{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ST5NILT7I3A3PIPG7XEP6KMFCH","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":"df5c5fcbaabf1d8a2df211599655f494c38fa46d66b2d4e9f8e3988b868d4c02","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-06T14:37:33Z","title_canon_sha256":"b769fe8a7d70332360d72ba3daa2d2a4d4dd95ac277256f91835e05fed6a83d5"},"schema_version":"1.0","source":{"id":"2606.08200","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08200","created_at":"2026-06-09T01:05:29Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08200v1","created_at":"2026-06-09T01:05:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08200","created_at":"2026-06-09T01:05:29Z"},{"alias_kind":"pith_short_12","alias_value":"ST5NILT7I3A3","created_at":"2026-06-09T01:05:29Z"},{"alias_kind":"pith_short_16","alias_value":"ST5NILT7I3A3PIPG","created_at":"2026-06-09T01:05:29Z"},{"alias_kind":"pith_short_8","alias_value":"ST5NILT7","created_at":"2026-06-09T01:05:29Z"}],"graph_snapshots":[{"event_id":"sha256:1838fac2eb3495fe3e25cc45509a892776f93cd540522312c85845dee0bcc2b0","target":"graph","created_at":"2026-06-09T01:05:29Z","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/2606.08200/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating LLM-powered interactive social agents is challenging because socially relevant behaviors depend not only on isolated outputs, but also on prior interactions, social roles, and downstream actions. Existing methods typically allow a target agent to act freely in an environment and then score the resulting trajectory. However, this passive setup can miss capabilities that only become observable under specific social circumstances; for example, conflict handling may remain untested if no disagreement arises. We propose Online Agent-as-a-Judge, a situation-generating evaluation framework","authors_text":"Chaeun Lee, Donghoon Ham, Hyogon Ryu, Jeonghwan Kim, Jeongwook Kim, Yewon Lim","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-06T14:37:33Z","title":"Online Agent-as-a-Judge: Situation-Generating Evaluation for Interactive Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08200","kind":"arxiv","version":1},"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":"sha256:78c58f3592af1e5651f21d0cac9360fd121b309c8550304232d83bde1b240891","target":"record","created_at":"2026-06-09T01:05:29Z","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":"df5c5fcbaabf1d8a2df211599655f494c38fa46d66b2d4e9f8e3988b868d4c02","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-06T14:37:33Z","title_canon_sha256":"b769fe8a7d70332360d72ba3daa2d2a4d4dd95ac277256f91835e05fed6a83d5"},"schema_version":"1.0","source":{"id":"2606.08200","kind":"arxiv","version":1}},"canonical_sha256":"94fad42e7f46c1b7a1e6fdc8ff298511dace7686962c7e254727f60985e1dae0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94fad42e7f46c1b7a1e6fdc8ff298511dace7686962c7e254727f60985e1dae0","first_computed_at":"2026-06-09T01:05:29.861898Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:29.861898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4cggWBTS5dYlF0CuKnm/38UKgmmv2G4xgf41PkyblmGPfDh20T+0HQlAIl65L+Wg6KfKmovnGUMBcQM6WI/eCw==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:29.862504Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08200","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78c58f3592af1e5651f21d0cac9360fd121b309c8550304232d83bde1b240891","sha256:1838fac2eb3495fe3e25cc45509a892776f93cd540522312c85845dee0bcc2b0"],"state_sha256":"9214c9a45cc879b8fa37d00c7414ec3dfe3f044d22d49b4d5fc25c389e8410e5"}