{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XLAAXLMKBDUR5N5OCFRATPXMJP","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":"a8506f61b536b86ad424ca88af62943ab1ed4d729c0d88fcfd82998d2899c0fb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-02T12:58:42Z","title_canon_sha256":"e35b9cacee8d7cd56ce25e939c00b263eb47d565ab594d4937e45560e0cbbfc9"},"schema_version":"1.0","source":{"id":"2504.01698","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.01698","created_at":"2026-07-05T11:03:58Z"},{"alias_kind":"arxiv_version","alias_value":"2504.01698v3","created_at":"2026-07-05T11:03:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01698","created_at":"2026-07-05T11:03:58Z"},{"alias_kind":"pith_short_12","alias_value":"XLAAXLMKBDUR","created_at":"2026-07-05T11:03:58Z"},{"alias_kind":"pith_short_16","alias_value":"XLAAXLMKBDUR5N5O","created_at":"2026-07-05T11:03:58Z"},{"alias_kind":"pith_short_8","alias_value":"XLAAXLMK","created_at":"2026-07-05T11:03:58Z"}],"graph_snapshots":[{"event_id":"sha256:4636f0751b362a9d54ba3227bf4eceef31e5a52a413be6ad41a93eb6bdb541be","target":"graph","created_at":"2026-07-05T11:03:58Z","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/2504.01698/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Theory of Mind (ToM), the ability to attribute mental states to others, is fundamental for human social intelligence and a critical capability for advanced Artificial Intelligence. Recent advancements in Large Language Models (LLMs) have shown promising performance on ToM benchmarks, raising the question: Do these benchmarks necessitate explicit human-like reasoning processes, or can models succeed through alternative strategies? We investigate this question empirically by applying Reinforcement Learning (RL) and Supervised Fine-Tuning (SFT) to LLMs of varying scales (0.5B to 7B parameters) an","authors_text":"Chunhui Zhang, Jiajun Song, Lifeng Fan, Wei Wang, Yi-Long Lu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-02T12:58:42Z","title":"Do Theory of Mind Benchmarks Need Explicit Human-like Reasoning in Language Models?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01698","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":"sha256:0f9dd0005592570c5207a9450ed0470a637a64be4fe589bd618fe4b48cc5aa0d","target":"record","created_at":"2026-07-05T11:03:58Z","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":"a8506f61b536b86ad424ca88af62943ab1ed4d729c0d88fcfd82998d2899c0fb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-02T12:58:42Z","title_canon_sha256":"e35b9cacee8d7cd56ce25e939c00b263eb47d565ab594d4937e45560e0cbbfc9"},"schema_version":"1.0","source":{"id":"2504.01698","kind":"arxiv","version":3}},"canonical_sha256":"bac00bad8a08e91eb7ae116209beec4bf2522da300c6811b6f5613d65f8c7926","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bac00bad8a08e91eb7ae116209beec4bf2522da300c6811b6f5613d65f8c7926","first_computed_at":"2026-07-05T11:03:58.937129Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:03:58.937129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1ev3md7QxkZrbvlX7Nl4sk8wtEmEp+ckq46XQ7uVh/39D6BgJ69sWnMXrpE5o+wG/k0EVoDryenJYnNIa0gbAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:03:58.937620Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.01698","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f9dd0005592570c5207a9450ed0470a637a64be4fe589bd618fe4b48cc5aa0d","sha256:4636f0751b362a9d54ba3227bf4eceef31e5a52a413be6ad41a93eb6bdb541be"],"state_sha256":"2e7765337d5d17b69e7659ff966e1a0434daa91b71bbeb8437f44589c297b339"}