{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:HBOWFGHLLL3SIPKZN3W6JLDHHZ","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":"f927f01eb93a9afa73d4005ef8094ed9cce5a085ee9064c35ef3c2447eec6401","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-27T03:56:57Z","title_canon_sha256":"d12aef9174011b1d7bf1c92bc16e1a5434d787b5317cabdce7c9d81fae96c2dd"},"schema_version":"1.0","source":{"id":"2606.30682","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30682","created_at":"2026-07-01T00:17:13Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30682v1","created_at":"2026-07-01T00:17:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30682","created_at":"2026-07-01T00:17:13Z"},{"alias_kind":"pith_short_12","alias_value":"HBOWFGHLLL3S","created_at":"2026-07-01T00:17:13Z"},{"alias_kind":"pith_short_16","alias_value":"HBOWFGHLLL3SIPKZ","created_at":"2026-07-01T00:17:13Z"},{"alias_kind":"pith_short_8","alias_value":"HBOWFGHL","created_at":"2026-07-01T00:17:13Z"}],"graph_snapshots":[{"event_id":"sha256:4febc1b6f649fbd1816738f3b2bd8091d4d9e4864b5991fd30cbce88d70f5639","target":"graph","created_at":"2026-07-01T00:17:13Z","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/2606.30682/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aaron Yee, Chenang Jiang, Fengjie Lu, Helin Wang, Jiarui Hai","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-27T03:56:57Z","title":"ALM2Vec: Learning Audio Embeddings for Universal Audio Retrieval with Large Audio-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30682","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":"sha256:09fbc29cf622f9e319fb8f97e76934dea00a11fdd12ef4550c15592031d34f43","target":"record","created_at":"2026-07-01T00:17:13Z","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":"f927f01eb93a9afa73d4005ef8094ed9cce5a085ee9064c35ef3c2447eec6401","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-27T03:56:57Z","title_canon_sha256":"d12aef9174011b1d7bf1c92bc16e1a5434d787b5317cabdce7c9d81fae96c2dd"},"schema_version":"1.0","source":{"id":"2606.30682","kind":"arxiv","version":1}},"canonical_sha256":"385d6298eb5af7243d596eede4ac673e72727fcc1d816a5de03945502d39812b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"385d6298eb5af7243d596eede4ac673e72727fcc1d816a5de03945502d39812b","first_computed_at":"2026-07-01T00:17:13.453958Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T00:17:13.453958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ppm2nk2pCwv90y6i+2rq+lAnlcAvCayVqC6RXZM/fGd9oaPhjXTfoBBdJQn+GuLYNhcpUMBEa1W+F9MPzLobDQ==","signature_status":"signed_v1","signed_at":"2026-07-01T00:17:13.454479Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.30682","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09fbc29cf622f9e319fb8f97e76934dea00a11fdd12ef4550c15592031d34f43","sha256:4febc1b6f649fbd1816738f3b2bd8091d4d9e4864b5991fd30cbce88d70f5639"],"state_sha256":"e1181b3bf6c8e3bea673cd0576a95c01c6fd7b6d626464108baa625486524238"}