith/U56H2C2MWNDCNGLUZ4EEHXVDED/bundle.json","state":"https://pith.science/pith/U56H2C2MWNDCNGLUZ4EEHXVDED/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U56H2C2MWNDCNGLUZ4EEHXVDED/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:U56H2C2MWNDCNGLUZ4EEHXVDED","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":"5e5bae534aadd1ca8ed012253dcadf1e0f4d2e77024961efa5bff84d54336bf5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-14T17:45:51Z","title_canon_sha256":"09b59c981e23ba376eea83cb961b0543eb98ffcec4d0cea265c6af5c4b6c8eb6"},"schema_version":"1.0","source":{"id":"2309.08638","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.08638","created_at":"2026-07-05T07:46:22Z"},{"alias_kind":"arxiv_version","alias_value":"2309.08638v2","created_at":"2026-07-05T07:46:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08638","created_at":"2026-07-05T07:46:22Z"},{"alias_kind":"pith_short_12","alias_value":"U56H2C2MWNDC","created_at":"2026-07-05T07:46:22Z"},{"alias_kind":"pith_short_16","alias_value":"U56H2C2MWNDCNGLU","created_at":"2026-07-05T07:46:22Z"},{"alias_kind":"pith_short_8","alias_value":"U56H2C2M","created_at":"2026-07-05T07:46:22Z"}],"graph_snapshots":[{"event_id":"sha256:9ed3f41b58994d1d8305f89b85355629be4cd7de7678fa63345b23819789b229","target":"graph","created_at":"2026-07-05T07:46:22Z","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/2309.08638/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern language models often exhibit powerful but brittle behavior, leading to the development of larger and more diverse benchmarks to reliably assess their behavior. Here, we suggest that model performance can be benchmarked and elucidated with much smaller evaluation sets. We first show that in six popular language classification benchmarks, model confidence in the correct class on many pairs of points is strongly correlated across models. We build upon this phenomenon to propose Anchor Point Selection, a technique to select small subsets of datasets that capture model behavior across the e","authors_text":"Diyi Yang, Douwe Kiela, Kawin Ethayarajh, Rajan Vivek","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-14T17:45:51Z","title":"Anchor Points: Benchmarking Models with Much Fewer Examples"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08638","kind":"arxiv","version":2},"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":"sha256:5c8b04a6c1156216188ac86672e39f1f285c883269cf5f1cf89df3cf57fffd71","target":"record","created_at":"2026-07-05T07:46:22Z","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":"5e5bae534aadd1ca8ed012253dcadf1e0f4d2e77024961efa5bff84d54336bf5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-14T17:45:51Z","title_canon_sha256":"09b59c981e23ba376eea83cb961b0543eb98ffcec4d0cea265c6af5c4b6c8eb6"},"schema_version":"1.0","source":{"id":"2309.08638","kind":"arxiv","version":2}},"canonical_sha256":"a77c7d0b4cb346269974cf0843dea320fdd81680341f9d3636eea664b7e97bfd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a77c7d0b4cb346269974cf0843dea320fdd81680341f9d3636eea664b7e97bfd","first_computed_at":"2026-07-05T07:46:22.685148Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:46:22.685148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Wf8hVqBz1cH4RGcTkNQic1EQbrYxGkKQQMp6101wg4yKSUos7fOY5ZPE28ds7LKVR4X9cWtpJr+3e5PifXLoBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:46:22.685677Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.08638","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c8b04a6c1156216188ac86672e39f1f285c883269cf5f1cf89df3cf57fffd71","sha256:9ed3f41b58994d1d8305f89b85355629be4cd7de7678fa63345b23819789b229"],"state_sha256":"95beeeeedcf07db78cb5abad4395817bf2832f3f2f073d850dcd2eb4df978c45"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YXwto5R9sjnAA2BlF9ZhUdbQpc1rnycfiK05CigIBRicgs+4uKZP0KDgudVSZXu8tEzCp8uB4g32pAmxhic+Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:21:40.962616Z","bundle_sha256":"30532d576808b34a9edeae1a00a23840c46bb679dd7648f2ddd146534bc8a7b4"}}