{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YNQJL4CMKFECWAPFYQ6KXDPJKD","short_pith_number":"pith:YNQJL4CM","schema_version":"1.0","canonical_sha256":"c36095f04c51482b01e5c43cab8de950e4981d45e47e73177019011181475703","source":{"kind":"arxiv","id":"2603.27259","version":3},"attestation_state":"computed","paper":{"title":"Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmark","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Vision-language models forget long-range scene context in videos, shown by a new benchmark with sharp accuracy drops.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Li, Chenglam Ho, Hao Chen, Jinping Wang, Seng Nam Chen, Xinyu Mao, Yu Zhang","submitted_at":"2026-03-28T12:44:19Z","abstract_excerpt":"Long video understanding (LVU) remains a core challenge in multimodal learning. Although recent vision-language models (VLMs) have made notable progress, existing benchmarks mainly focus on either fine-grained perception or coarse summarization, offering limited insight into temporal understanding over long contexts. In this work, we define a scene as a coherent segment of a video in which both visual and semantic contexts remain consistent, aligning with human perception. This leads us to a key question: can current VLMs reason effectively over long, scene-level contexts? To answer this, we i"},"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":"2603.27259","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-28T12:44:19Z","cross_cats_sorted":[],"title_canon_sha256":"3ca3f6151f7d08480faf12c4676262d71303d8b81b2330b5e919c0d9e9c76115","abstract_canon_sha256":"9b4a89f2c7c43f0f960d61d77cc48477fdefe91ef8f2eef88e3cedeea7cb2d5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:04.172903Z","signature_b64":"8k4ZkCt1i8+XYIIPBYoH/TNr3+dSLXpcVEyfTWh7IajitPqBDneuBJbaKMLfzR2HnIJ/Km3ViJD2ArX5c4UODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c36095f04c51482b01e5c43cab8de950e4981d45e47e73177019011181475703","last_reissued_at":"2026-06-23T01:12:04.172364Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:04.172364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmark","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Vision-language models forget long-range scene context in videos, shown by a new benchmark with sharp accuracy drops.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Li, Chenglam Ho, Hao Chen, Jinping Wang, Seng Nam Chen, Xinyu Mao, Yu Zhang","submitted_at":"2026-03-28T12:44:19Z","abstract_excerpt":"Long video understanding (LVU) remains a core challenge in multimodal learning. Although recent vision-language models (VLMs) have made notable progress, existing benchmarks mainly focus on either fine-grained perception or coarse summarization, offering limited insight into temporal understanding over long contexts. In this work, we define a scene as a coherent segment of a video in which both visual and semantic contexts remain consistent, aligning with human perception. This leads us to a key question: can current VLMs reason effectively over long, scene-level contexts? To answer this, we i"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our evaluation reveals a sharp drop in accuracy when VLMs attempt to answer scene-level questions, indicating significant forgetting of long-range context.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the authors' definition of a scene as a coherent segment with consistent visual and semantic contexts accurately isolates long-range forgetting, and that the benchmark questions do not introduce other confounds in video selection or question design.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SceneBench shows VLMs lose accuracy on scene-level questions in long videos due to forgetting, and Scene-RAG retrieval improves performance by 2.5%.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Vision-language models forget long-range scene context in videos, shown by a new benchmark with sharp accuracy drops.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a917d5f8448758645675e74b0e4a912d18ccb4bfee6a590719933b28662f355d"},"source":{"id":"2603.27259","kind":"arxiv","version":3},"verdict":{"id":"b363ad80-56a4-4b57-bcbe-4a1a8a10ddcb","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T22:02:10.306737Z","strongest_claim":"Our evaluation reveals a sharp drop in accuracy when VLMs attempt to answer scene-level questions, indicating significant forgetting of long-range context.","one_line_summary":"SceneBench shows VLMs lose accuracy on scene-level questions in long videos due to forgetting, and Scene-RAG retrieval improves performance by 2.5%.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the authors' definition of a scene as a coherent segment with consistent visual and semantic contexts accurately isolates long-range forgetting, and that the benchmark questions do not introduce other confounds in video selection or question design.","pith_extraction_headline":"Vision-language models forget long-range scene context in videos, shown by a new benchmark with sharp accuracy drops."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.27259/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":"2603.27259","created_at":"2026-06-23T01:12:04.172449+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.27259v3","created_at":"2026-06-23T01:12:04.172449+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.27259","created_at":"2026-06-23T01:12:04.172449+00:00"},{"alias_kind":"pith_short_12","alias_value":"YNQJL4CMKFEC","created_at":"2026-06-23T01:12:04.172449+00:00"},{"alias_kind":"pith_short_16","alias_value":"YNQJL4CMKFECWAPF","created_at":"2026-06-23T01:12:04.172449+00:00"},{"alias_kind":"pith_short_8","alias_value":"YNQJL4CM","created_at":"2026-06-23T01:12:04.172449+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/YNQJL4CMKFECWAPFYQ6KXDPJKD","json":"https://pith.science/pith/YNQJL4CMKFECWAPFYQ6KXDPJKD.json","graph_json":"https://pith.science/api/pith-number/YNQJL4CMKFECWAPFYQ6KXDPJKD/graph.json","events_json":"https://pith.science/api/pith-number/YNQJL4CMKFECWAPFYQ6KXDPJKD/events.json","paper":"https://pith.science/paper/YNQJL4CM"},"agent_actions":{"view_html":"https://pith.science/pith/YNQJL4CMKFECWAPFYQ6KXDPJKD","download_json":"https://pith.science/pith/YNQJL4CMKFECWAPFYQ6KXDPJKD.json","view_paper":"https://pith.science/paper/YNQJL4CM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.27259&json=true","fetch_graph":"https://pith.science/api/pith-number/YNQJL4CMKFECWAPFYQ6KXDPJKD/graph.json","fetch_events":"https://pith.science/api/pith-number/YNQJL4CMKFECWAPFYQ6KXDPJKD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YNQJL4CMKFECWAPFYQ6KXDPJKD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YNQJL4CMKFECWAPFYQ6KXDPJKD/action/storage_attestation","attest_author":"https://pith.science/pith/YNQJL4CMKFECWAPFYQ6KXDPJKD/action/author_attestation","sign_citation":"https://pith.science/pith/YNQJL4CMKFECWAPFYQ6KXDPJKD/action/citation_signature","submit_replication":"https://pith.science/pith/YNQJL4CMKFECWAPFYQ6KXDPJKD/action/replication_record"}},"created_at":"2026-06-23T01:12:04.172449+00:00","updated_at":"2026-06-23T01:12:04.172449+00:00"}