{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TBQO3C35HEQJQUBTS56FVM3B2D","short_pith_number":"pith:TBQO3C35","schema_version":"1.0","canonical_sha256":"9860ed8b7d3920985033977c5ab361d0e7478b62a4058c08e0845b9069b36e09","source":{"kind":"arxiv","id":"2605.25179","version":1},"attestation_state":"computed","paper":{"title":"Locality Matters for Training-Free Audio Token Compression in Audio-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haoji Hu, Jiale Luo, Xiaoyu Liang","submitted_at":"2026-05-24T17:19:31Z","abstract_excerpt":"Audio-language models (ALMs) are increasingly used for audio captioning, question answering, and open-ended audio understanding, but their inference cost remains high when audio inputs are represented as long prefix-token sequences. These audio prefixes consume context budget, increase memory usage, and make deployment harder in resource-constrained or latency-sensitive settings. Existing training-free audio-token reduction methods mainly rely on fixed pooling or score-based pruning. Fixed pooling is content-agnostic, while score-based pruning can preserve isolated salient tokens but discard n"},"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":"2605.25179","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-24T17:19:31Z","cross_cats_sorted":[],"title_canon_sha256":"71fa35c21b4e2f7e2d69c69a19680300296dd3dd3f4c0408e5a9d1872c4f4cd6","abstract_canon_sha256":"e162723227d50dc88f348c732200dcb509243fabaff1fa3a3d0770d3dda18575"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:21.720804Z","signature_b64":"CV3fqAB6VvZ4Z5XLImvlvIykRljAEDdMRX8TG9j8YbWNQDQEcdAQpYtSe8vdR0oN6Yrb3v5oL/qcrgf1s1ZUAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9860ed8b7d3920985033977c5ab361d0e7478b62a4058c08e0845b9069b36e09","last_reissued_at":"2026-05-26T02:04:21.720024Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:21.720024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Locality Matters for Training-Free Audio Token Compression in Audio-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haoji Hu, Jiale Luo, Xiaoyu Liang","submitted_at":"2026-05-24T17:19:31Z","abstract_excerpt":"Audio-language models (ALMs) are increasingly used for audio captioning, question answering, and open-ended audio understanding, but their inference cost remains high when audio inputs are represented as long prefix-token sequences. These audio prefixes consume context budget, increase memory usage, and make deployment harder in resource-constrained or latency-sensitive settings. Existing training-free audio-token reduction methods mainly rely on fixed pooling or score-based pruning. Fixed pooling is content-agnostic, while score-based pruning can preserve isolated salient tokens but discard n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25179","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/2605.25179/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":"2605.25179","created_at":"2026-05-26T02:04:21.720161+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.25179v1","created_at":"2026-05-26T02:04:21.720161+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25179","created_at":"2026-05-26T02:04:21.720161+00:00"},{"alias_kind":"pith_short_12","alias_value":"TBQO3C35HEQJ","created_at":"2026-05-26T02:04:21.720161+00:00"},{"alias_kind":"pith_short_16","alias_value":"TBQO3C35HEQJQUBT","created_at":"2026-05-26T02:04:21.720161+00:00"},{"alias_kind":"pith_short_8","alias_value":"TBQO3C35","created_at":"2026-05-26T02:04:21.720161+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/TBQO3C35HEQJQUBTS56FVM3B2D","json":"https://pith.science/pith/TBQO3C35HEQJQUBTS56FVM3B2D.json","graph_json":"https://pith.science/api/pith-number/TBQO3C35HEQJQUBTS56FVM3B2D/graph.json","events_json":"https://pith.science/api/pith-number/TBQO3C35HEQJQUBTS56FVM3B2D/events.json","paper":"https://pith.science/paper/TBQO3C35"},"agent_actions":{"view_html":"https://pith.science/pith/TBQO3C35HEQJQUBTS56FVM3B2D","download_json":"https://pith.science/pith/TBQO3C35HEQJQUBTS56FVM3B2D.json","view_paper":"https://pith.science/paper/TBQO3C35","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.25179&json=true","fetch_graph":"https://pith.science/api/pith-number/TBQO3C35HEQJQUBTS56FVM3B2D/graph.json","fetch_events":"https://pith.science/api/pith-number/TBQO3C35HEQJQUBTS56FVM3B2D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TBQO3C35HEQJQUBTS56FVM3B2D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TBQO3C35HEQJQUBTS56FVM3B2D/action/storage_attestation","attest_author":"https://pith.science/pith/TBQO3C35HEQJQUBTS56FVM3B2D/action/author_attestation","sign_citation":"https://pith.science/pith/TBQO3C35HEQJQUBTS56FVM3B2D/action/citation_signature","submit_replication":"https://pith.science/pith/TBQO3C35HEQJQUBTS56FVM3B2D/action/replication_record"}},"created_at":"2026-05-26T02:04:21.720161+00:00","updated_at":"2026-05-26T02:04:21.720161+00:00"}