{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ARIN6D55IUSPYA7NRVA75GPMMK","short_pith_number":"pith:ARIN6D55","schema_version":"1.0","canonical_sha256":"0450df0fbd4524fc03ed8d41fe99ec62a39053da89101a6e819607b75ebdb787","source":{"kind":"arxiv","id":"2509.24563","version":3},"attestation_state":"computed","paper":{"title":"NeMo: Needle in a Montage for Video-Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Duo Zheng, Jianguang Yu, Jia Qin, Jing Huang, Liwei Wang, Meng Fang, Shijia Huang, Shuo Liang, Wei Feng, Yanyang Li, Yeyao Tao, Yin Li, Zi-Yuan Hu","submitted_at":"2025-09-29T10:16:05Z","abstract_excerpt":"Recent advances in video large language models (VideoLLMs) call for new evaluation protocols and benchmarks for video-language understanding. Inspired by the needle in a haystack test widely used by LLMs, we introduce a novel task of Needle in a Montage (NeMo), which is designed to assess the temporal understanding capabilities of advanced VideoLLMs. Specifically, the proposed task focuses on two fundamental abilities critical for temporal understanding, i.e., retrieval-style long-context recall and temporal grounding. To generate video question answering data for our task, we develop a scalab"},"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":"2509.24563","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-29T10:16:05Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f450e4edffc03fbd68ee2c545a576fc28a984d56eb697e471620c1bb4971c032","abstract_canon_sha256":"fc3462b704dbad06314a84784522d3f234af5554b070ec168b50a12e7eb18fa3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T01:22:28.477564Z","signature_b64":"RiuIjrhRNULsaZWDsF0IIL/aVuIg24aGXwwsXDWWMHDE8aWeAsvmOAqTWsXnzrP1hoJn4BCP+Z2mlZhG/+L2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0450df0fbd4524fc03ed8d41fe99ec62a39053da89101a6e819607b75ebdb787","last_reissued_at":"2026-07-16T01:22:28.476662Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T01:22:28.476662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NeMo: Needle in a Montage for Video-Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Duo Zheng, Jianguang Yu, Jia Qin, Jing Huang, Liwei Wang, Meng Fang, Shijia Huang, Shuo Liang, Wei Feng, Yanyang Li, Yeyao Tao, Yin Li, Zi-Yuan Hu","submitted_at":"2025-09-29T10:16:05Z","abstract_excerpt":"Recent advances in video large language models (VideoLLMs) call for new evaluation protocols and benchmarks for video-language understanding. Inspired by the needle in a haystack test widely used by LLMs, we introduce a novel task of Needle in a Montage (NeMo), which is designed to assess the temporal understanding capabilities of advanced VideoLLMs. Specifically, the proposed task focuses on two fundamental abilities critical for temporal understanding, i.e., retrieval-style long-context recall and temporal grounding. To generate video question answering data for our task, we develop a scalab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.24563","kind":"arxiv","version":3},"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/2509.24563/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":"2509.24563","created_at":"2026-07-16T01:22:28.477092+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.24563v3","created_at":"2026-07-16T01:22:28.477092+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.24563","created_at":"2026-07-16T01:22:28.477092+00:00"},{"alias_kind":"pith_short_12","alias_value":"ARIN6D55IUSP","created_at":"2026-07-16T01:22:28.477092+00:00"},{"alias_kind":"pith_short_16","alias_value":"ARIN6D55IUSPYA7N","created_at":"2026-07-16T01:22:28.477092+00:00"},{"alias_kind":"pith_short_8","alias_value":"ARIN6D55","created_at":"2026-07-16T01:22:28.477092+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2606.05008","citing_title":"M$^3$Eval: Multi-Modal Memory Evaluation through Cognitively-Grounded Video Tasks","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2511.04670","citing_title":"Cambrian-S: Towards Spatial Supersensing in Video","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ARIN6D55IUSPYA7NRVA75GPMMK","json":"https://pith.science/pith/ARIN6D55IUSPYA7NRVA75GPMMK.json","graph_json":"https://pith.science/api/pith-number/ARIN6D55IUSPYA7NRVA75GPMMK/graph.json","events_json":"https://pith.science/api/pith-number/ARIN6D55IUSPYA7NRVA75GPMMK/events.json","paper":"https://pith.science/paper/ARIN6D55"},"agent_actions":{"view_html":"https://pith.science/pith/ARIN6D55IUSPYA7NRVA75GPMMK","download_json":"https://pith.science/pith/ARIN6D55IUSPYA7NRVA75GPMMK.json","view_paper":"https://pith.science/paper/ARIN6D55","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.24563&json=true","fetch_graph":"https://pith.science/api/pith-number/ARIN6D55IUSPYA7NRVA75GPMMK/graph.json","fetch_events":"https://pith.science/api/pith-number/ARIN6D55IUSPYA7NRVA75GPMMK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ARIN6D55IUSPYA7NRVA75GPMMK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ARIN6D55IUSPYA7NRVA75GPMMK/action/storage_attestation","attest_author":"https://pith.science/pith/ARIN6D55IUSPYA7NRVA75GPMMK/action/author_attestation","sign_citation":"https://pith.science/pith/ARIN6D55IUSPYA7NRVA75GPMMK/action/citation_signature","submit_replication":"https://pith.science/pith/ARIN6D55IUSPYA7NRVA75GPMMK/action/replication_record"}},"created_at":"2026-07-16T01:22:28.477092+00:00","updated_at":"2026-07-16T01:22:28.477092+00:00"}