{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WQZ6GTIBOZEYPCQ7EABSJOLDRQ","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":"0ee398b76bdb86d4f25b173f42d223f44710e1cc5bc18a3f88e8f313e07343e9","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-03-05T02:18:26Z","title_canon_sha256":"19375cc5ad0fd20976fdc336fd90a3833c683d81ae6c67c68b0c67971f295ab8"},"schema_version":"1.0","source":{"id":"2603.04737","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.04737","created_at":"2026-05-20T00:03:07Z"},{"alias_kind":"arxiv_version","alias_value":"2603.04737v4","created_at":"2026-05-20T00:03:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.04737","created_at":"2026-05-20T00:03:07Z"},{"alias_kind":"pith_short_12","alias_value":"WQZ6GTIBOZEY","created_at":"2026-05-20T00:03:07Z"},{"alias_kind":"pith_short_16","alias_value":"WQZ6GTIBOZEYPCQ7","created_at":"2026-05-20T00:03:07Z"},{"alias_kind":"pith_short_8","alias_value":"WQZ6GTIB","created_at":"2026-05-20T00:03:07Z"}],"graph_snapshots":[{"event_id":"sha256:02a5709a26e3e161087c9bb2e8390445d782a4418d15c62863b4e336771fb15e","target":"graph","created_at":"2026-05-20T00:03:07Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Interactive benchmarks using budgeted multi-turn interaction with objective feedback assess AI reasoning more robustly than fixed tests or preference judgments."}],"snapshot_sha256":"d53f749ba466aa07ccf604acdfc951e2c92db283ffd8b5bcb5d49614a28c86bf"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.04737/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Baoqing Yue, Brian Fan, Hufei Yang, Jichen Feng, Mengdi Wang, Qian Sun, Yifan Zhang, Yutong Han, Zihan Zhu","cross_cats":["cs.CL","cs.LG"],"headline":"Interactive benchmarks using budgeted multi-turn interaction with objective feedback assess AI reasoning more robustly than fixed tests or preference judgments.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-03-05T02:18:26Z","title":"Interactive Benchmarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.04737","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-15T17:08:18.972350Z","id":"2bbbcc01-c884-4d57-96b4-f154a9b89bb5","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Interactive benchmarks using budgeted multi-turn interaction with objective feedback assess AI reasoning more robustly than fixed tests or preference judgments.","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.","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."}},"verdict_id":"2bbbcc01-c884-4d57-96b4-f154a9b89bb5"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9c82027165c196b59104ecd1dc504034b74091506437e412f024d0ecf82fa7a7","target":"record","created_at":"2026-05-20T00:03:07Z","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":"0ee398b76bdb86d4f25b173f42d223f44710e1cc5bc18a3f88e8f313e07343e9","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-03-05T02:18:26Z","title_canon_sha256":"19375cc5ad0fd20976fdc336fd90a3833c683d81ae6c67c68b0c67971f295ab8"},"schema_version":"1.0","source":{"id":"2603.04737","kind":"arxiv","version":4}},"canonical_sha256":"b433e34d017649878a1f200324b9638c0fe4230eee1cb2c35ec246b9b08169a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b433e34d017649878a1f200324b9638c0fe4230eee1cb2c35ec246b9b08169a0","first_computed_at":"2026-05-20T00:03:07.791472Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:07.791472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yE96nfI5kXVCoMW+DBW9gaP+NgMo4dvn+8BHEHu7PNU9wMOPDxFbamWrDPQKPrjgmt2swjFjFMFHZqRM5vLWAA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:07.792265Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.04737","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c82027165c196b59104ecd1dc504034b74091506437e412f024d0ecf82fa7a7","sha256:02a5709a26e3e161087c9bb2e8390445d782a4418d15c62863b4e336771fb15e"],"state_sha256":"4016f2965235912fefa7d087669545df3b365163b870c1c239ac3ebd9bb1a0d0"}