{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TZOMBIMZ2R6ALYFBGQBIAUBTG4","short_pith_number":"pith:TZOMBIMZ","schema_version":"1.0","canonical_sha256":"9e5cc0a199d47c05e0a13402805033373ed70c69a74304e6d12b33151a0828c8","source":{"kind":"arxiv","id":"2512.10324","version":2},"attestation_state":"computed","paper":{"title":"EchoingPixels: Aliasing-Resistant Joint Token Reduction for Audio-Visual LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Gong, Depeng Wang, Huijia Zhu, Jingjing Chen, Ya Guo, Zhipeng Wei","submitted_at":"2025-12-11T06:18:58Z","abstract_excerpt":"Audio-Visual Large Language Models (AV-LLMs) face prohibitive computational costs of processing massive, redundant audio-visual tokens. Existing unimodal compression techniques fail to capture the heterogeneous and mutually influential information density of joint audio-visual signals. Furthermore, we identify a fundamental and overlooked theoretical bottleneck in sparse token reduction: positional aliasing. We demonstrate that aggressive sparse sampling on standard position-encoded sequences violates the Nyquist limit relative to the effective token interval, causing phase-wrapping collisions"},"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":"2512.10324","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-11T06:18:58Z","cross_cats_sorted":[],"title_canon_sha256":"71bba07af63a1370cf3980bad8c04542360f5b7b34c2d445746202f8523cfcc9","abstract_canon_sha256":"70ea731da3f80e98f8c95d7a19e0c10d78f8030ffc46a648bf6221784010ae46"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T03:13:52.348409Z","signature_b64":"yvFi3IJypeVXVAmw3lY5kx+G8kbZFw/vco7eGW4yxIHZMPlq9xchJ5MH/pIYM6NRIXzUmVgQKn7kKjtHq4uNCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e5cc0a199d47c05e0a13402805033373ed70c69a74304e6d12b33151a0828c8","last_reissued_at":"2026-06-23T03:13:52.347910Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T03:13:52.347910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EchoingPixels: Aliasing-Resistant Joint Token Reduction for Audio-Visual LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Gong, Depeng Wang, Huijia Zhu, Jingjing Chen, Ya Guo, Zhipeng Wei","submitted_at":"2025-12-11T06:18:58Z","abstract_excerpt":"Audio-Visual Large Language Models (AV-LLMs) face prohibitive computational costs of processing massive, redundant audio-visual tokens. Existing unimodal compression techniques fail to capture the heterogeneous and mutually influential information density of joint audio-visual signals. Furthermore, we identify a fundamental and overlooked theoretical bottleneck in sparse token reduction: positional aliasing. We demonstrate that aggressive sparse sampling on standard position-encoded sequences violates the Nyquist limit relative to the effective token interval, causing phase-wrapping collisions"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.10324","kind":"arxiv","version":2},"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/2512.10324/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":"2512.10324","created_at":"2026-06-23T03:13:52.347969+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.10324v2","created_at":"2026-06-23T03:13:52.347969+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.10324","created_at":"2026-06-23T03:13:52.347969+00:00"},{"alias_kind":"pith_short_12","alias_value":"TZOMBIMZ2R6A","created_at":"2026-06-23T03:13:52.347969+00:00"},{"alias_kind":"pith_short_16","alias_value":"TZOMBIMZ2R6ALYFB","created_at":"2026-06-23T03:13:52.347969+00:00"},{"alias_kind":"pith_short_8","alias_value":"TZOMBIMZ","created_at":"2026-06-23T03:13:52.347969+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2605.20035","citing_title":"Stage-adaptive Token Selection for Efficient Omni-modal LLMs","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12056","citing_title":"OmniRefine: Alignment-Aware Cooperative Compression for Efficient Omnimodal Large Language Models","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11605","citing_title":"Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10050","citing_title":"EchoPrune: Interpreting Redundancy as Temporal Echoes for Efficient VideoLLMs","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TZOMBIMZ2R6ALYFBGQBIAUBTG4","json":"https://pith.science/pith/TZOMBIMZ2R6ALYFBGQBIAUBTG4.json","graph_json":"https://pith.science/api/pith-number/TZOMBIMZ2R6ALYFBGQBIAUBTG4/graph.json","events_json":"https://pith.science/api/pith-number/TZOMBIMZ2R6ALYFBGQBIAUBTG4/events.json","paper":"https://pith.science/paper/TZOMBIMZ"},"agent_actions":{"view_html":"https://pith.science/pith/TZOMBIMZ2R6ALYFBGQBIAUBTG4","download_json":"https://pith.science/pith/TZOMBIMZ2R6ALYFBGQBIAUBTG4.json","view_paper":"https://pith.science/paper/TZOMBIMZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.10324&json=true","fetch_graph":"https://pith.science/api/pith-number/TZOMBIMZ2R6ALYFBGQBIAUBTG4/graph.json","fetch_events":"https://pith.science/api/pith-number/TZOMBIMZ2R6ALYFBGQBIAUBTG4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TZOMBIMZ2R6ALYFBGQBIAUBTG4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TZOMBIMZ2R6ALYFBGQBIAUBTG4/action/storage_attestation","attest_author":"https://pith.science/pith/TZOMBIMZ2R6ALYFBGQBIAUBTG4/action/author_attestation","sign_citation":"https://pith.science/pith/TZOMBIMZ2R6ALYFBGQBIAUBTG4/action/citation_signature","submit_replication":"https://pith.science/pith/TZOMBIMZ2R6ALYFBGQBIAUBTG4/action/replication_record"}},"created_at":"2026-06-23T03:13:52.347969+00:00","updated_at":"2026-06-23T03:13:52.347969+00:00"}