{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VTCNL6DYCC3B3NWYVBKEEMUD7X","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f53fed6c06e022aa65bfc4004fee7c88128c1c1f52489bd332b58023083c8ba5","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T08:06:58Z","title_canon_sha256":"34d0a37b99eb48f5ec171c674b00b117057f9f43c6f2638d7ff742bc36b642fd"},"schema_version":"1.0","source":{"id":"2606.24286","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24286","created_at":"2026-06-24T01:14:49Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24286v1","created_at":"2026-06-24T01:14:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24286","created_at":"2026-06-24T01:14:49Z"},{"alias_kind":"pith_short_12","alias_value":"VTCNL6DYCC3B","created_at":"2026-06-24T01:14:49Z"},{"alias_kind":"pith_short_16","alias_value":"VTCNL6DYCC3B3NWY","created_at":"2026-06-24T01:14:49Z"},{"alias_kind":"pith_short_8","alias_value":"VTCNL6DY","created_at":"2026-06-24T01:14:49Z"}],"graph_snapshots":[{"event_id":"sha256:5b59e5203bcc1165bd82caddfa1d4277c65dc6a6a010be7bd4f86be466223f43","target":"graph","created_at":"2026-06-24T01:14:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.24286/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Guojie Zhu, Hao Jiang, Kaisi Guan, Ruihua Song, Wenhui Tan, Xiangyang Li, Xiaoyi Yu, Xin Cheng, Yijing Chen, Yuyue Wang","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T08:06:58Z","title":"AVOC: Enhancing Hour-Level Audio-Video Understanding in Omni-Modal LLMs via Retrieval-Inspired Token Compression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24286","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f250ae1ae4a89a9cefc28fd6ea81483c3166a16ae7a100d21eceb8f39a2f5a34","target":"record","created_at":"2026-06-24T01:14:49Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f53fed6c06e022aa65bfc4004fee7c88128c1c1f52489bd332b58023083c8ba5","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-23T08:06:58Z","title_canon_sha256":"34d0a37b99eb48f5ec171c674b00b117057f9f43c6f2638d7ff742bc36b642fd"},"schema_version":"1.0","source":{"id":"2606.24286","kind":"arxiv","version":1}},"canonical_sha256":"acc4d5f87810b61db6d8a854423283fdee72c2fe07b9782bd9acfdf407a5634e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acc4d5f87810b61db6d8a854423283fdee72c2fe07b9782bd9acfdf407a5634e","first_computed_at":"2026-06-24T01:14:49.023495Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:14:49.023495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uqq37pu1653yd/7vPPqkxaK7buwCuw2bNQy/4+5o17gVNM4hzl4KxeSRpiV0d1KDirzhtAYbTVk9VstjpzAGCg==","signature_status":"signed_v1","signed_at":"2026-06-24T01:14:49.023914Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.24286","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f250ae1ae4a89a9cefc28fd6ea81483c3166a16ae7a100d21eceb8f39a2f5a34","sha256:5b59e5203bcc1165bd82caddfa1d4277c65dc6a6a010be7bd4f86be466223f43"],"state_sha256":"17c92b0479949bb11c81e0eeb10cd03e9875645a2507049eeaeaad7ae7a49e17"}