{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OVF7F5YV74QB2FASUYZOJQVHO6","short_pith_number":"pith:OVF7F5YV","canonical_record":{"source":{"id":"2605.23216","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-22T04:19:29Z","cross_cats_sorted":[],"title_canon_sha256":"6929072ca497faa409d2065cdfc0347d6048d21962cd8426140568a5728ef5be","abstract_canon_sha256":"dfb265774476edbb104dd03996793482c8ecf6fe41b0ab670182ec52bf96e8f6"},"schema_version":"1.0"},"canonical_sha256":"754bf2f715ff201d1412a632e4c2a7778a211ff7f18a48c16f61ae7607bf7e5b","source":{"kind":"arxiv","id":"2605.23216","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23216","created_at":"2026-05-25T02:01:44Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23216v1","created_at":"2026-05-25T02:01:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23216","created_at":"2026-05-25T02:01:44Z"},{"alias_kind":"pith_short_12","alias_value":"OVF7F5YV74QB","created_at":"2026-05-25T02:01:44Z"},{"alias_kind":"pith_short_16","alias_value":"OVF7F5YV74QB2FAS","created_at":"2026-05-25T02:01:44Z"},{"alias_kind":"pith_short_8","alias_value":"OVF7F5YV","created_at":"2026-05-25T02:01:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OVF7F5YV74QB2FASUYZOJQVHO6","target":"record","payload":{"canonical_record":{"source":{"id":"2605.23216","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-22T04:19:29Z","cross_cats_sorted":[],"title_canon_sha256":"6929072ca497faa409d2065cdfc0347d6048d21962cd8426140568a5728ef5be","abstract_canon_sha256":"dfb265774476edbb104dd03996793482c8ecf6fe41b0ab670182ec52bf96e8f6"},"schema_version":"1.0"},"canonical_sha256":"754bf2f715ff201d1412a632e4c2a7778a211ff7f18a48c16f61ae7607bf7e5b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:44.074410Z","signature_b64":"oR/G1QPyWR+qQZXctgyiTcxtC88FfLYnc0MzuOn4torxXTma5jyRPBiT/8uIA/9Y3xGqrKhnTridDBqNH6ojCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"754bf2f715ff201d1412a632e4c2a7778a211ff7f18a48c16f61ae7607bf7e5b","last_reissued_at":"2026-05-25T02:01:44.073778Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:44.073778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.23216","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":"2026-05-25T02:01:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mA3xnGXoOYHj6VViibsWZJba+mEJQryXmViEBWbDvWQ8SDj8RW5+0d24lbTamS7SiXdAHKPzbgnxoMEkpRKDCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T08:30:58.332288Z"},"content_sha256":"bffd63018dcdc00d706d3e14b12702c6a404aca3e4368d6b2d07cc506c55edd4","schema_version":"1.0","event_id":"sha256:bffd63018dcdc00d706d3e14b12702c6a404aca3e4368d6b2d07cc506c55edd4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OVF7F5YV74QB2FASUYZOJQVHO6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ashutosh Kumar, Caixin Kang, Hsuan-Kung Yang, Jingjing Pan, Mingfang Zhang, Mustafa Erdogan, Quan Kong, Rajat Saini, Yifei Huang, Yoichi Sato","submitted_at":"2026-05-22T04:19:29Z","abstract_excerpt":"Cause-and-effect reasoning in video is a significant challenge for Vision-Language Models (VLMs), as it requires going beyond surface-level perception to a deeper understanding of causal mechanisms. However, existing benchmarks rarely provide the fine-grained, grounded evidence needed to rigorously evaluate this capability. To address this gap, we introduce CaST-Bench, a benchmark for Causal Chain-Grounded Spatio-Temporal Video Reasoning. CaST-Bench presents complex causal questions that require models to identify and localize a chain of multiple spatio-temporal evidences. Through a human-AI c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23216","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/2605.23216/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":"2026-05-25T02:01:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6C14iwpBbSLEEQGU0xY7Ch3r87JNMDQXlL1vQFX6sh+oHiAC64nx5z8TJG/HB4i+RKgCFRE/y4kvLWoYVtZwDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T08:30:58.332998Z"},"content_sha256":"434e7685fa732248d7c5158e35c892ac64879754bd2dafbd37ea8f6bd15af5e8","schema_version":"1.0","event_id":"sha256:434e7685fa732248d7c5158e35c892ac64879754bd2dafbd37ea8f6bd15af5e8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OVF7F5YV74QB2FASUYZOJQVHO6/bundle.json","state_url":"https://pith.science/pith/OVF7F5YV74QB