{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QU27U3ZNJT2WEEE4VG4LE5DM4I","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":"a846f38ef18798bb40b3760ec04c8cfa44d47e5ae79933d22bbba9824ae1c2b6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-27T17:13:20Z","title_canon_sha256":"c9cea23e59d2a74d0ac2fdfef5b8d15e1ea632a24fa705f7bcb6922178f69eb5"},"schema_version":"1.0","source":{"id":"2602.24188","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.24188","created_at":"2026-08-12T00:22:17Z"},{"alias_kind":"arxiv_version","alias_value":"2602.24188v2","created_at":"2026-08-12T00:22:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.24188","created_at":"2026-08-12T00:22:17Z"},{"alias_kind":"pith_short_12","alias_value":"QU27U3ZNJT2W","created_at":"2026-08-12T00:22:17Z"},{"alias_kind":"pith_short_16","alias_value":"QU27U3ZNJT2WEEE4","created_at":"2026-08-12T00:22:17Z"},{"alias_kind":"pith_short_8","alias_value":"QU27U3ZN","created_at":"2026-08-12T00:22:17Z"}],"graph_snapshots":[{"event_id":"sha256:887ed148489b422594f7d77726cdaa1f712460af58c716c8ade97a0aff7d4365","target":"graph","created_at":"2026-08-12T00:22:17Z","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/2602.24188/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a scalable and verifiable methodology for evaluating language models in multi-turn interactions, using a suite of collaborative games that require effective communication about private information. This enables an interactive scaling analysis, in which a fixed token budget is divided over a variable number of turns. We find that language models often fail to use interactive collaboration to improve over the non-interactive baseline in which one agent summarizes its information and the other agent immediately acts, despite substantial headroom. This suggests that state-of-the-art mod","authors_text":"Adam Fisch, Fantine Huot, Jacob Eisenstein, Jonathan Berant, Mirella Lapata","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-27T17:13:20Z","title":"MT-PingEval: Evaluating Multi-Turn Collaboration with Private Information Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.24188","kind":"arxiv","version":2},"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":"sha256:0871ff5c33d079e4e873deaf3644f287e3c284e2ef740b5fd36c4696f5416a4b","target":"record","created_at":"2026-08-12T00:22:17Z","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":"a846f38ef18798bb40b3760ec04c8cfa44d47e5ae79933d22bbba9824ae1c2b6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-27T17:13:20Z","title_canon_sha256":"c9cea23e59d2a74d0ac2fdfef5b8d15e1ea632a24fa705f7bcb6922178f69eb5"},"schema_version":"1.0","source":{"id":"2602.24188","kind":"arxiv","version":2}},"canonical_sha256":"8535fa6f2d4cf562109ca9b8b2746ce20ec6eee6ce2e9d8cbd8024a700e58f0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8535fa6f2d4cf562109ca9b8b2746ce20ec6eee6ce2e9d8cbd8024a700e58f0e","first_computed_at":"2026-08-12T00:22:17.050098Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-12T00:22:17.050098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G2ncRRCrZeiBtuedoEEH+k/t9U38zd2NZgrqRhdmAk0ww8CFSGqs1pXTsNOHtIwkS5TpfNBlMXi4ImJm+rsxCg==","signature_status":"signed_v1","signed_at":"2026-08-12T00:22:17.051962Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.24188","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0871ff5c33d079e4e873deaf3644f287e3c284e2ef740b5fd36c4696f5416a4b","sha256:887ed148489b422594f7d77726cdaa1f712460af58c716c8ade97a0aff7d4365"],"state_sha256":"939e6048c1e7cc38769aae3b29e9a8291d2f8c8f1c3ea2d5b8daa72018e58bd4"}