{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OVDKRNZOITKXV5CVIR65KUJSCL","short_pith_number":"pith:OVDKRNZO","schema_version":"1.0","canonical_sha256":"7546a8b72e44d57af455447dd5513212d5175b919ca284b17415e678abc383a1","source":{"kind":"arxiv","id":"2210.07631","version":1},"attestation_state":"computed","paper":{"title":"Hardness of Samples Need to be Quantified for a Reliable Evaluation System: Exploring Potential Opportunities with a New Task","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Anjana Arunkumar, Chitta Baral, Chris Bryan, Swaroop Mishra","submitted_at":"2022-10-14T08:26:32Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2210.07631","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-14T08:26:32Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"633a86fb2ae2a39320c81b810e54108a3cad67540972dc2225fda6b1b43e1242","abstract_canon_sha256":"d053577692ba57010ac29a092e91865a5a58ce161a1962ad9631573becd2bc9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:39.531534Z","signature_b64":"oZ9y/nUas0h6doyTFGlAQ7o3JSf+vkDHgdjdlyf1tkq9un46E1O2qLjSNCGwfXuzl9C5VA7hx+8xnJAlKzTUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7546a8b72e44d57af455447dd5513212d5175b919ca284b17415e678abc383a1","last_reissued_at":"2026-07-05T05:06:39.531131Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:39.531131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hardness of Samples Need to be Quantified for a Reliable Evaluation System: Exploring Potential Opportunities with a New Task","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Anjana Arunkumar, Chitta Baral, Chris Bryan, Swaroop Mishra","submitted_at":"2022-10-14T08:26:32Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.07631","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/2210.07631/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2210.07631","created_at":"2026-07-05T05:06:39.531193+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.07631v1","created_at":"2026-07-05T05:06:39.531193+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.07631","created_at":"2026-07-05T05:06:39.531193+00:00"},{"alias_kind":"pith_short_12","alias_value":"OVDKRNZOITKX","created_at":"2026-07-05T05:06:39.531193+00:00"},{"alias_kind":"pith_short_16","alias_value":"OVDKRNZOITKXV5CV","created_at":"2026-07-05T05:06:39.531193+00:00"},{"alias_kind":"pith_short_8","alias_value":"OVDKRNZO","created_at":"2026-07-05T05:06:39.531193+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.12844","citing_title":"AGI-Elo: How Far Are We From Mastering A Task?","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OVDKRNZOITKXV5CVIR65KUJSCL","json":"https://pith.science/pith/OVDKRNZOITKXV5CVIR65KUJSCL.json","graph_json":"https://pith.science/api/pith-number/OVDKRNZOITKXV5CVIR65KUJSCL/graph.json","events_json":"https://pith.science/api/pith-number/OVDKRNZOITKXV5CVIR65KUJSCL/events.json","paper":"https://pith.science/paper/OVDKRNZO"},"agent_actions":{"view_html":"https://pith.science/pith/OVDKRNZOITKXV5CVIR65KUJSCL","download_json":"https://pith.science/pith/OVDKRNZOITKXV5CVIR65KUJSCL.json","view_paper":"https://pith.science/paper/OVDKRNZO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.07631&json=true","fetch_graph":"https://pith.science/api/pith-number/OVDKRNZOITKXV5CVIR65KUJSCL/graph.json","fetch_events":"https://pith.science/api/pith-number/OVDKRNZOITKXV5CVIR65KUJSCL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OVDKRNZOITKXV5CVIR65KUJSCL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OVDKRNZOITKXV5CVIR65KUJSCL/action/storage_attestation","attest_author":"https://pith.science/pith/OVDKRNZOITKXV5CVIR65KUJSCL/action/author_attestation","sign_citation":"https://pith.science/pith/OVDKRNZOITKXV5CVIR65KUJSCL/action/citation_signature","submit_replication":"https://pith.science/pith/OVDKRNZOITKXV5CVIR65KUJSCL/action/replication_record"}},"created_at":"2026-07-05T05:06:39.531193+00:00","updated_at":"2026-07-05T05:06:39.531193+00:00"}