{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:E4LRRRQ5JVDOC7HENUAHERGM4Q","short_pith_number":"pith:E4LRRRQ5","schema_version":"1.0","canonical_sha256":"271718c61d4d46e17ce46d007244cce40fa9e8e0c61e932a087dfff1d7060f1a","source":{"kind":"arxiv","id":"2606.05544","version":1},"attestation_state":"computed","paper":{"title":"Probing Spatial Structure in Pretrained Audio Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Adrian S. Roman, Chuyang Chen, Juan Pablo Bello, Sivan Ding","submitted_at":"2026-06-04T00:58:16Z","abstract_excerpt":"Pretrained spatial audio encoders are increasingly used as general-purpose representations for perceptual tasks, yet their spatial encoding capabilities remain poorly understood. We introduce the Spatial Audio Representation Learning (SARL) benchmark, a controlled framework for evaluating spatial information in pretrained audio models. SARL probes source-level factors (azimuth, elevation, distance, class) and room-level factors (RT60, volume, shape). Experiments across diverse encoders reveal three patterns: input configuration and training paradigm shape spatial encoding; source factors are c"},"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":"2606.05544","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-04T00:58:16Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"01cc7a8e19719e8fa405ac8622a1a65404350bb9de5a7fe852a439c2c7a427a9","abstract_canon_sha256":"82b2b1117ac070c60c585a0ed2de063c529c81ac75ce7e9d2c2f3fdebdef8351"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:14:54.343057Z","signature_b64":"JSgsisSFOCOe74PA4INDOmFVexcKpAcQBES7mu590G0tkWoPSwb77jvQOgZjaOk1iUiXGQrN0xG6/TC/RqqjBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"271718c61d4d46e17ce46d007244cce40fa9e8e0c61e932a087dfff1d7060f1a","last_reissued_at":"2026-06-05T01:14:54.342605Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:14:54.342605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probing Spatial Structure in Pretrained Audio Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Adrian S. Roman, Chuyang Chen, Juan Pablo Bello, Sivan Ding","submitted_at":"2026-06-04T00:58:16Z","abstract_excerpt":"Pretrained spatial audio encoders are increasingly used as general-purpose representations for perceptual tasks, yet their spatial encoding capabilities remain poorly understood. We introduce the Spatial Audio Representation Learning (SARL) benchmark, a controlled framework for evaluating spatial information in pretrained audio models. SARL probes source-level factors (azimuth, elevation, distance, class) and room-level factors (RT60, volume, shape). Experiments across diverse encoders reveal three patterns: input configuration and training paradigm shape spatial encoding; source factors are c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05544","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/2606.05544/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":"2606.05544","created_at":"2026-06-05T01:14:54.342674+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05544v1","created_at":"2026-06-05T01:14:54.342674+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05544","created_at":"2026-06-05T01:14:54.342674+00:00"},{"alias_kind":"pith_short_12","alias_value":"E4LRRRQ5JVDO","created_at":"2026-06-05T01:14:54.342674+00:00"},{"alias_kind":"pith_short_16","alias_value":"E4LRRRQ5JVDOC7HE","created_at":"2026-06-05T01:14:54.342674+00:00"},{"alias_kind":"pith_short_8","alias_value":"E4LRRRQ5","created_at":"2026-06-05T01:14:54.342674+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/E4LRRRQ5JVDOC7HENUAHERGM4Q","json":"https://pith.science/pith/E4LRRRQ5JVDOC7HENUAHERGM4Q.json","graph_json":"https://pith.science/api/pith-number/E4LRRRQ5JVDOC7HENUAHERGM4Q/graph.json","events_json":"https://pith.science/api/pith-number/E4LRRRQ5JVDOC7HENUAHERGM4Q/events.json","paper":"https://pith.science/paper/E4LRRRQ5"},"agent_actions":{"view_html":"https://pith.science/pith/E4LRRRQ5JVDOC7HENUAHERGM4Q","download_json":"https://pith.science/pith/E4LRRRQ5JVDOC7HENUAHERGM4Q.json","view_paper":"https://pith.science/paper/E4LRRRQ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05544&json=true","fetch_graph":"https://pith.science/api/pith-number/E4LRRRQ5JVDOC7HENUAHERGM4Q/graph.json","fetch_events":"https://pith.science/api/pith-number/E4LRRRQ5JVDOC7HENUAHERGM4Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E4LRRRQ5JVDOC7HENUAHERGM4Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E4LRRRQ5JVDOC7HENUAHERGM4Q/action/storage_attestation","attest_author":"https://pith.science/pith/E4LRRRQ5JVDOC7HENUAHERGM4Q/action/author_attestation","sign_citation":"https://pith.science/pith/E4LRRRQ5JVDOC7HENUAHERGM4Q/action/citation_signature","submit_replication":"https://pith.science/pith/E4LRRRQ5JVDOC7HENUAHERGM4Q/action/replication_record"}},"created_at":"2026-06-05T01:14:54.342674+00:00","updated_at":"2026-06-05T01:14:54.342674+00:00"}