{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XJKCQFUNOB5CIO5DJEXB6LWASP","short_pith_number":"pith:XJKCQFUN","schema_version":"1.0","canonical_sha256":"ba5428168d707a243ba3492e1f2ec093d67ed54a8bdd7030464ea35c0e606628","source":{"kind":"arxiv","id":"2604.20443","version":2},"attestation_state":"computed","paper":{"title":"DialToM: A Theory of Mind Benchmark for Forecasting State-Driven Dialogue Trajectories","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"LLMs identify mental states in dialogue but mostly fail to forecast how conversations will unfold from those states.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ee-Peng Lim, Jing Jiang, Neemesh Yadav, Palakorn Achananuparp","submitted_at":"2026-04-22T11:07:46Z","abstract_excerpt":"We introduce DialToM, an annotated Theory of Mind (ToM) benchmark built from naturalistic human-human dialogues using a multiple-choice evaluation framework. Concurrent with recent work showing a gap between explicit mental-state inference and applied ToM in synthetic settings~\\cite{gu2024simpletom}, we establish a stricter \\emph{State-Driven Diagnostic Probe} in which models must forecast state-consistent dialogue trajectories solely from isolated mental-state profiles without dialogue context. Our evaluation reveals a systematic reasoning asymmetry -- LLMs excel at inferring mental states (L"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2604.20443","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-22T11:07:46Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2e57dfb93a3f43f4336b19bb1018e135f22eb1596f1a075b039054fad6ab05ba","abstract_canon_sha256":"a25d475a8c8736d531719bc2b874818b43bdeba61a4bc96432f36c6330245e50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:10.264393Z","signature_b64":"YcyPeCu45pPUhfnZc4AR50KSwI31jUZkx4xrbfMy0ALPnLgeatChl0nVzXJTxBfLie+SqZE67lLQLKkcwP9iCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba5428168d707a243ba3492e1f2ec093d67ed54a8bdd7030464ea35c0e606628","last_reissued_at":"2026-05-29T01:05:10.263651Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:10.263651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DialToM: A Theory of Mind Benchmark for Forecasting State-Driven Dialogue Trajectories","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"LLMs identify mental states in dialogue but mostly fail to forecast how conversations will unfold from those states.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ee-Peng Lim, Jing Jiang, Neemesh Yadav, Palakorn Achananuparp","submitted_at":"2026-04-22T11:07:46Z","abstract_excerpt":"We introduce DialToM, an annotated Theory of Mind (ToM) benchmark built from naturalistic human-human dialogues using a multiple-choice evaluation framework. Concurrent with recent work showing a gap between explicit mental-state inference and applied ToM in synthetic settings~\\cite{gu2024simpletom}, we establish a stricter \\emph{State-Driven Diagnostic Probe} in which models must forecast state-consistent dialogue trajectories solely from isolated mental-state profiles without dialogue context. Our evaluation reveals a systematic reasoning asymmetry -- LLMs excel at inferring mental states (L"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"while LLMs excel at identifying mental states, most (except for Gemini 3 Pro) fail to leverage this understanding to forecast social trajectories. Additionally, we find only weak semantic similarities between human and LLM-generated inferences.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The multiple-choice forecasting task and human verification process truly isolate functional use of mental states rather than surface patterns or dataset artifacts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LLMs identify mental states in dialogues well but mostly fail to forecast state-consistent future trajectories, except Gemini 3 Pro, with only weak overlap to human inferences.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"LLMs identify mental states in dialogue but mostly fail to forecast how conversations will unfold from those states.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"db27c057a6ab35cad11b4953bd0b753ca65b4cf01db87a13a0aae541705eedd1"},"source":{"id":"2604.20443","kind":"arxiv","version":2},"verdict":{"id":"2a223c87-1837-41c9-ab90-842526338d29","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T00:08:44.170035Z","strongest_claim":"while LLMs excel at identifying mental states, most (except for Gemini 3 Pro) fail to leverage this understanding to forecast social trajectories. Additionally, we find only weak semantic similarities between human and LLM-generated inferences.","one_line_summary":"LLMs identify mental states in dialogues well but mostly fail to forecast state-consistent future trajectories, except Gemini 3 Pro, with only weak overlap to human inferences.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The multiple-choice forecasting task and human verification process truly isolate functional use of mental states rather than surface patterns or dataset artifacts.","pith_extraction_headline":"LLMs identify mental states in dialogue but mostly fail to forecast how conversations will unfold from those states."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.20443/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T14:40:55.183844Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-20T01:57:39.116414Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"0b11cfeed745d09eb6e11add2546c83246ea7c4c7075a73314cd03e0d93c561f"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2604.20443","created_at":"2026-05-29T01:05:10.263734+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.20443v2","created_at":"2026-05-29T01:05:10.263734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.20443","created_at":"2026-05-29T01:05:10.263734+00:00"},{"alias_kind":"pith_short_12","alias_value":"XJKCQFUNOB5C","created_at":"2026-05-29T01:05:10.263734+00:00"},{"alias_kind":"pith_short_16","alias_value":"XJKCQFUNOB5CIO5D","created_at":"2026-05-29T01:05:10.263734+00:00"},{"alias_kind":"pith_short_8","alias_value":"XJKCQFUN","created_at":"2026-05-29T01:05:10.263734+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XJKCQFUNOB5CIO5DJEXB6LWASP","json":"https://pith.science/pith/XJKCQFUNOB5CIO5DJEXB6LWASP.json","graph_json":"https://pith.science/api/pith-number/XJKCQFUNOB5CIO5DJEXB6LWASP/graph.json","events_json":"https://pith.science/api/pith-number/XJKCQFUNOB5CIO5DJEXB6LWASP/events.json","paper":"https://pith.science/paper/XJKCQFUN"},"agent_actions":{"view_html":"https://pith.science/pith/XJKCQFUNOB5CIO5DJEXB6LWASP","download_json":"https://pith.science/pith/XJKCQFUNOB5CIO5DJEXB6LWASP.json","view_paper":"https://pith.science/paper/XJKCQFUN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.20443&json=true","fetch_graph":"https://pith.science/api/pith-number/XJKCQFUNOB5CIO5DJEXB6LWASP/graph.json","fetch_events":"https://pith.science/api/pith-number/XJKCQFUNOB5CIO5DJEXB6LWASP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XJKCQFUNOB5CIO5DJEXB6LWASP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XJKCQFUNOB5CIO5DJEXB6LWASP/action/storage_attestation","attest_author":"https://pith.science/pith/XJKCQFUNOB5CIO5DJEXB6LWASP/action/author_attestation","sign_citation":"https://pith.science/pith/XJKCQFUNOB5CIO5DJEXB6LWASP/action/citation_signature","submit_replication":"https://pith.science/pith/XJKCQFUNOB5CIO5DJEXB6LWASP/action/replication_record"}},"created_at":"2026-05-29T01:05:10.263734+00:00","updated_at":"2026-05-29T01:05:10.263734+00:00"}