{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BOQ3GXOIQPOGFDRBM6WA62CJ67","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":"8c688d70bd627c408d334e2e941b58d47e2826d826b2833eb20c1734126c602d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-26T15:46:14Z","title_canon_sha256":"e16d4946b59f8089f0f32af25fffc4da457b6e3832a53f06640bd8657311a963"},"schema_version":"1.0","source":{"id":"2509.22504","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.22504","created_at":"2026-05-29T02:05:36Z"},{"alias_kind":"arxiv_version","alias_value":"2509.22504v3","created_at":"2026-05-29T02:05:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.22504","created_at":"2026-05-29T02:05:36Z"},{"alias_kind":"pith_short_12","alias_value":"BOQ3GXOIQPOG","created_at":"2026-05-29T02:05:36Z"},{"alias_kind":"pith_short_16","alias_value":"BOQ3GXOIQPOGFDRB","created_at":"2026-05-29T02:05:36Z"},{"alias_kind":"pith_short_8","alias_value":"BOQ3GXOI","created_at":"2026-05-29T02:05:36Z"}],"graph_snapshots":[{"event_id":"sha256:56374cba163baf2dedbfe16867b5c5a246e8b7648ffc21825843d7298937eacc","target":"graph","created_at":"2026-05-29T02:05:36Z","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/2509.22504/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As language model (LM) agents become increasingly capable and adopted in real-world applications, there is a growing need for scalable evaluation frameworks beyond costly, manually designed benchmarks. We propose information-theoretic evaluation based on empowerment, an information-theoretic measure of an agent's influence on future states through its actions. To handle the unique challenges of text-based environments, we introduce EELMA (Estimating Empowerment of Language Model Agents), an algorithm for approximating effective empowerment from multi-turn text interactions. We demonstrate EELM","authors_text":"Jeff Gore, Jinyeop Song, Max Kleiman-Weiner","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-26T15:46:14Z","title":"Estimating the Empowerment of Language Model Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.22504","kind":"arxiv","version":3},"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":"sha256:7b2eeed5f1eb764aa7ea457b927581216c68caf59c93a937d6655a286528eaca","target":"record","created_at":"2026-05-29T02:05:36Z","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":"8c688d70bd627c408d334e2e941b58d47e2826d826b2833eb20c1734126c602d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-09-26T15:46:14Z","title_canon_sha256":"e16d4946b59f8089f0f32af25fffc4da457b6e3832a53f06640bd8657311a963"},"schema_version":"1.0","source":{"id":"2509.22504","kind":"arxiv","version":3}},"canonical_sha256":"0ba1b35dc883dc628e2167ac0f6849f7d130f898c086000e6b130646878f0617","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ba1b35dc883dc628e2167ac0f6849f7d130f898c086000e6b130646878f0617","first_computed_at":"2026-05-29T02:05:36.430982Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:05:36.430982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3J+ug37EtT4rxIB15XgekhIYZCc69/lff1Z/YHMoJiZk5XTRuskaDywE4G2kWgMpEJHU+fr9n0FjHNd1WHbqDw==","signature_status":"signed_v1","signed_at":"2026-05-29T02:05:36.431421Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.22504","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7b2eeed5f1eb764aa7ea457b927581216c68caf59c93a937d6655a286528eaca","sha256:56374cba163baf2dedbfe16867b5c5a246e8b7648ffc21825843d7298937eacc"],"state_sha256":"20a9543bf62c38feeba6ee6a0722f88cab996fa095f7ab444e266e2591841a0c"}