2FASUYZOJQVHO6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OVF7F5YV74QB2FASUYZOJQVHO6/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":"2026-05-26T08:30:58Z","links":{"resolver":"https://pith.science/pith/OVF7F5YV74QB2FASUYZOJQVHO6","bundle":"https://pith.science/pith/OVF7F5YV74QB2FASUYZOJQVHO6/bundle.json","state":"https://pith.science/pith/OVF7F5YV74QB2FASUYZOJQVHO6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OVF7F5YV74QB2FASUYZOJQVHO6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OVF7F5YV74QB2FASUYZOJQVHO6","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":"dfb265774476edbb104dd03996793482c8ecf6fe41b0ab670182ec52bf96e8f6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-22T04:19:29Z","title_canon_sha256":"6929072ca497faa409d2065cdfc0347d6048d21962cd8426140568a5728ef5be"},"schema_version":"1.0","source":{"id":"2605.23216","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23216","created_at":"2026-05-25T02:01:44Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23216v1","created_at":"2026-05-25T02:01:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23216","created_at":"2026-05-25T02:01:44Z"},{"alias_kind":"pith_short_12","alias_value":"OVF7F5YV74QB","created_at":"2026-05-25T02:01:44Z"},{"alias_kind":"pith_short_16","alias_value":"OVF7F5YV74QB2FAS","created_at":"2026-05-25T02:01:44Z"},{"alias_kind":"pith_short_8","alias_value":"OVF7F5YV","created_at":"2026-05-25T02:01:44Z"}],"graph_snapshots":[{"event_id":"sha256:434e7685fa732248d7c5158e35c892ac64879754bd2dafbd37ea8f6bd15af5e8","target":"graph","created_at":"2026-05-25T02:01:44Z","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/2605.23216/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cause-and-effect reasoning in video is a significant challenge for Vision-Language Models (VLMs), as it requires going beyond surface-level perception to a deeper understanding of causal mechanisms. However, existing benchmarks rarely provide the fine-grained, grounded evidence needed to rigorously evaluate this capability. To address this gap, we introduce CaST-Bench, a benchmark for Causal Chain-Grounded Spatio-Temporal Video Reasoning. CaST-Bench presents complex causal questions that require models to identify and localize a chain of multiple spatio-temporal evidences. Through a human-AI c","authors_text":"Ashutosh Kumar, Caixin Kang, Hsuan-Kung Yang, Jingjing Pan, Mingfang Zhang, Mustafa Erdogan, Quan Kong, Rajat Saini, Yifei Huang, Yoichi Sato","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-22T04:19:29Z","title":"CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23216","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:bffd63018dcdc00d706d3e14b12702c6a404aca3e4368d6b2d07cc506c55edd4","target":"record","created_at":"2026-05-25T02:01:44Z","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":"dfb265774476edbb104dd03996793482c8ecf6fe41b0ab670182ec52bf96e8f6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-22T04:19:29Z","title_canon_sha256":"6929072ca497faa409d2065cdfc0347d6048d21962cd8426140568a5728ef5be"},"schema_version":"1.0","source":{"id":"2605.23216","kind":"arxiv","version":1}},"canonical_sha256":"754bf2f715ff201d1412a632e4c2a7778a211ff7f18a48c16f61ae7607bf7e5b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"754bf2f715ff201d1412a632e4c2a7778a211ff7f18a48c16f61ae7607bf7e5b","first_computed_at":"2026-05-25T02:01:44.073778Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:44.073778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oR/G1QPyWR+qQZXctgyiTcxtC88FfLYnc0MzuOn4torxXTma5jyRPBiT/8uIA/9Y3xGqrKhnTridDBqNH6ojCg==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:44.074410Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.23216","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bffd63018dcdc00d706d3e14b12702c6a404aca3e4368d6b2d07cc506c55edd4","sha256:434e7685fa732248d7c5158e35c892ac64879754bd2dafbd37ea8f6bd15af5e8"],"state_sha256":"7bfd4c7564f81cbf53fab45a0d5dad897b4a9aaeb6a87b0b86b79e52b00941e6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dKnodhJ2GRUSAXExF1CGQvoFyWc9daI9gHLdezPraPjbjCY+4+xYwKN+BAx0CbrFtUyGW87rxqR1od/B70vdAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T08:30:58.335759Z","bundle_sha256":"16f836881ef927252e17d04dfc47f45076264cf83d0fb9ebd87bc108f4cf0beb"}}