{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QE6KHWNGG2ZYSZWGGEC7XNHZNK","short_pith_number":"pith:QE6KHWNG","schema_version":"1.0","canonical_sha256":"813ca3d9a636b38966c63105fbb4f96aae165def0d0e300f5be213902741d977","source":{"kind":"arxiv","id":"2606.13141","version":1},"attestation_state":"computed","paper":{"title":"Rethinking RAG in Long Videos: What to Retrieve and How to Use It?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fatih Porikli, Hwanjun Song, Jihwan Bang, Jisu Shin, Juntae Lee, Kyuwoong Hwang, Nicole Hee-Yeon Kim, Yuho Lee","submitted_at":"2026-06-11T10:05:49Z","abstract_excerpt":"Retrieval-augmented generation is moving beyond text into long, egocentric video, where systems must select query-relevant chunks across multiple modalities and temporal granularities. Yet progress in VideoRAG is limited by two gaps: existing benchmarks allow queries to be answered without the video, obscuring retrieval errors, and prior methods apply a single modality-granularity configuration per query, ignoring chunk-level variability. We address both by introducing V-RAGBench, a benchmark of $\\langle$query, evidence chunk, answer$\\rangle$ triplets that enables faithful, decoupled evaluatio"},"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":"2606.13141","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-11T10:05:49Z","cross_cats_sorted":[],"title_canon_sha256":"7ed45f59023c2e25eda60f03b9a2e0446d2c499dc7f5f7bec664d68662a591fa","abstract_canon_sha256":"133527c93e96f44cb4d9f0183c48342bc0a77d6345f909f77d5e3d2abc31622b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:42.539091Z","signature_b64":"Th3xwu9027IIQtWP36rRECRlZEstOK7/GYScGO+uyD0O6evV0dFOMORHvTWeZDCp8UqPVYtMjWqs+ChIuN5uDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"813ca3d9a636b38966c63105fbb4f96aae165def0d0e300f5be213902741d977","last_reissued_at":"2026-06-12T01:09:42.538304Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:42.538304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking RAG in Long Videos: What to Retrieve and How to Use It?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fatih Porikli, Hwanjun Song, Jihwan Bang, Jisu Shin, Juntae Lee, Kyuwoong Hwang, Nicole Hee-Yeon Kim, Yuho Lee","submitted_at":"2026-06-11T10:05:49Z","abstract_excerpt":"Retrieval-augmented generation is moving beyond text into long, egocentric video, where systems must select query-relevant chunks across multiple modalities and temporal granularities. Yet progress in VideoRAG is limited by two gaps: existing benchmarks allow queries to be answered without the video, obscuring retrieval errors, and prior methods apply a single modality-granularity configuration per query, ignoring chunk-level variability. We address both by introducing V-RAGBench, a benchmark of $\\langle$query, evidence chunk, answer$\\rangle$ triplets that enables faithful, decoupled evaluatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13141","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/2606.13141/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":"2606.13141","created_at":"2026-06-12T01:09:42.538454+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.13141v1","created_at":"2026-06-12T01:09:42.538454+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13141","created_at":"2026-06-12T01:09:42.538454+00:00"},{"alias_kind":"pith_short_12","alias_value":"QE6KHWNGG2ZY","created_at":"2026-06-12T01:09:42.538454+00:00"},{"alias_kind":"pith_short_16","alias_value":"QE6KHWNGG2ZYSZWG","created_at":"2026-06-12T01:09:42.538454+00:00"},{"alias_kind":"pith_short_8","alias_value":"QE6KHWNG","created_at":"2026-06-12T01:09:42.538454+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/QE6KHWNGG2ZYSZWGGEC7XNHZNK","json":"https://pith.science/pith/QE6KHWNGG2ZYSZWGGEC7XNHZNK.json","graph_json":"https://pith.science/api/pith-number/QE6KHWNGG2ZYSZWGGEC7XNHZNK/graph.json","events_json":"https://pith.science/api/pith-number/QE6KHWNGG2ZYSZWGGEC7XNHZNK/events.json","paper":"https://pith.science/paper/QE6KHWNG"},"agent_actions":{"view_html":"https://pith.science/pith/QE6KHWNGG2ZYSZWGGEC7XNHZNK","download_json":"https://pith.science/pith/QE6KHWNGG2ZYSZWGGEC7XNHZNK.json","view_paper":"https://pith.science/paper/QE6KHWNG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.13141&json=true","fetch_graph":"https://pith.science/api/pith-number/QE6KHWNGG2ZYSZWGGEC7XNHZNK/graph.json","fetch_events":"https://pith.science/api/pith-number/QE6KHWNGG2ZYSZWGGEC7XNHZNK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QE6KHWNGG2ZYSZWGGEC7XNHZNK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QE6KHWNGG2ZYSZWGGEC7XNHZNK/action/storage_attestation","attest_author":"https://pith.science/pith/QE6KHWNGG2ZYSZWGGEC7XNHZNK/action/author_attestation","sign_citation":"https://pith.science/pith/QE6KHWNGG2ZYSZWGGEC7XNHZNK/action/citation_signature","submit_replication":"https://pith.science/pith/QE6KHWNGG2ZYSZWGGEC7XNHZNK/action/replication_record"}},"created_at":"2026-06-12T01:09:42.538454+00:00","updated_at":"2026-06-12T01:09:42.538454+00:00"}