{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DHFJL7GBMPQOVHTGB33QBZ5S65","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":"971b17eac94525f4287fdb302b7febadb916c8b316f4326ec77a1ef8b2d4d6d7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T16:05:18Z","title_canon_sha256":"2ee1723fa380b6d3a0a0e4c95ce85f86e15b3dd06a48b97a115c0d0895ad8e2a"},"schema_version":"1.0","source":{"id":"2502.14669","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14669","created_at":"2026-07-05T10:19:39Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14669v3","created_at":"2026-07-05T10:19:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14669","created_at":"2026-07-05T10:19:39Z"},{"alias_kind":"pith_short_12","alias_value":"DHFJL7GBMPQO","created_at":"2026-07-05T10:19:39Z"},{"alias_kind":"pith_short_16","alias_value":"DHFJL7GBMPQOVHTG","created_at":"2026-07-05T10:19:39Z"},{"alias_kind":"pith_short_8","alias_value":"DHFJL7GB","created_at":"2026-07-05T10:19:39Z"}],"graph_snapshots":[{"event_id":"sha256:462376ea03c95caf80f3d53e0880090787a08519ed3fe586267c8ee5647143f4","target":"graph","created_at":"2026-07-05T10:19:39Z","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/2502.14669/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated impressive capabilities in language processing, yet they often struggle with tasks requiring genuine visual spatial reasoning. In this paper, we introduce a novel two-stage training framework designed to equip standard LLMs with visual reasoning abilities for maze navigation. First, we leverage Supervised Fine Tuning (SFT) on a curated dataset of tokenized maze representations to teach the model to predict step-by-step movement commands. Next, we apply Group Relative Policy Optimization (GRPO)-a technique used in DeepSeekR1-with a carefully crafte","authors_text":"Alan Dao (Gia Tuan Dao), Dinh Bach Vu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T16:05:18Z","title":"AlphaMaze: Enhancing Large Language Models' Spatial Intelligence via GRPO"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14669","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":"sha256:18d1b556133fdb68adc3e530a00c817a2d4949dd675af591adda6bcfaf1f2c99","target":"record","created_at":"2026-07-05T10:19:39Z","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":"971b17eac94525f4287fdb302b7febadb916c8b316f4326ec77a1ef8b2d4d6d7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T16:05:18Z","title_canon_sha256":"2ee1723fa380b6d3a0a0e4c95ce85f86e15b3dd06a48b97a115c0d0895ad8e2a"},"schema_version":"1.0","source":{"id":"2502.14669","kind":"arxiv","version":3}},"canonical_sha256":"19ca95fcc163e0ea9e660ef700e7b2f772ef49cb6b638e8384b3014997cd5d1e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19ca95fcc163e0ea9e660ef700e7b2f772ef49cb6b638e8384b3014997cd5d1e","first_computed_at":"2026-07-05T10:19:39.720587Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:19:39.720587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MYuhkHun00iQXOb/ILOB3OAkppU6zYTamSxcapKG51XvKY4YBUS6F9RGvMJyrpRbA5HRccWQzMtnURT52I4XAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:19:39.721065Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.14669","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:18d1b556133fdb68adc3e530a00c817a2d4949dd675af591adda6bcfaf1f2c99","sha256:462376ea03c95caf80f3d53e0880090787a08519ed3fe586267c8ee5647143f4"],"state_sha256":"e67ea76dd6b077d91dab1b7d59b7322b66e085210c28ad8ac0e2c2d050de8f2d"}