{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WQZ6GTIBOZEYPCQ7EABSJOLDRQ","short_pith_number":"pith:WQZ6GTIB","schema_version":"1.0","canonical_sha256":"b433e34d017649878a1f200324b9638c0fe4230eee1cb2c35ec246b9b08169a0","source":{"kind":"arxiv","id":"2603.04737","version":4},"attestation_state":"computed","paper":{"title":"Interactive Benchmarks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Interactive benchmarks using budgeted multi-turn interaction with objective feedback assess AI reasoning more robustly than fixed tests or preference judgments.","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Baoqing Yue, Brian Fan, Hufei Yang, Jichen Feng, Mengdi Wang, Qian Sun, Yifan Zhang, Yutong Han, Zihan Zhu","submitted_at":"2026-03-05T02:18:26Z","abstract_excerpt":"Existing reasoning evaluation paradigms suffer from different limitations: fixed benchmarks are increasingly saturated and vulnerable to contamination, while preference-based evaluations rely on subjective judgments. We argue that a core aspect of intelligence is the ability to decide what information to acquire and how to use it effectively. We propose Interactive Benchmarks, a unified evaluation paradigm that assesses a model's reasoning ability through budgeted multi-turn interaction. We evaluate models under this framework in two settings: Interactive Proofs, where models interact with a j"},"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":"2603.04737","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-03-05T02:18:26Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"19375cc5ad0fd20976fdc336fd90a3833c683d81ae6c67c68b0c67971f295ab8","abstract_canon_sha256":"0ee398b76bdb86d4f25b173f42d223f44710e1cc5bc18a3f88e8f313e07343e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:07.792265Z","signature_b64":"yE96nfI5kXVCoMW+DBW9gaP+NgMo4dvn+8BHEHu7PNU9wMOPDxFbamWrDPQKPrjgmt2swjFjFMFHZqRM5vLWAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b433e34d017649878a1f200324b9638c0fe4230eee1cb2c35ec246b9b08169a0","last_reissued_at":"2026-05-20T00:03:07.791472Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:07.791472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interactive Benchmarks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Interactive benchmarks using budgeted multi-turn interaction with objective feedback assess AI reasoning more robustly than fixed tests or preference judgments.","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Baoqing Yue, Brian Fan, Hufei Yang, Jichen Feng, Mengdi Wang, Qian Sun, Yifan Zhang, Yutong Han, Zihan Zhu","submitted_at":"2026-03-05T02:18:26Z","abstract_excerpt":"Existing reasoning evaluation paradigms suffer from different limitations: fixed benchmarks are increasingly saturated and vulnerable to contamination, while preference-based evaluations rely on subjective judgments. We argue that a core aspect of intelligence is the ability to decide what information to acquire and how to use it effectively. We propose Interactive Benchmarks, a unified evaluation paradigm that assesses a model's reasoning ability through budgeted multi-turn interaction. We evaluate models under this framework in two settings: Interactive Proofs, where models interact with a j"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our results show that interactive benchmarks provide a more robust assessment of this dimension of model intelligence, revealing substantial room for improvement in interactive scenarios.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That budgeted multi-turn interaction with objective feedback accurately isolates and measures core reasoning ability without introducing new biases from the interaction protocol or judge design.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Interactive Benchmarks assess AI reasoning via budgeted multi-turn interactions in proof and game settings, offering a more robust alternative to saturated fixed benchmarks and subjective preferences.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Interactive benchmarks using budgeted multi-turn interaction with objective feedback assess AI reasoning more robustly than fixed tests or preference judgments.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d53f749ba466aa07ccf604acdfc951e2c92db283ffd8b5bcb5d49614a28c86bf"},"source":{"id":"2603.04737","kind":"arxiv","version":4},"verdict":{"id":"2bbbcc01-c884-4d57-96b4-f154a9b89bb5","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T17:08:18.972350Z","strongest_claim":"Our results show that interactive benchmarks provide a more robust assessment of this dimension of model intelligence, revealing substantial room for improvement in interactive scenarios.","one_line_summary":"Interactive Benchmarks assess AI reasoning via budgeted multi-turn interactions in proof and game settings, offering a more robust alternative to saturated fixed benchmarks and subjective preferences.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That budgeted multi-turn interaction with objective feedback accurately isolates and measures core reasoning ability without introducing new biases from the interaction protocol or judge design.","pith_extraction_headline":"Interactive benchmarks using budgeted multi-turn interaction with objective feedback assess AI reasoning more robustly than fixed tests or preference judgments."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.04737/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":"2603.04737","created_at":"2026-05-20T00:03:07.791597+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.04737v4","created_at":"2026-05-20T00:03:07.791597+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.04737","created_at":"2026-05-20T00:03:07.791597+00:00"},{"alias_kind":"pith_short_12","alias_value":"WQZ6GTIBOZEY","created_at":"2026-05-20T00:03:07.791597+00:00"},{"alias_kind":"pith_short_16","alias_value":"WQZ6GTIBOZEYPCQ7","created_at":"2026-05-20T00:03:07.791597+00:00"},{"alias_kind":"pith_short_8","alias_value":"WQZ6GTIB","created_at":"2026-05-20T00:03:07.791597+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.17829","citing_title":"Interactive Evaluation Requires a Design Science","ref_index":67,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10379","citing_title":"Not All Proofs Are Equal: Evaluating LLM Proof Quality Beyond Correctness","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WQZ6GTIBOZEYPCQ7EABSJOLDRQ","json":"https://pith.science/pith/WQZ6GTIBOZEYPCQ7EABSJOLDRQ.json","graph_json":"https://pith.science/api/pith-number/WQZ6GTIBOZEYPCQ7EABSJOLDRQ/graph.json","events_json":"https://pith.science/api/pith-number/WQZ6GTIBOZEYPCQ7EABSJOLDRQ/events.json","paper":"https://pith.science/paper/WQZ6GTIB"},"agent_actions":{"view_html":"https://pith.science/pith/WQZ6GTIBOZEYPCQ7EABSJOLDRQ","download_json":"https://pith.science/pith/WQZ6GTIBOZEYPCQ7EABSJOLDRQ.json","view_paper":"https://pith.science/paper/WQZ6GTIB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.04737&json=true","fetch_graph":"https://pith.science/api/pith-number/WQZ6GTIBOZEYPCQ7EABSJOLDRQ/graph.json","fetch_events":"https://pith.science/api/pith-number/WQZ6GTIBOZEYPCQ7EABSJOLDRQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WQZ6GTIBOZEYPCQ7EABSJOLDRQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WQZ6GTIBOZEYPCQ7EABSJOLDRQ/action/storage_attestation","attest_author":"https://pith.science/pith/WQZ6GTIBOZEYPCQ7EABSJOLDRQ/action/author_attestation","sign_citation":"https://pith.science/pith/WQZ6GTIBOZEYPCQ7EABSJOLDRQ/action/citation_signature","submit_replication":"https://pith.science/pith/WQZ6GTIBOZEYPCQ7EABSJOLDRQ/action/replication_record"}},"created_at":"2026-05-20T00:03:07.791597+00:00","updated_at":"2026-05-20T00:03:07.791597+00:00"}