{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:C2RWHQKVUYCNYFMBCHZZYWO4FQ","short_pith_number":"pith:C2RWHQKV","schema_version":"1.0","canonical_sha256":"16a363c155a604dc158111f39c59dc2c15c52d12d2d833a377d9ec65c853a665","source":{"kind":"arxiv","id":"2607.25125","version":1},"attestation_state":"computed","paper":{"title":"LENS: Adaptive Spatio-Temporal Zooming for Keyframe Sampling in Long-Form Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ce Zhang, Jinxi He, Katia Sycara, Yaqi Xie","submitted_at":"2026-07-27T22:36:33Z","abstract_excerpt":"Despite rapid progress in Multi-modal Large Language Models (MLLMs), understanding long-form videos is still bottlenecked by limited context windows. While recent keyframe sampling methods attempt to mitigate this by distilling video inputs into a compact set of query-relevant frames, navigating the vast spatio-temporal search space remains challenging, as spatial detail and temporal coverage often conflict. To address this, we introduce LENS, a training-free keyframe sampling framework that dynamically decides when to zoom in for fine-grained details and when to zoom out for broader context b"},"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":"2607.25125","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-27T22:36:33Z","cross_cats_sorted":[],"title_canon_sha256":"a54dd6dbde6831a76fa275793b8fb4e8d0693d6e5623fb40285111e20b8b48c4","abstract_canon_sha256":"2d08786b0cfb01f9b663e19064ecc5089d821e5857a3c983f1d84c5b68bb3a1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T00:25:04.081568Z","signature_b64":"bnB7pP+CygP3ResYha3eLx5vCbM6DptBGrKMQWrwIA7XWs/DPmjQ4eZ7KZm0s/k4eH7riZynZO9K6Ij4mQ6aDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16a363c155a604dc158111f39c59dc2c15c52d12d2d833a377d9ec65c853a665","last_reissued_at":"2026-07-29T00:25:04.080679Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T00:25:04.080679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LENS: Adaptive Spatio-Temporal Zooming for Keyframe Sampling in Long-Form Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ce Zhang, Jinxi He, Katia Sycara, Yaqi Xie","submitted_at":"2026-07-27T22:36:33Z","abstract_excerpt":"Despite rapid progress in Multi-modal Large Language Models (MLLMs), understanding long-form videos is still bottlenecked by limited context windows. While recent keyframe sampling methods attempt to mitigate this by distilling video inputs into a compact set of query-relevant frames, navigating the vast spatio-temporal search space remains challenging, as spatial detail and temporal coverage often conflict. To address this, we introduce LENS, a training-free keyframe sampling framework that dynamically decides when to zoom in for fine-grained details and when to zoom out for broader context b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.25125","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/2607.25125/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":"2607.25125","created_at":"2026-07-29T00:25:04.081140+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.25125v1","created_at":"2026-07-29T00:25:04.081140+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.25125","created_at":"2026-07-29T00:25:04.081140+00:00"},{"alias_kind":"pith_short_12","alias_value":"C2RWHQKVUYCN","created_at":"2026-07-29T00:25:04.081140+00:00"},{"alias_kind":"pith_short_16","alias_value":"C2RWHQKVUYCNYFMB","created_at":"2026-07-29T00:25:04.081140+00:00"},{"alias_kind":"pith_short_8","alias_value":"C2RWHQKV","created_at":"2026-07-29T00:25:04.081140+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/C2RWHQKVUYCNYFMBCHZZYWO4FQ","json":"https://pith.science/pith/C2RWHQKVUYCNYFMBCHZZYWO4FQ.json","graph_json":"https://pith.science/api/pith-number/C2RWHQKVUYCNYFMBCHZZYWO4FQ/graph.json","events_json":"https://pith.science/api/pith-number/C2RWHQKVUYCNYFMBCHZZYWO4FQ/events.json","paper":"https://pith.science/paper/C2RWHQKV"},"agent_actions":{"view_html":"https://pith.science/pith/C2RWHQKVUYCNYFMBCHZZYWO4FQ","download_json":"https://pith.science/pith/C2RWHQKVUYCNYFMBCHZZYWO4FQ.json","view_paper":"https://pith.science/paper/C2RWHQKV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.25125&json=true","fetch_graph":"https://pith.science/api/pith-number/C2RWHQKVUYCNYFMBCHZZYWO4FQ/graph.json","fetch_events":"https://pith.science/api/pith-number/C2RWHQKVUYCNYFMBCHZZYWO4FQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C2RWHQKVUYCNYFMBCHZZYWO4FQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C2RWHQKVUYCNYFMBCHZZYWO4FQ/action/storage_attestation","attest_author":"https://pith.science/pith/C2RWHQKVUYCNYFMBCHZZYWO4FQ/action/author_attestation","sign_citation":"https://pith.science/pith/C2RWHQKVUYCNYFMBCHZZYWO4FQ/action/citation_signature","submit_replication":"https://pith.science/pith/C2RWHQKVUYCNYFMBCHZZYWO4FQ/action/replication_record"}},"created_at":"2026-07-29T00:25:04.081140+00:00","updated_at":"2026-07-29T00:25:04.081140+00:00"}