{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NRPU7DSDS5LDD2XNY6RATMYRSG","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":"a10af04004cbaabdd004c3933055d72bd49c84bddb88a423c0ff831a63b9d49f","cross_cats_sorted":["cs.AI","cs.CL","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-09T18:00:28Z","title_canon_sha256":"2dccb0ecdf73d37338bfce391c6ff9c3958d528aa95da399ec8188f7263301e6"},"schema_version":"1.0","source":{"id":"2602.08964","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.08964","created_at":"2026-06-01T02:03:34Z"},{"alias_kind":"arxiv_version","alias_value":"2602.08964v2","created_at":"2026-06-01T02:03:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.08964","created_at":"2026-06-01T02:03:34Z"},{"alias_kind":"pith_short_12","alias_value":"NRPU7DSDS5LD","created_at":"2026-06-01T02:03:34Z"},{"alias_kind":"pith_short_16","alias_value":"NRPU7DSDS5LDD2XN","created_at":"2026-06-01T02:03:34Z"},{"alias_kind":"pith_short_8","alias_value":"NRPU7DSD","created_at":"2026-06-01T02:03:34Z"}],"graph_snapshots":[{"event_id":"sha256:6199a6f765c2376a718a8fee3e3045256448a0bc067861aef36b7f47225d9519","target":"graph","created_at":"2026-06-01T02:03:34Z","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/2602.08964/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding an agent's goals helps explain and predict its behaviour, yet there is no established methodology for reliably attributing goals to agentic systems. We propose a framework for evaluating goal-directedness that integrates behavioural evaluation with interpretability-based analyses of models' internal representations. As a case study, we examine an LLM agent navigating a 2D grid world towards a goal state. Behaviourally, we evaluate the agent against optimal policies across varying grid sizes, obstacle densities, and goal structures, finding that performance scales with task diffic","authors_text":"Angelos Nalmpantis, Calum McNamara, Evgenii Kortukov, Fade Chen, Gabriele Sarti, Mario Giulianelli, Moksh Nirvaan, Niall Dalton, Raghu Arghal","cross_cats":["cs.AI","cs.CL","cs.CY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-09T18:00:28Z","title":"A Behavioural and Representational Evaluation of Goal-Directedness in Language Model Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.08964","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":"sha256:8b4a32add1336d9376ffdee48dcb5f80a434e35982d43e5d4be36f097b6b884f","target":"record","created_at":"2026-06-01T02:03:34Z","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":"a10af04004cbaabdd004c3933055d72bd49c84bddb88a423c0ff831a63b9d49f","cross_cats_sorted":["cs.AI","cs.CL","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-09T18:00:28Z","title_canon_sha256":"2dccb0ecdf73d37338bfce391c6ff9c3958d528aa95da399ec8188f7263301e6"},"schema_version":"1.0","source":{"id":"2602.08964","kind":"arxiv","version":2}},"canonical_sha256":"6c5f4f8e43975631eaedc7a209b31191a4a20d9fdea7dbc351de662a7ab81745","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c5f4f8e43975631eaedc7a209b31191a4a20d9fdea7dbc351de662a7ab81745","first_computed_at":"2026-06-01T02:03:34.694555Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T02:03:34.694555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7b9mM910VA4Pp/MHAXqvREqCi01yGwd6L3ooO0QHaXfK/jWeDVmzYWttziWNqxrVDrRpph0DX38PwZgIjuPiDQ==","signature_status":"signed_v1","signed_at":"2026-06-01T02:03:34.695691Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.08964","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b4a32add1336d9376ffdee48dcb5f80a434e35982d43e5d4be36f097b6b884f","sha256:6199a6f765c2376a718a8fee3e3045256448a0bc067861aef36b7f47225d9519"],"state_sha256":"9c5665b7eeed912ea65117137f28cb2eec7605134a17383e8ec16d50432c6115"}