{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5OOW6IQN2FWMOHAGAMHD3CGZQS","short_pith_number":"pith:5OOW6IQN","schema_version":"1.0","canonical_sha256":"eb9d6f220dd16cc71c06030e3d88d984b213dc5994f94f9ff17284e70a088f28","source":{"kind":"arxiv","id":"2506.03922","version":4},"attestation_state":"computed","paper":{"title":"HSSBench: Benchmarking Humanities and Social Sciences Ability for Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Chaoya Jiang, Huaxuan Ding, Jiaxu Yan, Junhao Gong, Junzhe Chen, Kaidong Yu, Shannan Yan, Siqi He, Wanke Xia, Wei Ye, Wenhao Cao, Xiaomin He, Xuelong Li, Yian Wang, Zhaolu Kang, Zhiyuan Feng, Zhuo Cheng, Ziwen Wang","submitted_at":"2025-06-04T13:14:13Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated significant potential to advance a broad range of domains. However, current benchmarks for evaluating MLLMs primarily emphasize general knowledge and vertical step-by-step reasoning typical of STEM disciplines, while overlooking the distinct needs and potential of the Humanities and Social Sciences (HSS). Tasks in the HSS domain require more horizontal, interdisciplinary thinking and a deep integration of knowledge across related fields, which presents unique challenges for MLLMs, particularly in linking abstract concepts with correspo"},"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":"2506.03922","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T13:14:13Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"9f64b55d660661b61ba9f35966359c4f97bc2361ac4eb4c88f07e649917edb28","abstract_canon_sha256":"1d53c2a525ab34244a5840da9b3f011ce736916f5a4bb3357827f0938ffe121e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-12T01:21:14.060103Z","signature_b64":"Z38pYeNv/QEhijaBgTExwp28adADwoh1FqY9Dwd+iknCaSp06qLcfLP04hx3PlknvjHyXmdj6pg3+BnJqJ0tCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb9d6f220dd16cc71c06030e3d88d984b213dc5994f94f9ff17284e70a088f28","last_reissued_at":"2026-08-12T01:21:14.058247Z","signature_status":"signed_v1","first_computed_at":"2026-08-12T01:21:14.058247Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HSSBench: Benchmarking Humanities and Social Sciences Ability for Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Chaoya Jiang, Huaxuan Ding, Jiaxu Yan, Junhao Gong, Junzhe Chen, Kaidong Yu, Shannan Yan, Siqi He, Wanke Xia, Wei Ye, Wenhao Cao, Xiaomin He, Xuelong Li, Yian Wang, Zhaolu Kang, Zhiyuan Feng, Zhuo Cheng, Ziwen Wang","submitted_at":"2025-06-04T13:14:13Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated significant potential to advance a broad range of domains. However, current benchmarks for evaluating MLLMs primarily emphasize general knowledge and vertical step-by-step reasoning typical of STEM disciplines, while overlooking the distinct needs and potential of the Humanities and Social Sciences (HSS). Tasks in the HSS domain require more horizontal, interdisciplinary thinking and a deep integration of knowledge across related fields, which presents unique challenges for MLLMs, particularly in linking abstract concepts with correspo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03922","kind":"arxiv","version":4},"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/2506.03922/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.03922","created_at":"2026-08-12T01:21:14.062058+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.03922v4","created_at":"2026-08-12T01:21:14.062058+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03922","created_at":"2026-08-12T01:21:14.062058+00:00"},{"alias_kind":"pith_short_12","alias_value":"5OOW6IQN2FWM","created_at":"2026-08-12T01:21:14.062058+00:00"},{"alias_kind":"pith_short_16","alias_value":"5OOW6IQN2FWMOHAG","created_at":"2026-08-12T01:21:14.062058+00:00"},{"alias_kind":"pith_short_8","alias_value":"5OOW6IQN","created_at":"2026-08-12T01:21:14.062058+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":8,"sample":[{"citing_arxiv_id":"2604.22748","citing_title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","ref_index":171,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27826","citing_title":"NormAct: Benchmarking Embodied Agents' Proactive Compliance with Unspoken Social Norms","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23176","citing_title":"DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23176","citing_title":"DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17079","citing_title":"Can LLMs Think Like Consumers? Benchmarking Crowd-Level Reaction Reconstruction with ConsumerSimBench","ref_index":72,"is_internal_anchor":true},{"citing_arxiv_id":"2603.06665","citing_title":"Better Eyes, Better Thoughts: Why Vision Chain-of-Thought Fails in Medicine","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22748","citing_title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","ref_index":171,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04886","citing_title":"BenCSSmark: Making the Social Sciences Count in LLM Research","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5OOW6IQN2FWMOHAGAMHD3CGZQS","json":"https://pith.science/pith/5OOW6IQN2FWMOHAGAMHD3CGZQS.json","graph_json":"https://pith.science/api/pith-number/5OOW6IQN2FWMOHAGAMHD3CGZQS/graph.json","events_json":"https://pith.science/api/pith-number/5OOW6IQN2FWMOHAGAMHD3CGZQS/events.json","paper":"https://pith.science/paper/5OOW6IQN"},"agent_actions":{"view_html":"https://pith.science/pith/5OOW6IQN2FWMOHAGAMHD3CGZQS","download_json":"https://pith.science/pith/5OOW6IQN2FWMOHAGAMHD3CGZQS.json","view_paper":"https://pith.science/paper/5OOW6IQN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.03922&json=true","fetch_graph":"https://pith.science/api/pith-number/5OOW6IQN2FWMOHAGAMHD3CGZQS/graph.json","fetch_events":"https://pith.science/api/pith-number/5OOW6IQN2FWMOHAGAMHD3CGZQS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5OOW6IQN2FWMOHAGAMHD3CGZQS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5OOW6IQN2FWMOHAGAMHD3CGZQS/action/storage_attestation","attest_author":"https://pith.science/pith/5OOW6IQN2FWMOHAGAMHD3CGZQS/action/author_attestation","sign_citation":"https://pith.science/pith/5OOW6IQN2FWMOHAGAMHD3CGZQS/action/citation_signature","submit_replication":"https://pith.science/pith/5OOW6IQN2FWMOHAGAMHD3CGZQS/action/replication_record"}},"created_at":"2026-08-12T01:21:14.062058+00:00","updated_at":"2026-08-12T01:21:14.062058+00:00"}