{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Z6HLR2KOITW2GTPLADW3PQM6WY","short_pith_number":"pith:Z6HLR2KO","schema_version":"1.0","canonical_sha256":"cf8eb8e94e44eda34deb00edb7c19eb6111e73e74512c24e1287abf96d159910","source":{"kind":"arxiv","id":"2605.14310","version":1},"attestation_state":"computed","paper":{"title":"CoRDS: Coreset-based Representative and Diverse Selection for Streaming Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Treating KV-cache compression as coreset selection improves streaming video understanding under fixed memory budgets.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ailar Mahdizadeh, Leonid Sigal, Muchen Li, Puria Azadi, Xiangteng He","submitted_at":"2026-05-14T03:22:30Z","abstract_excerpt":"Streaming video understanding with large vision-language models (VLMs) requires a compact memory that can support future reasoning over an ever-growing visual history. A common solution is to compress the key-value (KV) cache, but existing streaming methods typically rely on local token-wise heuristics, such as recency, temporal redundancy, or saliency, which do not explicitly optimize whether the retained cache is representative of the accumulated history. We propose to view KV-cache compression as a coreset selection problem: rather than scoring tokens independently for retention, we select "},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.14310","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T03:22:30Z","cross_cats_sorted":[],"title_canon_sha256":"0b3c0d18e1f31bb8b3496673bb86fa0d1b96f8140acf5c2ebf52d0e4339d3520","abstract_canon_sha256":"d89c916e7a11a6617f46c67f171b91b726f96ccf276a611b3aeeebd5f145ee1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:10.004159Z","signature_b64":"Q5LWr7kRKDnM4L0iz9/m2xo6DH6QWWlflH6CLUz9yk3bsB/aBGm7oBy7vUqbi3uon4zMkXql22Kbn4EWFoxlBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf8eb8e94e44eda34deb00edb7c19eb6111e73e74512c24e1287abf96d159910","last_reissued_at":"2026-05-17T23:39:10.003699Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:10.003699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoRDS: Coreset-based Representative and Diverse Selection for Streaming Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Treating KV-cache compression as coreset selection improves streaming video understanding under fixed memory budgets.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ailar Mahdizadeh, Leonid Sigal, Muchen Li, Puria Azadi, Xiangteng He","submitted_at":"2026-05-14T03:22:30Z","abstract_excerpt":"Streaming video understanding with large vision-language models (VLMs) requires a compact memory that can support future reasoning over an ever-growing visual history. A common solution is to compress the key-value (KV) cache, but existing streaming methods typically rely on local token-wise heuristics, such as recency, temporal redundancy, or saliency, which do not explicitly optimize whether the retained cache is representative of the accumulated history. We propose to view KV-cache compression as a coreset selection problem: rather than scoring tokens independently for retention, we select "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Across four open-source VLMs and five long-video and streaming-video benchmarks, our method improves over heuristic streaming compression baselines under a fixed cache budget.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a small coreset chosen by joint KV coverage and orthogonality will preserve the information needed for arbitrary future reasoning queries over the full history.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CoRDS selects a compact KV-cache subset via joint-space coreset coverage and log-det diversity to outperform token-wise heuristics on long-video VLM benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Treating KV-cache compression as coreset selection improves streaming video understanding under fixed memory budgets.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d3c1de20f15168de3249dfe5176e72b4d1eda4bd635eb4d9c36fff85a1725ba3"},"source":{"id":"2605.14310","kind":"arxiv","version":1},"verdict":{"id":"4a664be5-ccb1-4be9-a9c7-1ea9c582dcb5","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T02:24:37.272302Z","strongest_claim":"Across four open-source VLMs and five long-video and streaming-video benchmarks, our method improves over heuristic streaming compression baselines under a fixed cache budget.","one_line_summary":"CoRDS selects a compact KV-cache subset via joint-space coreset coverage and log-det diversity to outperform token-wise heuristics on long-video VLM benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a small coreset chosen by joint KV coverage and orthogonality will preserve the information needed for arbitrary future reasoning queries over the full history.","pith_extraction_headline":"Treating KV-cache compression as coreset selection improves streaming video understanding under fixed memory budgets."},"references":{"count":32,"sample":[{"doi":"","year":2024,"title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","work_id":"8abcfe4f-e0fb-44b7-9123-448fac95f90a","ref_index":2,"cited_arxiv_id":"2409.12191","is_internal_anchor":true},{"doi":"","year":2025,"title":"Long context transfer from language to vision.Transactions on Machine Learning Research, 2025","work_id":"62705864-363c-4f27-84b3-0f90e70f58f2","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Infinipot-v: Memory-constrained kv cache compression for streaming video understanding","work_id":"fd86124e-903d-4c8e-a169-f9b97c80b4b6","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Streaming long video understanding with large language models","work_id":"6a0c4f9b-d588-49db-8fe1-5d2652cc34f5","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Kim, Bilge Soran, Raghuraman Krishnamoorthi, Mohamed Elhoseiny, and Vikas Chandra","work_id":"e47963a0-7038-4696-99ee-74c58cd4e5de","ref_index":6,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":32,"snapshot_sha256":"e47305bb4df4f97304fbc7b8522295edd67bd1fc08b7cc0c177e4d4cab054d3f","internal_anchors":7},"formal_canon":{"evidence_count":2,"snapshot_sha256":"b1cc6b3b748e09ee0735fa762b4d42b27c47d6e4fc29ccb0e729e336af5b5524"},"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":"2605.14310","created_at":"2026-05-17T23:39:10.003771+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14310v1","created_at":"2026-05-17T23:39:10.003771+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14310","created_at":"2026-05-17T23:39:10.003771+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z6HLR2KOITW2","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z6HLR2KOITW2GTPL","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z6HLR2KO","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z6HLR2KOITW2GTPLADW3PQM6WY","json":"https://pith.science/pith/Z6HLR2KOITW2GTPLADW3PQM6WY.json","graph_json":"https://pith.science/api/pith-number/Z6HLR2KOITW2GTPLADW3PQM6WY/graph.json","events_json":"https://pith.science/api/pith-number/Z6HLR2KOITW2GTPLADW3PQM6WY/events.json","paper":"https://pith.science/paper/Z6HLR2KO"},"agent_actions":{"view_html":"https://pith.science/pith/Z6HLR2KOITW2GTPLADW3PQM6WY","download_json":"https://pith.science/pith/Z6HLR2KOITW2GTPLADW3PQM6WY.json","view_paper":"https://pith.science/paper/Z6HLR2KO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14310&json=true","fetch_graph":"https://pith.science/api/pith-number/Z6HLR2KOITW2GTPLADW3PQM6WY/graph.json","fetch_events":"https://pith.science/api/pith-number/Z6HLR2KOITW2GTPLADW3PQM6WY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z6HLR2KOITW2GTPLADW3PQM6WY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z6HLR2KOITW2GTPLADW3PQM6WY/action/storage_attestation","attest_author":"https://pith.science/pith/Z6HLR2KOITW2GTPLADW3PQM6WY/action/author_attestation","sign_citation":"https://pith.science/pith/Z6HLR2KOITW2GTPLADW3PQM6WY/action/citation_signature","submit_replication":"https://pith.science/pith/Z6HLR2KOITW2GTPLADW3PQM6WY/action/replication_record"}},"created_at":"2026-05-17T23:39:10.003771+00:00","updated_at":"2026-05-17T23:39:10.003771+00:00"}