{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XSR2IGQPMAG64RPRDPJ327S2MG","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":"41c3b3f4e8645138c9a9a2f21cd280077aba08dbd27995614a497f6c54a5ff38","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-21T01:10:42Z","title_canon_sha256":"54e580ab94643ee80e74c122b1ba74638074ba5c56601496914214463b038514"},"schema_version":"1.0","source":{"id":"2601.14569","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.14569","created_at":"2026-06-03T01:05:09Z"},{"alias_kind":"arxiv_version","alias_value":"2601.14569v2","created_at":"2026-06-03T01:05:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.14569","created_at":"2026-06-03T01:05:09Z"},{"alias_kind":"pith_short_12","alias_value":"XSR2IGQPMAG6","created_at":"2026-06-03T01:05:09Z"},{"alias_kind":"pith_short_16","alias_value":"XSR2IGQPMAG64RPR","created_at":"2026-06-03T01:05:09Z"},{"alias_kind":"pith_short_8","alias_value":"XSR2IGQP","created_at":"2026-06-03T01:05:09Z"}],"graph_snapshots":[{"event_id":"sha256:3b629c9ca49d1cd4c5556ac6f0d37610339d085e5fd40fe90794d43b443b13de","target":"graph","created_at":"2026-06-03T01:05:09Z","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/2601.14569/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Social understanding abilities are crucial for multimodal large language models (MLLMs) to interpret human social interactions. We introduce SOCIAL CAPTION, a framework grounded in interaction theory to evaluate social understanding abilities of MLLMs along three dimensions: Social Inference (SI), the ability to make accurate inferences about interactions; Holistic Social Analysis (HSA), the ability to generate comprehensive descriptions of interactions; Directed Social Analysis (DSA), the ability to generate relevant information from interactions. We analyze factors influencing model performa","authors_text":"Bhaavanaa Thumu, Leena Mathur, Louis-Philippe Morency, Youssouf Kebe","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-21T01:10:42Z","title":"Social Caption: Evaluating Social Understanding in Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.14569","kind":"arxiv","version":2},"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:c0b8e7caaedfbdaf3b32757c0df73d8b27e49c0fb14fb9a560e9eac0e359b7e4","target":"record","created_at":"2026-06-03T01:05:09Z","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":"41c3b3f4e8645138c9a9a2f21cd280077aba08dbd27995614a497f6c54a5ff38","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-01-21T01:10:42Z","title_canon_sha256":"54e580ab94643ee80e74c122b1ba74638074ba5c56601496914214463b038514"},"schema_version":"1.0","source":{"id":"2601.14569","kind":"arxiv","version":2}},"canonical_sha256":"bca3a41a0f600dee45f11bd3bd7e5a61b1630e64c8dced2254b97cbb947a787a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bca3a41a0f600dee45f11bd3bd7e5a61b1630e64c8dced2254b97cbb947a787a","first_computed_at":"2026-06-03T01:05:09.291226Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:09.291226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wSkdSw3QeDe4U6S6nNLMwVZQy99veWzUTT20MbIFl7sVdZjNzFkHoC7faGLpJM4bLKpYB+I4dSFcS/OFtX6WCA==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:09.291737Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.14569","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0b8e7caaedfbdaf3b32757c0df73d8b27e49c0fb14fb9a560e9eac0e359b7e4","sha256:3b629c9ca49d1cd4c5556ac6f0d37610339d085e5fd40fe90794d43b443b13de"],"state_sha256":"4a79516372ef3629d292b15fa7f2eda975193819faca1da642f001d5f3e31f8a"}