{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IBG7XPTFQGHLPPR45SRE2PDNVA","short_pith_number":"pith:IBG7XPTF","canonical_record":{"source":{"id":"2504.10839","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.HC","submitted_at":"2025-04-15T03:44:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"855723536812f9fca8dc5a753c8f24d6e8c7c3f989e16e1169164f771035b905","abstract_canon_sha256":"c91d42d368af1e03312a7e55054302bafc359936fc08c3f27b77db6e68799fa1"},"schema_version":"1.0"},"canonical_sha256":"404dfbbe65818eb7be3ceca24d3c6da80358a0dbc1c26a6f7ef3eb8d47e3314b","source":{"kind":"arxiv","id":"2504.10839","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.10839","created_at":"2026-07-05T10:49:24Z"},{"alias_kind":"arxiv_version","alias_value":"2504.10839v1","created_at":"2026-07-05T10:49:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.10839","created_at":"2026-07-05T10:49:24Z"},{"alias_kind":"pith_short_12","alias_value":"IBG7XPTFQGHL","created_at":"2026-07-05T10:49:24Z"},{"alias_kind":"pith_short_16","alias_value":"IBG7XPTFQGHLPPR4","created_at":"2026-07-05T10:49:24Z"},{"alias_kind":"pith_short_8","alias_value":"IBG7XPTF","created_at":"2026-07-05T10:49:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IBG7XPTFQGHLPPR45SRE2PDNVA","target":"record","payload":{"canonical_record":{"source":{"id":"2504.10839","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.HC","submitted_at":"2025-04-15T03:44:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"855723536812f9fca8dc5a753c8f24d6e8c7c3f989e16e1169164f771035b905","abstract_canon_sha256":"c91d42d368af1e03312a7e55054302bafc359936fc08c3f27b77db6e68799fa1"},"schema_version":"1.0"},"canonical_sha256":"404dfbbe65818eb7be3ceca24d3c6da80358a0dbc1c26a6f7ef3eb8d47e3314b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:24.999833Z","signature_b64":"t1ZnpqFFo+z0laK7cjfmw2Bw5Jmjuy/xOjgk470L7b3DcRktEs/c6fH1SeMPAZIH4/aof6cY4q4xNf0RbX1vDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"404dfbbe65818eb7be3ceca24d3c6da80358a0dbc1c26a6f7ef3eb8d47e3314b","last_reissued_at":"2026-07-05T10:49:24.999378Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:24.999378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.10839","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:49:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MRKtINUue50oCi/k1RN3NvidurONdT3XKWDjGmyRuNRR/agYvO1Nl7I1UUH5p11fjx9YoBJQWLhSqLrd78LmDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:37:29.326227Z"},"content_sha256":"7d9ff29428ac99445f75278cf3046269b96da33d3afc5258b6a246f3a635832f","schema_version":"1.0","event_id":"sha256:7d9ff29428ac99445f75278cf3046269b96da33d3afc5258b6a246f3a635832f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IBG7XPTFQGHLPPR45SRE2PDNVA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking Theory of Mind Benchmarks for LLMs: Towards A User-Centered Perspective","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Hong Shen, Jodi Forlizzi, Maarten Sap, Qiaosi Wang, Xuhui Zhou","submitted_at":"2025-04-15T03:44:43Z","abstract_excerpt":"The last couple of years have witnessed emerging research that appropriates Theory-of-Mind (ToM) tasks designed for humans to benchmark LLM's ToM capabilities as an indication of LLM's social intelligence. However, this approach has a number of limitations. Drawing on existing psychology and AI literature, we summarize the theoretical, methodological, and evaluation limitations by pointing out that certain issues are inherently present in the original ToM tasks used to evaluate human's ToM, which continues to persist and exacerbated when appropriated to benchmark LLM's ToM. Taking a human-comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.10839","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.10839/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:49:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"19LumrPdDOK8uAArlkbQ3CwI+CADHznYOApIK14a86QFE7ythjvnzWixk+H00d1EOgxLb3BcXcuBBH9ErMIFCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:37:29.326762Z"},"content_sha256":"613e57fb4eb3fcfee196133dadf256c506d253d6c3bbe6d8dcef72d6ea7db3f9","schema_version":"1.0","event_id":"sha256:613e57fb4eb3fcfee196133dadf256c506d253d6c3bbe6d8dcef72d6ea7db3f9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IBG7XPTFQGHLPPR45SRE2PDNVA/bundle.json","state_url":"https://pith.science/pith/IBG7XPTFQGHLPPR45