{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3JMZEFV2NOUKAK6VBHRJZ6ES3L","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":"bd25b121fd31b68623bfeb234644fe75b6579c3809eba0bdae9254622398776f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-21T16:47:59Z","title_canon_sha256":"52898d728d827f9a36b6ceb185fc80b247dcb69f87be3de6a3a661ee6eec8c77"},"schema_version":"1.0","source":{"id":"2507.15788","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.15788","created_at":"2026-07-05T11:40:44Z"},{"alias_kind":"arxiv_version","alias_value":"2507.15788v1","created_at":"2026-07-05T11:40:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.15788","created_at":"2026-07-05T11:40:44Z"},{"alias_kind":"pith_short_12","alias_value":"3JMZEFV2NOUK","created_at":"2026-07-05T11:40:44Z"},{"alias_kind":"pith_short_16","alias_value":"3JMZEFV2NOUKAK6V","created_at":"2026-07-05T11:40:44Z"},{"alias_kind":"pith_short_8","alias_value":"3JMZEFV2","created_at":"2026-07-05T11:40:44Z"}],"graph_snapshots":[{"event_id":"sha256:4c1c23bbbfb51be92ae0480cf1b8e98cc6b3360dfd37a15a265702e6850a781a","target":"graph","created_at":"2026-07-05T11:40:44Z","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/2507.15788/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in large language models (LLMs) have demonstrated emergent capabilities in complex reasoning, largely spurred by rule-based Reinforcement Learning (RL) techniques applied during the post-training. This has raised the question of whether similar methods can instill more nuanced, human-like social intelligence, such as a Theory of Mind (ToM), in LLMs. This paper investigates whether small-scale LLMs can acquire a robust and generalizable ToM capability through RL with verifiable rewards (RLVR). We conduct a systematic evaluation by training models on various combinations of p","authors_text":"Hanan Salam, Sneheel Sarangi","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-21T16:47:59Z","title":"Small LLMs Do Not Learn a Generalizable Theory of Mind via Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.15788","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":"sha256:63cc9538664922e23ea001ea86d33374a0b70e5325531a2b77424360eb1d8e35","target":"record","created_at":"2026-07-05T11:40:44Z","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":"bd25b121fd31b68623bfeb234644fe75b6579c3809eba0bdae9254622398776f","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-21T16:47:59Z","title_canon_sha256":"52898d728d827f9a36b6ceb185fc80b247dcb69f87be3de6a3a661ee6eec8c77"},"schema_version":"1.0","source":{"id":"2507.15788","kind":"arxiv","version":1}},"canonical_sha256":"da599216ba6ba8a02bd509e29cf892daf685521d996d33df5521a0cce9e0b6af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da599216ba6ba8a02bd509e29cf892daf685521d996d33df5521a0cce9e0b6af","first_computed_at":"2026-07-05T11:40:44.279793Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:44.279793Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9yr3a2//F/SZJ0KFJBXMKWKE4P2Bz1MX0oj/AEZMBSwjnj0Pinc7vqcTDIvTWlL96KlETZH9WWXNS3S2RSx0Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:44.280263Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.15788","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63cc9538664922e23ea001ea86d33374a0b70e5325531a2b77424360eb1d8e35","sha256:4c1c23bbbfb51be92ae0480cf1b8e98cc6b3360dfd37a15a265702e6850a781a"],"state_sha256":"144984f77b49faa902ee6d90d575426eb03f1fc86f8bdee17544ba9f70365366"}