{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:52YMVX2E3PTADRRW2TGBBHRIV2","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":"5ba0faef346c4e747a642d3d361844ba8cab33c653abb4796f627b7444a2d7a0","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-18T06:50:39Z","title_canon_sha256":"975351d4a72f5edd602fd0e9234c39931bc46d67fa9bd38be36e6316aa3d8c74"},"schema_version":"1.0","source":{"id":"2412.13549","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13549","created_at":"2026-07-05T11:08:39Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13549v2","created_at":"2026-07-05T11:08:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13549","created_at":"2026-07-05T11:08:39Z"},{"alias_kind":"pith_short_12","alias_value":"52YMVX2E3PTA","created_at":"2026-07-05T11:08:39Z"},{"alias_kind":"pith_short_16","alias_value":"52YMVX2E3PTADRRW","created_at":"2026-07-05T11:08:39Z"},{"alias_kind":"pith_short_8","alias_value":"52YMVX2E","created_at":"2026-07-05T11:08:39Z"}],"graph_snapshots":[{"event_id":"sha256:dbba242a112fcb5c6855b2cfee953ef7519256f110769ab4d27567e038178997","target":"graph","created_at":"2026-07-05T11:08:39Z","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/2412.13549/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language model agents excel in long-session planning and reasoning, but existing benchmarks primarily focus on goal-oriented tasks with explicit objectives, neglecting creative adaptation in unfamiliar environments. To address this, we introduce EscapeBench, a benchmark suite of room escape game environments designed to challenge agents with creative reasoning, unconventional tool use, and iterative problem-solving to uncover implicit goals. Our results show that current LM models, despite employing working memory and Chain-of-Thought reasoning, achieve only 15% average progress without hints,","authors_text":"Bingxiang He, Cheng Qian, Denghui Zhang, Heng Ji, Hongyi Du, Jiarui Yao, Peixuan Han, Qinyu Luo, Xiaocheng Yang, Xiusi Chen, Yuji Zhang, Yunzhu Li","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-18T06:50:39Z","title":"EscapeBench: Towards Advancing Creative Intelligence of Language Model Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13549","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":"sha256:87ae29e6c6c17ac3c4014f50019623f7c5bfe4cb1324394ebce01bc6fe41e943","target":"record","created_at":"2026-07-05T11:08:39Z","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":"5ba0faef346c4e747a642d3d361844ba8cab33c653abb4796f627b7444a2d7a0","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-18T06:50:39Z","title_canon_sha256":"975351d4a72f5edd602fd0e9234c39931bc46d67fa9bd38be36e6316aa3d8c74"},"schema_version":"1.0","source":{"id":"2412.13549","kind":"arxiv","version":2}},"canonical_sha256":"eeb0cadf44dbe601c636d4cc109e28aeb9327361760a60383e57f54e2254e38b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eeb0cadf44dbe601c636d4cc109e28aeb9327361760a60383e57f54e2254e38b","first_computed_at":"2026-07-05T11:08:39.444406Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:39.444406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CgD731gd5co4Yyw2NnfXN/7wqz3t7khNIsHyqNaMSEfzqCVDJwyCBg0akMK7Lyske/9Iz+0MXo0l4GC0iXpKCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:39.444854Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.13549","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:87ae29e6c6c17ac3c4014f50019623f7c5bfe4cb1324394ebce01bc6fe41e943","sha256:dbba242a112fcb5c6855b2cfee953ef7519256f110769ab4d27567e038178997"],"state_sha256":"be48b1ce9d638e6d16863b88576140c0b3d4b450d063e7c778db7536d97c17d7"}