{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VTCNL6DYCC3B3NWYVBKEEMUD7X","short_pith_number":"pith:VTCNL6DY","schema_version":"1.0","canonical_sha256":"acc4d5f87810b61db6d8a854423283fdee72c2fe07b9782bd9acfdf407a5634e","source":{"kind":"arxiv","id":"2606.24286","version":1},"attestation_state":"computed","paper":{"title":"AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Guojie Zhu, Hao Jiang, Kaisi Guan, Ruihua Song, Wenhui Tan, Xiangyang Li, Xiaoyi Yu, Xin Cheng, Yijing Chen, Yuyue Wang","submitted_at":"2026-06-23T08:06:58Z","abstract_excerpt":"Multimodal Large Language Models have achieved remarkable progress in short-form audio-video understanding, yet long-form audio-video comprehension remains challenged by limited context windows and severe information redundancy. To address these bottlenecks, we propose AVOC, a framework for long-form audio-video understanding in Omni-modal Large Language Models. AVOC introduces a learnable token compression module between the modality encoders and the LLM backbone. We reframe multimodal token compression as a top-$K$ retrieval problem: given a fixed context budget, the module must retrieve a c"},"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":"2606.24286","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T08:06:58Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"34d0a37b99eb48f5ec171c674b00b117057f9f43c6f2638d7ff742bc36b642fd","abstract_canon_sha256":"f53fed6c06e022aa65bfc4004fee7c88128c1c1f52489bd332b58023083c8ba5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:49.023914Z","signature_b64":"uqq37pu1653yd/7vPPqkxaK7buwCuw2bNQy/4+5o17gVNM4hzl4KxeSRpiV0d1KDirzhtAYbTVk9VstjpzAGCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acc4d5f87810b61db6d8a854423283fdee72c2fe07b9782bd9acfdf407a5634e","last_reissued_at":"2026-06-24T01:14:49.023495Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:49.023495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Guojie Zhu, Hao Jiang, Kaisi Guan, Ruihua Song, Wenhui Tan, Xiangyang Li, Xiaoyi Yu, Xin Cheng, Yijing Chen, Yuyue Wang","submitted_at":"2026-06-23T08:06:58Z","abstract_excerpt":"Multimodal Large Language Models have achieved remarkable progress in short-form audio-video understanding, yet long-form audio-video comprehension remains challenged by limited context windows and severe information redundancy. To address these bottlenecks, we propose AVOC, a framework for long-form audio-video understanding in Omni-modal Large Language Models. AVOC introduces a learnable token compression module between the modality encoders and the LLM backbone. We reframe multimodal token compression as a top-$K$ retrieval problem: given a fixed context budget, the module must retrieve a c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24286","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/2606.24286/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":"2606.24286","created_at":"2026-06-24T01:14:49.023559+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.24286v1","created_at":"2026-06-24T01:14:49.023559+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24286","created_at":"2026-06-24T01:14:49.023559+00:00"},{"alias_kind":"pith_short_12","alias_value":"VTCNL6DYCC3B","created_at":"2026-06-24T01:14:49.023559+00:00"},{"alias_kind":"pith_short_16","alias_value":"VTCNL6DYCC3B3NWY","created_at":"2026-06-24T01:14:49.023559+00:00"},{"alias_kind":"pith_short_8","alias_value":"VTCNL6DY","created_at":"2026-06-24T01:14:49.023559+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/VTCNL6DYCC3B3NWYVBKEEMUD7X","json":"https://pith.science/pith/VTCNL6DYCC3B3NWYVBKEEMUD7X.json","graph_json":"https://pith.science/api/pith-number/VTCNL6DYCC3B3NWYVBKEEMUD7X/graph.json","events_json":"https://pith.science/api/pith-number/VTCNL6DYCC3B3NWYVBKEEMUD7X/events.json","paper":"https://pith.science/paper/VTCNL6DY"},"agent_actions":{"view_html":"https://pith.science/pith/VTCNL6DYCC3B3NWYVBKEEMUD7X","download_json":"https://pith.science/pith/VTCNL6DYCC3B3NWYVBKEEMUD7X.json","view_paper":"https://pith.science/paper/VTCNL6DY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.24286&json=true","fetch_graph":"https://pith.science/api/pith-number/VTCNL6DYCC3B3NWYVBKEEMUD7X/graph.json","fetch_events":"https://pith.science/api/pith-number/VTCNL6DYCC3B3NWYVBKEEMUD7X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VTCNL6DYCC3B3NWYVBKEEMUD7X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VTCNL6DYCC3B3NWYVBKEEMUD7X/action/storage_attestation","attest_author":"https://pith.science/pith/VTCNL6DYCC3B3NWYVBKEEMUD7X/action/author_attestation","sign_citation":"https://pith.science/pith/VTCNL6DYCC3B3NWYVBKEEMUD7X/action/citation_signature","submit_replication":"https://pith.science/pith/VTCNL6DYCC3B3NWYVBKEEMUD7X/action/replication_record"}},"created_at":"2026-06-24T01:14:49.023559+00:00","updated_at":"2026-06-24T01:14:49.023559+00:00"}