SRE2PDNVA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IBG7XPTFQGHLPPR45SRE2PDNVA/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":"2026-08-09T08:37:29Z","links":{"resolver":"https://pith.science/pith/IBG7XPTFQGHLPPR45SRE2PDNVA","bundle":"https://pith.science/pith/IBG7XPTFQGHLPPR45SRE2PDNVA/bundle.json","state":"https://pith.science/pith/IBG7XPTFQGHLPPR45SRE2PDNVA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IBG7XPTFQGHLPPR45SRE2PDNVA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IBG7XPTFQGHLPPR45SRE2PDNVA","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":"c91d42d368af1e03312a7e55054302bafc359936fc08c3f27b77db6e68799fa1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.HC","submitted_at":"2025-04-15T03:44:43Z","title_canon_sha256":"855723536812f9fca8dc5a753c8f24d6e8c7c3f989e16e1169164f771035b905"},"schema_version":"1.0","source":{"id":"2504.10839","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.10839","created_at":"2026-07-05T10:49:24Z"},{"alias_kind":"arxiv_version","alias_value":"2504.10839v1","created_at":"2026-07-05T10:49:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.10839","created_at":"2026-07-05T10:49:24Z"},{"alias_kind":"pith_short_12","alias_value":"IBG7XPTFQGHL","created_at":"2026-07-05T10:49:24Z"},{"alias_kind":"pith_short_16","alias_value":"IBG7XPTFQGHLPPR4","created_at":"2026-07-05T10:49:24Z"},{"alias_kind":"pith_short_8","alias_value":"IBG7XPTF","created_at":"2026-07-05T10:49:24Z"}],"graph_snapshots":[{"event_id":"sha256:613e57fb4eb3fcfee196133dadf256c506d253d6c3bbe6d8dcef72d6ea7db3f9","target":"graph","created_at":"2026-07-05T10:49:24Z","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/2504.10839/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The last couple of years have witnessed emerging research that appropriates Theory-of-Mind (ToM) tasks designed for humans to benchmark LLM's ToM capabilities as an indication of LLM's social intelligence. However, this approach has a number of limitations. Drawing on existing psychology and AI literature, we summarize the theoretical, methodological, and evaluation limitations by pointing out that certain issues are inherently present in the original ToM tasks used to evaluate human's ToM, which continues to persist and exacerbated when appropriated to benchmark LLM's ToM. Taking a human-comp","authors_text":"Hong Shen, Jodi Forlizzi, Maarten Sap, Qiaosi Wang, Xuhui Zhou","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.HC","submitted_at":"2025-04-15T03:44:43Z","title":"Rethinking Theory of Mind Benchmarks for LLMs: Towards A User-Centered Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.10839","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":"sha256:7d9ff29428ac99445f75278cf3046269b96da33d3afc5258b6a246f3a635832f","target":"record","created_at":"2026-07-05T10:49:24Z","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":"c91d42d368af1e03312a7e55054302bafc359936fc08c3f27b77db6e68799fa1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.HC","submitted_at":"2025-04-15T03:44:43Z","title_canon_sha256":"855723536812f9fca8dc5a753c8f24d6e8c7c3f989e16e1169164f771035b905"},"schema_version":"1.0","source":{"id":"2504.10839","kind":"arxiv","version":1}},"canonical_sha256":"404dfbbe65818eb7be3ceca24d3c6da80358a0dbc1c26a6f7ef3eb8d47e3314b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"404dfbbe65818eb7be3ceca24d3c6da80358a0dbc1c26a6f7ef3eb8d47e3314b","first_computed_at":"2026-07-05T10:49:24.999378Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:49:24.999378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t1ZnpqFFo+z0laK7cjfmw2Bw5Jmjuy/xOjgk470L7b3DcRktEs/c6fH1SeMPAZIH4/aof6cY4q4xNf0RbX1vDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:49:24.999833Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.10839","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d9ff29428ac99445f75278cf3046269b96da33d3afc5258b6a246f3a635832f","sha256:613e57fb4eb3fcfee196133dadf256c506d253d6c3bbe6d8dcef72d6ea7db3f9"],"state_sha256":"9826e2d5111c8fa6957baefea2dc477caa8f29c5a0aac30a5ca045b9bbb397e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z70LrTdsZfif1Qk3BY3ySLnmv/62km4Vz9V9HHwcrLNQV6OgQjrnz2MyS562hVSPH/lN0GPw20rlzdvuW2i7Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T08:37:29.332080Z","bundle_sha256":"c7a286ed7759ccf4d717316bf7f4c79aa36241e300a4dfc3b6de7d1f3cadc620"}}