{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:OVDKRNZOITKXV5CVIR65KUJSCL","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":"d053577692ba57010ac29a092e91865a5a58ce161a1962ad9631573becd2bc9e","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-14T08:26:32Z","title_canon_sha256":"633a86fb2ae2a39320c81b810e54108a3cad67540972dc2225fda6b1b43e1242"},"schema_version":"1.0","source":{"id":"2210.07631","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.07631","created_at":"2026-07-05T05:06:39Z"},{"alias_kind":"arxiv_version","alias_value":"2210.07631v1","created_at":"2026-07-05T05:06:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.07631","created_at":"2026-07-05T05:06:39Z"},{"alias_kind":"pith_short_12","alias_value":"OVDKRNZOITKX","created_at":"2026-07-05T05:06:39Z"},{"alias_kind":"pith_short_16","alias_value":"OVDKRNZOITKXV5CV","created_at":"2026-07-05T05:06:39Z"},{"alias_kind":"pith_short_8","alias_value":"OVDKRNZO","created_at":"2026-07-05T05:06:39Z"}],"graph_snapshots":[{"event_id":"sha256:374dc259f1d39240ac2dde252a44c141202f68b57de1a052dad48641983728dc","target":"graph","created_at":"2026-07-05T05:06:39Z","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/2210.07631/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluation of models on benchmarks is unreliable without knowing the degree of sample hardness; this subsequently overestimates the capability of AI systems and limits their adoption in real world applications. We propose a Data Scoring task that requires assignment of each unannotated sample in a benchmark a score between 0 to 1, where 0 signifies easy and 1 signifies hard. Use of unannotated samples in our task design is inspired from humans who can determine a question difficulty without knowing its correct answer. This also rules out the use of methods involving model based supervision (si","authors_text":"Anjana Arunkumar, Chitta Baral, Chris Bryan, Swaroop Mishra","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-14T08:26:32Z","title":"Hardness of Samples Need to be Quantified for a Reliable Evaluation System: Exploring Potential Opportunities with a New Task"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.07631","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":"sha256:06df8843c091dd173c29793fe0b3bd4936b5699559f744f9ae4e48fa8b31b957","target":"record","created_at":"2026-07-05T05:06:39Z","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":"d053577692ba57010ac29a092e91865a5a58ce161a1962ad9631573becd2bc9e","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-14T08:26:32Z","title_canon_sha256":"633a86fb2ae2a39320c81b810e54108a3cad67540972dc2225fda6b1b43e1242"},"schema_version":"1.0","source":{"id":"2210.07631","kind":"arxiv","version":1}},"canonical_sha256":"7546a8b72e44d57af455447dd5513212d5175b919ca284b17415e678abc383a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7546a8b72e44d57af455447dd5513212d5175b919ca284b17415e678abc383a1","first_computed_at":"2026-07-05T05:06:39.531131Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:06:39.531131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oZ9y/nUas0h6doyTFGlAQ7o3JSf+vkDHgdjdlyf1tkq9un46E1O2qLjSNCGwfXuzl9C5VA7hx+8xnJAlKzTUDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:06:39.531534Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.07631","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:06df8843c091dd173c29793fe0b3bd4936b5699559f744f9ae4e48fa8b31b957","sha256:374dc259f1d39240ac2dde252a44c141202f68b57de1a052dad48641983728dc"],"state_sha256":"8f9668eb22a9f4bf49cdffc2f287ddd1b735d3a53a1e885714779fcb7abbb3ed"}