{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WWDXHIOLQBLOQBDDYMWOMFLJDM","short_pith_number":"pith:WWDXHIOL","schema_version":"1.0","canonical_sha256":"b58773a1cb8056e80463c32ce615691b04810c779968b2c61435ee519d50585e","source":{"kind":"arxiv","id":"2605.27101","version":1},"attestation_state":"computed","paper":{"title":"Pop-Up Distractions Reveal Bag-of-Events Behavior in Video Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Dishant Zaveri, Khoa D. Doan, Kuan-Hao Huang, Oscar Chew, Patricia Lu, Qian-Hui Chen, Serhii Honcharenko","submitted_at":"2026-05-26T14:41:05Z","abstract_excerpt":"A key capability for video understanding is reliably linking subjects to events across time, yet whether Video Large Language Models (VideoLLMs) actually achieve this remains unclear. In this work, we introduce DistractionBench to evaluate whether VideoLLMs can robustly link subjects and events in the presence of unrelated video segments. Through controlled interventions, such as inserting short advertisement clips into longer videos, we show that VideoLLMs frequently hallucinate interactions between entities from different segments, incorrectly attributing actions from injected advertisements"},"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":"2605.27101","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T14:41:05Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7344ea186acb112d037d92a4d7a6e9d7191a44ae4bef15aeb7aed10f6863f057","abstract_canon_sha256":"6a5fb2dc2815926f1d9d831d85321d5185ace08cab2272e7acb21552c906b768"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T02:05:41.791232Z","signature_b64":"uOJG9LdVBY7Ad7djb6im8doOFYh4LCTkKTPSo6fI5bIMKYYeNVOrc4nJp9GHcMviwpLFOTiBTVjJ1iujX29bDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b58773a1cb8056e80463c32ce615691b04810c779968b2c61435ee519d50585e","last_reissued_at":"2026-05-27T02:05:41.790594Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T02:05:41.790594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pop-Up Distractions Reveal Bag-of-Events Behavior in Video Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Dishant Zaveri, Khoa D. Doan, Kuan-Hao Huang, Oscar Chew, Patricia Lu, Qian-Hui Chen, Serhii Honcharenko","submitted_at":"2026-05-26T14:41:05Z","abstract_excerpt":"A key capability for video understanding is reliably linking subjects to events across time, yet whether Video Large Language Models (VideoLLMs) actually achieve this remains unclear. In this work, we introduce DistractionBench to evaluate whether VideoLLMs can robustly link subjects and events in the presence of unrelated video segments. Through controlled interventions, such as inserting short advertisement clips into longer videos, we show that VideoLLMs frequently hallucinate interactions between entities from different segments, incorrectly attributing actions from injected advertisements"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27101","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/2605.27101/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":"2605.27101","created_at":"2026-05-27T02:05:41.790720+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27101v1","created_at":"2026-05-27T02:05:41.790720+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27101","created_at":"2026-05-27T02:05:41.790720+00:00"},{"alias_kind":"pith_short_12","alias_value":"WWDXHIOLQBLO","created_at":"2026-05-27T02:05:41.790720+00:00"},{"alias_kind":"pith_short_16","alias_value":"WWDXHIOLQBLOQBDD","created_at":"2026-05-27T02:05:41.790720+00:00"},{"alias_kind":"pith_short_8","alias_value":"WWDXHIOL","created_at":"2026-05-27T02:05:41.790720+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/WWDXHIOLQBLOQBDDYMWOMFLJDM","json":"https://pith.science/pith/WWDXHIOLQBLOQBDDYMWOMFLJDM.json","graph_json":"https://pith.science/api/pith-number/WWDXHIOLQBLOQBDDYMWOMFLJDM/graph.json","events_json":"https://pith.science/api/pith-number/WWDXHIOLQBLOQBDDYMWOMFLJDM/events.json","paper":"https://pith.science/paper/WWDXHIOL"},"agent_actions":{"view_html":"https://pith.science/pith/WWDXHIOLQBLOQBDDYMWOMFLJDM","download_json":"https://pith.science/pith/WWDXHIOLQBLOQBDDYMWOMFLJDM.json","view_paper":"https://pith.science/paper/WWDXHIOL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27101&json=true","fetch_graph":"https://pith.science/api/pith-number/WWDXHIOLQBLOQBDDYMWOMFLJDM/graph.json","fetch_events":"https://pith.science/api/pith-number/WWDXHIOLQBLOQBDDYMWOMFLJDM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WWDXHIOLQBLOQBDDYMWOMFLJDM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WWDXHIOLQBLOQBDDYMWOMFLJDM/action/storage_attestation","attest_author":"https://pith.science/pith/WWDXHIOLQBLOQBDDYMWOMFLJDM/action/author_attestation","sign_citation":"https://pith.science/pith/WWDXHIOLQBLOQBDDYMWOMFLJDM/action/citation_signature","submit_replication":"https://pith.science/pith/WWDXHIOLQBLOQBDDYMWOMFLJDM/action/replication_record"}},"created_at":"2026-05-27T02:05:41.790720+00:00","updated_at":"2026-05-27T02:05:41.790720+00:00"}