{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:G6DBARYTQK3QFZJPPSAJMIIDO7","short_pith_number":"pith:G6DBARYT","schema_version":"1.0","canonical_sha256":"378610471382b702e52f7c8096210377c95f699b6018ad5f698462b87e6ee2e4","source":{"kind":"arxiv","id":"2507.04289","version":1},"attestation_state":"computed","paper":{"title":"M$^3$-Med: A Benchmark for Multi-lingual, Multi-modal, and Multi-hop Reasoning in Medical Instructional Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Li, Fuxia Yang, Hongliang Li, Kan Li, Mingyang Zhao, Shenxi Liu, Shoujun Zhou, Yuhang Tian","submitted_at":"2025-07-06T08:14:35Z","abstract_excerpt":"With the rapid progress of artificial intelligence (AI) in multi-modal understanding, there is increasing potential for video comprehension technologies to support professional domains such as medical education. However, existing benchmarks suffer from two primary limitations: (1) Linguistic Singularity: they are largely confined to English, neglecting the need for multilingual resources; and (2) Shallow Reasoning: their questions are often designed for surface-level information retrieval, failing to properly assess deep multi-modal integration. To address these limitations, we present M3-Med,"},"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":"2507.04289","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-06T08:14:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"580d748960f73337b7c9febee486dc872d2210ab4c11dbf903fbdc2f8935ab46","abstract_canon_sha256":"8d345f6171932a1a736f2e7a6e9fc74dae370ab96ff2858997559515d0e03446"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:45.062068Z","signature_b64":"CB/VSf+kTRO3KBxR+19zSbMFdqBtQRRqT7b7BSqQ8oO61i8BtdTctqkRuF9ePYgvN764mImq9Ib2cf/KNBpUAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"378610471382b702e52f7c8096210377c95f699b6018ad5f698462b87e6ee2e4","last_reissued_at":"2026-07-05T11:32:45.061542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:45.061542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M$^3$-Med: A Benchmark for Multi-lingual, Multi-modal, and Multi-hop Reasoning in Medical Instructional Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin Li, Fuxia Yang, Hongliang Li, Kan Li, Mingyang Zhao, Shenxi Liu, Shoujun Zhou, Yuhang Tian","submitted_at":"2025-07-06T08:14:35Z","abstract_excerpt":"With the rapid progress of artificial intelligence (AI) in multi-modal understanding, there is increasing potential for video comprehension technologies to support professional domains such as medical education. However, existing benchmarks suffer from two primary limitations: (1) Linguistic Singularity: they are largely confined to English, neglecting the need for multilingual resources; and (2) Shallow Reasoning: their questions are often designed for surface-level information retrieval, failing to properly assess deep multi-modal integration. To address these limitations, we present M3-Med,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04289","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/2507.04289/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":"2507.04289","created_at":"2026-07-05T11:32:45.061596+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.04289v1","created_at":"2026-07-05T11:32:45.061596+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04289","created_at":"2026-07-05T11:32:45.061596+00:00"},{"alias_kind":"pith_short_12","alias_value":"G6DBARYTQK3Q","created_at":"2026-07-05T11:32:45.061596+00:00"},{"alias_kind":"pith_short_16","alias_value":"G6DBARYTQK3QFZJP","created_at":"2026-07-05T11:32:45.061596+00:00"},{"alias_kind":"pith_short_8","alias_value":"G6DBARYT","created_at":"2026-07-05T11:32:45.061596+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20319","citing_title":"SurgCoT: Advancing Spatiotemporal Reasoning in Surgical Videos through a Chain-of-Thought Benchmark","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G6DBARYTQK3QFZJPPSAJMIIDO7","json":"https://pith.science/pith/G6DBARYTQK3QFZJPPSAJMIIDO7.json","graph_json":"https://pith.science/api/pith-number/G6DBARYTQK3QFZJPPSAJMIIDO7/graph.json","events_json":"https://pith.science/api/pith-number/G6DBARYTQK3QFZJPPSAJMIIDO7/events.json","paper":"https://pith.science/paper/G6DBARYT"},"agent_actions":{"view_html":"https://pith.science/pith/G6DBARYTQK3QFZJPPSAJMIIDO7","download_json":"https://pith.science/pith/G6DBARYTQK3QFZJPPSAJMIIDO7.json","view_paper":"https://pith.science/paper/G6DBARYT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.04289&json=true","fetch_graph":"https://pith.science/api/pith-number/G6DBARYTQK3QFZJPPSAJMIIDO7/graph.json","fetch_events":"https://pith.science/api/pith-number/G6DBARYTQK3QFZJPPSAJMIIDO7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G6DBARYTQK3QFZJPPSAJMIIDO7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G6DBARYTQK3QFZJPPSAJMIIDO7/action/storage_attestation","attest_author":"https://pith.science/pith/G6DBARYTQK3QFZJPPSAJMIIDO7/action/author_attestation","sign_citation":"https://pith.science/pith/G6DBARYTQK3QFZJPPSAJMIIDO7/action/citation_signature","submit_replication":"https://pith.science/pith/G6DBARYTQK3QFZJPPSAJMIIDO7/action/replication_record"}},"created_at":"2026-07-05T11:32:45.061596+00:00","updated_at":"2026-07-05T11:32:45.061596+00:00"}