{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HBOWFGHLLL3SIPKZN3W6JLDHHZ","short_pith_number":"pith:HBOWFGHL","schema_version":"1.0","canonical_sha256":"385d6298eb5af7243d596eede4ac673e72727fcc1d816a5de03945502d39812b","source":{"kind":"arxiv","id":"2606.30682","version":1},"attestation_state":"computed","paper":{"title":"ALM2Vec: Learning Audio Embeddings for Universal Audio Retrieval with Large Audio-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Aaron Yee, Chenang Jiang, Fengjie Lu, Helin Wang, Jiarui Hai","submitted_at":"2026-06-27T03:56:57Z","abstract_excerpt":"Recent advances in language--audio retrieval have been largely driven by contrastive dual-encoder architectures that align audio and text in a shared embedding space. While effective, existing retrieval embeddings are primarily optimized for audio--caption matching, limiting their ability to support diverse retrieval objectives and controllable retrieval behaviors. We present ALM2Vec, a universal audio embedding framework derived from pretrained large audio--language models (LALMs). By transferring the audio understanding, instruction-following, and reasoning capabilities acquired through larg"},"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":"2606.30682","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-27T03:56:57Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"d12aef9174011b1d7bf1c92bc16e1a5434d787b5317cabdce7c9d81fae96c2dd","abstract_canon_sha256":"f927f01eb93a9afa73d4005ef8094ed9cce5a085ee9064c35ef3c2447eec6401"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T00:17:13.454479Z","signature_b64":"ppm2nk2pCwv90y6i+2rq+lAnlcAvCayVqC6RXZM/fGd9oaPhjXTfoBBdJQn+GuLYNhcpUMBEa1W+F9MPzLobDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"385d6298eb5af7243d596eede4ac673e72727fcc1d816a5de03945502d39812b","last_reissued_at":"2026-07-01T00:17:13.453958Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T00:17:13.453958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ALM2Vec: Learning Audio Embeddings for Universal Audio Retrieval with Large Audio-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Aaron Yee, Chenang Jiang, Fengjie Lu, Helin Wang, Jiarui Hai","submitted_at":"2026-06-27T03:56:57Z","abstract_excerpt":"Recent advances in language--audio retrieval have been largely driven by contrastive dual-encoder architectures that align audio and text in a shared embedding space. While effective, existing retrieval embeddings are primarily optimized for audio--caption matching, limiting their ability to support diverse retrieval objectives and controllable retrieval behaviors. We present ALM2Vec, a universal audio embedding framework derived from pretrained large audio--language models (LALMs). By transferring the audio understanding, instruction-following, and reasoning capabilities acquired through larg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30682","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/2606.30682/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":"2606.30682","created_at":"2026-07-01T00:17:13.454024+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.30682v1","created_at":"2026-07-01T00:17:13.454024+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30682","created_at":"2026-07-01T00:17:13.454024+00:00"},{"alias_kind":"pith_short_12","alias_value":"HBOWFGHLLL3S","created_at":"2026-07-01T00:17:13.454024+00:00"},{"alias_kind":"pith_short_16","alias_value":"HBOWFGHLLL3SIPKZ","created_at":"2026-07-01T00:17:13.454024+00:00"},{"alias_kind":"pith_short_8","alias_value":"HBOWFGHL","created_at":"2026-07-01T00:17:13.454024+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/HBOWFGHLLL3SIPKZN3W6JLDHHZ","json":"https://pith.science/pith/HBOWFGHLLL3SIPKZN3W6JLDHHZ.json","graph_json":"https://pith.science/api/pith-number/HBOWFGHLLL3SIPKZN3W6JLDHHZ/graph.json","events_json":"https://pith.science/api/pith-number/HBOWFGHLLL3SIPKZN3W6JLDHHZ/events.json","paper":"https://pith.science/paper/HBOWFGHL"},"agent_actions":{"view_html":"https://pith.science/pith/HBOWFGHLLL3SIPKZN3W6JLDHHZ","download_json":"https://pith.science/pith/HBOWFGHLLL3SIPKZN3W6JLDHHZ.json","view_paper":"https://pith.science/paper/HBOWFGHL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.30682&json=true","fetch_graph":"https://pith.science/api/pith-number/HBOWFGHLLL3SIPKZN3W6JLDHHZ/graph.json","fetch_events":"https://pith.science/api/pith-number/HBOWFGHLLL3SIPKZN3W6JLDHHZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HBOWFGHLLL3SIPKZN3W6JLDHHZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HBOWFGHLLL3SIPKZN3W6JLDHHZ/action/storage_attestation","attest_author":"https://pith.science/pith/HBOWFGHLLL3SIPKZN3W6JLDHHZ/action/author_attestation","sign_citation":"https://pith.science/pith/HBOWFGHLLL3SIPKZN3W6JLDHHZ/action/citation_signature","submit_replication":"https://pith.science/pith/HBOWFGHLLL3SIPKZN3W6JLDHHZ/action/replication_record"}},"created_at":"2026-07-01T00:17:13.454024+00:00","updated_at":"2026-07-01T00:17:13.454024+00:00"}