{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WQZ6GTIBOZEYPCQ7EABSJOLDRQ","short_pith_number":"pith:WQZ6GTIB","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"},"canonical_sha256":"b433e34d017649878a1f200324b9638c0fe4230eee1cb2c35ec246b9b08169a0","source":{"kind":"arxiv","id":"2603.04737","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WQZ6GTIBOZEYPCQ7EABSJOLDRQ","target":"record","payload":{"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"},"canonical_sha256":"b433e34d017649878a1f200324b9638c0fe4230eee1cb2c35ec246b9b08169a0","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"},"source_kind":"arxiv","source_id":"2603.04737","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:03:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0D36eslmxvh5m3cXKBRU/9oVhzpwsjuIV0OZz/PUO3vJ9ffcubgUta614xbiQHOmJCd5HCWtP5mB+sNN16cFAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T04:55:08.844801Z"},"content_sha256":"9c82027165c196b59104ecd1dc504034b74091506437e412f024d0ecf82fa7a7","schema_version":"1.0","event_id":"sha256:9c82027165c196b59104ecd1dc504034b74091506437e412f024d0ecf82fa7a7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WQZ6GTIBOZEYPCQ7EABSJOLDRQ","target":"graph","payload":{"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"},"verdict_id":"2bbbcc01-c884-4d57-96b4-f154a9b89bb5"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:03:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q4z+rxUTPzQSPs1ZcUwCEnU7NV+kP9jizd+yH9oq/hzwRG45rDrdHe+DNp+pfvFhaUiGwv2rDCNQhciPazfNAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T04:55:08.845629Z"},"content_sha256":"02a5709a26e3e161087c9bb2e8390445d782a4418d15c62863b4e336771fb15e","schema_version":"1.0","event_id":"sha256:02a5709a26e3e161087c9bb2e8390445d782a4418d15c62863b4e336771fb15e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WQZ6GTIBOZEYPCQ7EABSJOLDRQ/bundle.json","state_url":"https://pith.science/pith/WQZ6GTIBOZEYPCQ7EABSJOLDRQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WQZ6GTIBOZEYPCQ7EABSJOLDRQ/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":"2026-05-24T04:55:08Z","links":{"resolver":"https://pith.science/pith/WQZ6GTIBOZEYPCQ7EABSJOLDRQ","bundle":"https://pith.science/pith/WQZ6GTIBOZEYPCQ7EABSJOLDRQ/bundle.json","state":"https://pith.science/pith/WQZ6GTIBOZEYPCQ7EABSJOLDRQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WQZ6GTIBOZEYPCQ7EABSJOLDRQ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bXaIIGRiZsCv4l9fW/Xa/xkRrRV+9lmFUd7XauXMjIZ4ot8o7wnP1sTnotJG5IWleDpYPgrGpVrXy7CficrVDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T04:55:08.849754Z","bundle_sha256":"a033298fb276f9d69c7d24ceea3e2b22337f2df56f24f6233a42f468546a7a70"}}