{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IQFDFTXCPXEZ37BNNMHI7ROJMR","short_pith_number":"pith:IQFDFTXC","schema_version":"1.0","canonical_sha256":"440a32cee27dc99dfc2d6b0e8fc5c964486158c22a9120aa702e0993d79ec8d4","source":{"kind":"arxiv","id":"2606.07924","version":1},"attestation_state":"computed","paper":{"title":"Decoupling Semantics and Logic: A Training-Free Coarse-to-Fine Pipeline for Video Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Jiamin Yan, Jiaxin Dai, Xiang Xiang, Zehang Wei","submitted_at":"2026-06-06T01:17:40Z","abstract_excerpt":"This paper presents our system description for the 2nd Workshop on Multimodal Augmented Generation via MultimodAl Retrieval (MAGMaR). Addressing the critical challenges of cross-lingual long-video comprehension, strict persona adherence, and zero-hallucination temporal grounding, we propose a fully training-free, two-stage cascaded Video RAG pipeline. Our architecture strategically decouples semantic retrieval from cognitive logical reasoning through a modality-aware division of labor. In the first stage, a high-recall semantic pre-fetching module employs dense retrieval using only high-fideli"},"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":"2606.07924","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-06T01:17:40Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"title_canon_sha256":"51274fa91d8f8639a2bf89671d1addadebb5201afe014360852c28bc6b622a9d","abstract_canon_sha256":"15f45fca3b4118ee916a8ef4bf6f95c649d9f2c3d0b32347b7ff7d2a91106936"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:04:55.534031Z","signature_b64":"ntUPxvlyw7/ObkFXES73ij9STAiJ9qhHSRfauDb9lY6FrNH8deKSqzfAseuI1WfkUASIrnOZrKwCPNAfQh/NAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"440a32cee27dc99dfc2d6b0e8fc5c964486158c22a9120aa702e0993d79ec8d4","last_reissued_at":"2026-06-09T01:04:55.533684Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:04:55.533684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoupling Semantics and Logic: A Training-Free Coarse-to-Fine Pipeline for Video Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Jiamin Yan, Jiaxin Dai, Xiang Xiang, Zehang Wei","submitted_at":"2026-06-06T01:17:40Z","abstract_excerpt":"This paper presents our system description for the 2nd Workshop on Multimodal Augmented Generation via MultimodAl Retrieval (MAGMaR). Addressing the critical challenges of cross-lingual long-video comprehension, strict persona adherence, and zero-hallucination temporal grounding, we propose a fully training-free, two-stage cascaded Video RAG pipeline. Our architecture strategically decouples semantic retrieval from cognitive logical reasoning through a modality-aware division of labor. In the first stage, a high-recall semantic pre-fetching module employs dense retrieval using only high-fideli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07924","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/2606.07924/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":"2606.07924","created_at":"2026-06-09T01:04:55.533746+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07924v1","created_at":"2026-06-09T01:04:55.533746+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07924","created_at":"2026-06-09T01:04:55.533746+00:00"},{"alias_kind":"pith_short_12","alias_value":"IQFDFTXCPXEZ","created_at":"2026-06-09T01:04:55.533746+00:00"},{"alias_kind":"pith_short_16","alias_value":"IQFDFTXCPXEZ37BN","created_at":"2026-06-09T01:04:55.533746+00:00"},{"alias_kind":"pith_short_8","alias_value":"IQFDFTXC","created_at":"2026-06-09T01:04:55.533746+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/IQFDFTXCPXEZ37BNNMHI7ROJMR","json":"https://pith.science/pith/IQFDFTXCPXEZ37BNNMHI7ROJMR.json","graph_json":"https://pith.science/api/pith-number/IQFDFTXCPXEZ37BNNMHI7ROJMR/graph.json","events_json":"https://pith.science/api/pith-number/IQFDFTXCPXEZ37BNNMHI7ROJMR/events.json","paper":"https://pith.science/paper/IQFDFTXC"},"agent_actions":{"view_html":"https://pith.science/pith/IQFDFTXCPXEZ37BNNMHI7ROJMR","download_json":"https://pith.science/pith/IQFDFTXCPXEZ37BNNMHI7ROJMR.json","view_paper":"https://pith.science/paper/IQFDFTXC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07924&json=true","fetch_graph":"https://pith.science/api/pith-number/IQFDFTXCPXEZ37BNNMHI7ROJMR/graph.json","fetch_events":"https://pith.science/api/pith-number/IQFDFTXCPXEZ37BNNMHI7ROJMR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IQFDFTXCPXEZ37BNNMHI7ROJMR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IQFDFTXCPXEZ37BNNMHI7ROJMR/action/storage_attestation","attest_author":"https://pith.science/pith/IQFDFTXCPXEZ37BNNMHI7ROJMR/action/author_attestation","sign_citation":"https://pith.science/pith/IQFDFTXCPXEZ37BNNMHI7ROJMR/action/citation_signature","submit_replication":"https://pith.science/pith/IQFDFTXCPXEZ37BNNMHI7ROJMR/action/replication_record"}},"created_at":"2026-06-09T01:04:55.533746+00:00","updated_at":"2026-06-09T01:04:55.533746+00:00"}