{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VTCNL6DYCC3B3NWYVBKEEMUD7X","short_pith_number":"pith:VTCNL6DY","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"},"canonical_sha256":"acc4d5f87810b61db6d8a854423283fdee72c2fe07b9782bd9acfdf407a5634e","source":{"kind":"arxiv","id":"2606.24286","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VTCNL6DYCC3B3NWYVBKEEMUD7X","target":"record","payload":{"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"},"canonical_sha256":"acc4d5f87810b61db6d8a854423283fdee72c2fe07b9782bd9acfdf407a5634e","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"},"source_kind":"arxiv","source_id":"2606.24286","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-24T01:14:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4JX3kCMMgaA5HovCF5Nc6Y3HMUuLv5egduUKoA1OA+2PyOEW9Jkq0iTgLqB9uejmuQgy057ufUSVl9uOiy+eCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T19:56:22.815226Z"},"content_sha256":"f250ae1ae4a89a9cefc28fd6ea81483c3166a16ae7a100d21eceb8f39a2f5a34","schema_version":"1.0","event_id":"sha256:f250ae1ae4a89a9cefc28fd6ea81483c3166a16ae7a100d21eceb8f39a2f5a34"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VTCNL6DYCC3B3NWYVBKEEMUD7X","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-24T01:14:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5eVW0Xl1G4fe0oMsRQkCjNxqJyHjbA/YAHmucfHC51KJx0Zwk/bk3dGeaeq58wLEOe4jTo8Q9B0cae0isz+aCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T19:56:22.815629Z"},"content_sha256":"5b59e5203bcc1165bd82caddfa1d4277c65dc6a6a010be7bd4f86be466223f43","schema_version":"1.0","event_id":"sha256:5b59e5203bcc1165bd82caddfa1d4277c65dc6a6a010be7bd4f86be466223f43"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VTCNL6DYCC3B3NWYVBKEEMUD7X/bundle.json","state_url":"https://pith.science/pith/VTCNL6DYCC3B3NWYVBKEEMUD7X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VTCNL6DYCC3B3NWYVBKEEMUD7X/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-27T19:56:22Z","links":{"resolver":"https://pith.science/pith/VTCNL6DYCC3B3NWYVBKEEMUD7X","bundle":"https://pith.science/pith/VTCNL6DYCC3B3NWYVBKEEMUD7X/bundle.json","state":"https://pith.science/pith/VTCNL6DYCC3B3NWYVBKEEMUD7X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VTCNL6DYCC3B3NWYVBKEEMUD7X/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u4DGpkUw8VJ+CWK9O+FYTqU4XyuH1TF7Yd+swxhxnkrZ62kbTEsmTRU3NcXACqIMlrob1y1BbToiKH1lOUF6CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T19:56:22.817615Z","bundle_sha256":"c9aafab53de1bdde7320a7b92d77ea6bc6489528d09b048187648c6488f5bfee"}}