{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MK3WJEVMJKGXKEE72PUUEHGEO2","short_pith_number":"pith:MK3WJEVM","schema_version":"1.0","canonical_sha256":"62b76492ac4a8d75109fd3e9421cc476a889fc190d271699e3f4a04dbfb44157","source":{"kind":"arxiv","id":"2403.14622","version":2},"attestation_state":"computed","paper":{"title":"Language Repository for Long Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jongwoo Park, Kanchana Ranasinghe, Kumara Kahatapitiya, Michael S. Ryoo","submitted_at":"2024-03-21T17:59:35Z","abstract_excerpt":"Language has become a prominent modality in computer vision with the rise of LLMs. Despite supporting long context-lengths, their effectiveness in handling long-term information gradually declines with input length. This becomes critical, especially in applications such as long-form video understanding. In this paper, we introduce a Language Repository (LangRepo) for LLMs, that maintains concise and structured information as an interpretable (i.e., all-textual) representation. Our repository is updated iteratively based on multi-scale video chunks. We introduce write and read operations that f"},"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":"2403.14622","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T17:59:35Z","cross_cats_sorted":[],"title_canon_sha256":"1b289831883c6f6189bbf55eaf07769211da19cca578491819d0b246efafa3cb","abstract_canon_sha256":"54c6b3d91b330ba276b45f1d607e753f8f080fbf917f068bdc67d9aaf7aff438"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:10.443405Z","signature_b64":"NAJoB0XMOSJcnuCzzRaD5MnWyq1FWoQH4agr32j9lU+ZrsHKZEWMES6Ce0b8jRxduAFGrC7IvQCHmUKRTEm5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62b76492ac4a8d75109fd3e9421cc476a889fc190d271699e3f4a04dbfb44157","last_reissued_at":"2026-07-05T09:52:10.442930Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:10.442930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Repository for Long Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jongwoo Park, Kanchana Ranasinghe, Kumara Kahatapitiya, Michael S. Ryoo","submitted_at":"2024-03-21T17:59:35Z","abstract_excerpt":"Language has become a prominent modality in computer vision with the rise of LLMs. Despite supporting long context-lengths, their effectiveness in handling long-term information gradually declines with input length. This becomes critical, especially in applications such as long-form video understanding. In this paper, we introduce a Language Repository (LangRepo) for LLMs, that maintains concise and structured information as an interpretable (i.e., all-textual) representation. Our repository is updated iteratively based on multi-scale video chunks. We introduce write and read operations that f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14622","kind":"arxiv","version":2},"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/2403.14622/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":"2403.14622","created_at":"2026-07-05T09:52:10.442985+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.14622v2","created_at":"2026-07-05T09:52:10.442985+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14622","created_at":"2026-07-05T09:52:10.442985+00:00"},{"alias_kind":"pith_short_12","alias_value":"MK3WJEVMJKGX","created_at":"2026-07-05T09:52:10.442985+00:00"},{"alias_kind":"pith_short_16","alias_value":"MK3WJEVMJKGXKEE7","created_at":"2026-07-05T09:52:10.442985+00:00"},{"alias_kind":"pith_short_8","alias_value":"MK3WJEVM","created_at":"2026-07-05T09:52:10.442985+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12195","citing_title":"InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning","ref_index":167,"is_internal_anchor":false},{"citing_arxiv_id":"2407.03320","citing_title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02891","citing_title":"Progressive Video Condensation with MLLM Agent for Long-form Video Understanding","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15280","citing_title":"Why Do Vision Language Models Struggle To Recognize Human Emotions?","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MK3WJEVMJKGXKEE72PUUEHGEO2","json":"https://pith.science/pith/MK3WJEVMJKGXKEE72PUUEHGEO2.json","graph_json":"https://pith.science/api/pith-number/MK3WJEVMJKGXKEE72PUUEHGEO2/graph.json","events_json":"https://pith.science/api/pith-number/MK3WJEVMJKGXKEE72PUUEHGEO2/events.json","paper":"https://pith.science/paper/MK3WJEVM"},"agent_actions":{"view_html":"https://pith.science/pith/MK3WJEVMJKGXKEE72PUUEHGEO2","download_json":"https://pith.science/pith/MK3WJEVMJKGXKEE72PUUEHGEO2.json","view_paper":"https://pith.science/paper/MK3WJEVM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.14622&json=true","fetch_graph":"https://pith.science/api/pith-number/MK3WJEVMJKGXKEE72PUUEHGEO2/graph.json","fetch_events":"https://pith.science/api/pith-number/MK3WJEVMJKGXKEE72PUUEHGEO2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MK3WJEVMJKGXKEE72PUUEHGEO2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MK3WJEVMJKGXKEE72PUUEHGEO2/action/storage_attestation","attest_author":"https://pith.science/pith/MK3WJEVMJKGXKEE72PUUEHGEO2/action/author_attestation","sign_citation":"https://pith.science/pith/MK3WJEVMJKGXKEE72PUUEHGEO2/action/citation_signature","submit_replication":"https://pith.science/pith/MK3WJEVMJKGXKEE72PUUEHGEO2/action/replication_record"}},"created_at":"2026-07-05T09:52:10.442985+00:00","updated_at":"2026-07-05T09:52:10.442985+00:00"}