{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HV2BXJHYEWAK6TKS5UKOQMSLMP","short_pith_number":"pith:HV2BXJHY","schema_version":"1.0","canonical_sha256":"3d741ba4f82580af4d52ed14e8324b63e39dfe23a48314f2743492039b9781d0","source":{"kind":"arxiv","id":"2507.16878","version":1},"attestation_state":"computed","paper":{"title":"CausalStep: A Benchmark for Explicit Stepwise Causal Reasoning in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kaiqi Huang, Shiyu Hu, Wentao Zhang, Xuchen Li, Xuzhao Li","submitted_at":"2025-07-22T12:29:13Z","abstract_excerpt":"Recent advances in large language models (LLMs) have improved reasoning in text and image domains, yet achieving robust video reasoning remains a significant challenge. Existing video benchmarks mainly assess shallow understanding and reasoning and allow models to exploit global context, failing to rigorously evaluate true causal and stepwise reasoning. We present CausalStep, a benchmark designed for explicit stepwise causal reasoning in videos. CausalStep segments videos into causally linked units and enforces a strict stepwise question-answer (QA) protocol, requiring sequential answers and p"},"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":"2507.16878","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-22T12:29:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2fbe7447e01d89607e22e329079028e8ff0a7bb8579fefd77a8e56c2b8c4a570","abstract_canon_sha256":"8f48f7b277cada4d4721ab3f3cdb4c7a21bf3ee748b97e62df0571393e7ae105"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:57.664664Z","signature_b64":"LoaljVUCjosLbc61mFyEaCwCzqAiOAofdvEDCtuwtG7DVVr7NhefpAEDn/DK/Gq5e5Bu2UVUaxcnwT4dbJIbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d741ba4f82580af4d52ed14e8324b63e39dfe23a48314f2743492039b9781d0","last_reissued_at":"2026-07-05T11:41:57.664174Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:57.664174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CausalStep: A Benchmark for Explicit Stepwise Causal Reasoning in Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kaiqi Huang, Shiyu Hu, Wentao Zhang, Xuchen Li, Xuzhao Li","submitted_at":"2025-07-22T12:29:13Z","abstract_excerpt":"Recent advances in large language models (LLMs) have improved reasoning in text and image domains, yet achieving robust video reasoning remains a significant challenge. Existing video benchmarks mainly assess shallow understanding and reasoning and allow models to exploit global context, failing to rigorously evaluate true causal and stepwise reasoning. We present CausalStep, a benchmark designed for explicit stepwise causal reasoning in videos. CausalStep segments videos into causally linked units and enforces a strict stepwise question-answer (QA) protocol, requiring sequential answers and p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.16878","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/2507.16878/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":"2507.16878","created_at":"2026-07-05T11:41:57.664230+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.16878v1","created_at":"2026-07-05T11:41:57.664230+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.16878","created_at":"2026-07-05T11:41:57.664230+00:00"},{"alias_kind":"pith_short_12","alias_value":"HV2BXJHYEWAK","created_at":"2026-07-05T11:41:57.664230+00:00"},{"alias_kind":"pith_short_16","alias_value":"HV2BXJHYEWAK6TKS","created_at":"2026-07-05T11:41:57.664230+00:00"},{"alias_kind":"pith_short_8","alias_value":"HV2BXJHY","created_at":"2026-07-05T11:41:57.664230+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HV2BXJHYEWAK6TKS5UKOQMSLMP","json":"https://pith.science/pith/HV2BXJHYEWAK6TKS5UKOQMSLMP.json","graph_json":"https://pith.science/api/pith-number/HV2BXJHYEWAK6TKS5UKOQMSLMP/graph.json","events_json":"https://pith.science/api/pith-number/HV2BXJHYEWAK6TKS5UKOQMSLMP/events.json","paper":"https://pith.science/paper/HV2BXJHY"},"agent_actions":{"view_html":"https://pith.science/pith/HV2BXJHYEWAK6TKS5UKOQMSLMP","download_json":"https://pith.science/pith/HV2BXJHYEWAK6TKS5UKOQMSLMP.json","view_paper":"https://pith.science/paper/HV2BXJHY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.16878&json=true","fetch_graph":"https://pith.science/api/pith-number/HV2BXJHYEWAK6TKS5UKOQMSLMP/graph.json","fetch_events":"https://pith.science/api/pith-number/HV2BXJHYEWAK6TKS5UKOQMSLMP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HV2BXJHYEWAK6TKS5UKOQMSLMP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HV2BXJHYEWAK6TKS5UKOQMSLMP/action/storage_attestation","attest_author":"https://pith.science/pith/HV2BXJHYEWAK6TKS5UKOQMSLMP/action/author_attestation","sign_citation":"https://pith.science/pith/HV2BXJHYEWAK6TKS5UKOQMSLMP/action/citation_signature","submit_replication":"https://pith.science/pith/HV2BXJHYEWAK6TKS5UKOQMSLMP/action/replication_record"}},"created_at":"2026-07-05T11:41:57.664230+00:00","updated_at":"2026-07-05T11:41:57.664230+00:00"}