{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:XJKCQFUNOB5CIO5DJEXB6LWASP","short_pith_number":"pith:XJKCQFUN","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"},"canonical_sha256":"ba5428168d707a243ba3492e1f2ec093d67ed54a8bdd7030464ea35c0e606628","source":{"kind":"arxiv","id":"2604.20443","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.20443","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"arxiv_version","alias_value":"2604.20443v2","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.20443","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"pith_short_12","alias_value":"XJKCQFUNOB5C","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"pith_short_16","alias_value":"XJKCQFUNOB5CIO5D","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"pith_short_8","alias_value":"XJKCQFUN","created_at":"2026-05-29T01:05:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:XJKCQFUNOB5CIO5DJEXB6LWASP","target":"record","payload":{"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"},"canonical_sha256":"ba5428168d707a243ba3492e1f2ec093d67ed54a8bdd7030464ea35c0e606628","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"},"source_kind":"arxiv","source_id":"2604.20443","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T01:05:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qn1bYhMDg/wbZLcvRutXzPH1VpcpfhgyGcKeWwvJm4SLiXDlRpWBOEoaE8DDaKtrhccmTi6wayGeHFB6V3SCBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T10:41:15.759116Z"},"content_sha256":"409e16f656bda21872a1de31ca1433f5d5ffb9df325995a9d6d93b434028f1f4","schema_version":"1.0","event_id":"sha256:409e16f656bda21872a1de31ca1433f5d5ffb9df325995a9d6d93b434028f1f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:XJKCQFUNOB5CIO5DJEXB6LWASP","target":"graph","payload":{"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"},"verdict_id":"2a223c87-1837-41c9-ab90-842526338d29"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T01:05:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cFZsrBMyh1KEAOYnxLilitQpJj9iOJyhiwAFuu8zetpnuTbScu7YmNSw8FAXXaV29eGRl3k7D+Jwfok8uAWeDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T10:41:15.759655Z"},"content_sha256":"2fcaf93a245ecee586fb765ea9b2abcbcb9bc308c7494455c9a360caa22346ee","schema_version":"1.0","event_id":"sha256:2fcaf93a245ecee586fb765ea9b2abcbcb9bc308c7494455c9a360caa22346ee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XJKCQFUNOB5CIO5DJEXB6LWASP/bundle.json","state_url":"https://pith.science/pith/XJKCQFUNOB5CIO5DJEXB6LWASP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XJKCQFUNOB5CIO5DJEXB6LWASP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-12T10:41:15Z","links":{"resolver":"https://pith.science/pith/XJKCQFUNOB5CIO5DJEXB6LWASP","bundle":"https://pith.science/pith/XJKCQFUNOB5CIO5DJEXB6LWASP/bundle.json","state":"https://pith.science/pith/XJKCQFUNOB5CIO5DJEXB6LWASP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XJKCQFUNOB5CIO5DJEXB6LWASP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XJKCQFUNOB5CIO5DJEXB6LWASP","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":"a25d475a8c8736d531719bc2b874818b43bdeba61a4bc96432f36c6330245e50","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-22T11:07:46Z","title_canon_sha256":"2e57dfb93a3f43f4336b19bb1018e135f22eb1596f1a075b039054fad6ab05ba"},"schema_version":"1.0","source":{"id":"2604.20443","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.20443","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"arxiv_version","alias_value":"2604.20443v2","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.20443","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"pith_short_12","alias_value":"XJKCQFUNOB5C","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"pith_short_16","alias_value":"XJKCQFUNOB5CIO5D","created_at":"2026-05-29T01:05:10Z"},{"alias_kind":"pith_short_8","alias_value":"XJKCQFUN","created_at":"2026-05-29T01:05:10Z"}],"graph_snapshots":[{"event_id":"sha256:2fcaf93a245ecee586fb765ea9b2abcbcb9bc308c7494455c9a360caa22346ee","target":"graph","created_at":"2026-05-29T01:05:10Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The multiple-choice forecasting task and human verification process truly isolate functional use of mental states rather than surface patterns or dataset artifacts."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"LLMs identify mental states in dialogue but mostly fail to forecast how conversations will unfold from those states."}],"snapshot_sha256":"db27c057a6ab35cad11b4953bd0b753ca65b4cf01db87a13a0aae541705eedd1"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2604.20443/integrity.json","findings":[],"snapshot_sha256":"0b11cfeed745d09eb6e11add2546c83246ea7c4c7075a73314cd03e0d93c561f","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ee-Peng Lim, Jing Jiang, Neemesh Yadav, Palakorn Achananuparp","cross_cats":["cs.AI","cs.LG"],"headline":"LLMs identify mental states in dialogue but mostly fail to forecast how conversations will unfold from those states.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-22T11:07:46Z","title":"DialToM: A Theory of Mind Benchmark for Forecasting State-Driven Dialogue Trajectories"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.20443","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T00:08:44.170035Z","id":"2a223c87-1837-41c9-ab90-842526338d29","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"LLMs identify mental states in dialogue but mostly fail to forecast how conversations will unfold from those states.","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.","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."}},"verdict_id":"2a223c87-1837-41c9-ab90-842526338d29"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:409e16f656bda21872a1de31ca1433f5d5ffb9df325995a9d6d93b434028f1f4","target":"record","created_at":"2026-05-29T01:05:10Z","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":"a25d475a8c8736d531719bc2b874818b43bdeba61a4bc96432f36c6330245e50","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-22T11:07:46Z","title_canon_sha256":"2e57dfb93a3f43f4336b19bb1018e135f22eb1596f1a075b039054fad6ab05ba"},"schema_version":"1.0","source":{"id":"2604.20443","kind":"arxiv","version":2}},"canonical_sha256":"ba5428168d707a243ba3492e1f2ec093d67ed54a8bdd7030464ea35c0e606628","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba5428168d707a243ba3492e1f2ec093d67ed54a8bdd7030464ea35c0e606628","first_computed_at":"2026-05-29T01:05:10.263651Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:10.263651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YcyPeCu45pPUhfnZc4AR50KSwI31jUZkx4xrbfMy0ALPnLgeatChl0nVzXJTxBfLie+SqZE67lLQLKkcwP9iCg==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:10.264393Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.20443","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:409e16f656bda21872a1de31ca1433f5d5ffb9df325995a9d6d93b434028f1f4","sha256:2fcaf93a245ecee586fb765ea9b2abcbcb9bc308c7494455c9a360caa22346ee"],"state_sha256":"a366123882d89c4875fd7207ae4270fd5a253cf877d9a31699d783ff497367bb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fyZTs/GiHtUd2ls+VNl9SCyXZt/j/GJe0jYKEonIRot2duYmRcsdtSdiTsbcuaSRp9zAX29JCBSmEAJyoaJMAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T10:41:15.763173Z","bundle_sha256":"2ad89f751feda5643d43071ebff7ce9506a321be8b059eb53754f425ed4c24c6"}}