{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WITV6MUA5QM4G52O546CD47DCY","short_pith_number":"pith:WITV6MUA","schema_version":"1.0","canonical_sha256":"b2275f3280ec19c3774eef3c21f3e3163f34ab6322ed9adee899d337007ae0ff","source":{"kind":"arxiv","id":"2204.12489","version":3},"attestation_state":"computed","paper":{"title":"Sound Localization by Self-Supervised Time Delay Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Andrew Owens, David F. Fouhey, Ziyang Chen","submitted_at":"2022-04-26T17:59:01Z","abstract_excerpt":"Sounds reach one microphone in a stereo pair sooner than the other, resulting in an interaural time delay that conveys their directions. Estimating a sound's time delay requires finding correspondences between the signals recorded by each microphone. We propose to learn these correspondences through self-supervision, drawing on recent techniques from visual tracking. We adapt the contrastive random walk of Jabri et al. to learn a cycle-consistent representation from unlabeled stereo sounds, resulting in a model that performs on par with supervised methods on \"in the wild\" internet recordings. "},"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":"2204.12489","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-04-26T17:59:01Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"ad8d5c80cc3e1dd559294a8ed330a62a7007440b6cf40723a0fc4f3eb25fe953","abstract_canon_sha256":"b6985f86e15722272b411556bfa4f7e3d336e298890673d34acff32272b0742b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:30.216341Z","signature_b64":"6jFDP/Ql/UfUUDFCK1ArwYIX5dpdqvpIkziSQyFnaUPB5QBm/SCby4/QB8ru6E9njA7egJV+tJfKRih8LmR/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2275f3280ec19c3774eef3c21f3e3163f34ab6322ed9adee899d337007ae0ff","last_reissued_at":"2026-07-05T05:36:30.215838Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:30.215838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sound Localization by Self-Supervised Time Delay Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Andrew Owens, David F. Fouhey, Ziyang Chen","submitted_at":"2022-04-26T17:59:01Z","abstract_excerpt":"Sounds reach one microphone in a stereo pair sooner than the other, resulting in an interaural time delay that conveys their directions. Estimating a sound's time delay requires finding correspondences between the signals recorded by each microphone. We propose to learn these correspondences through self-supervision, drawing on recent techniques from visual tracking. We adapt the contrastive random walk of Jabri et al. to learn a cycle-consistent representation from unlabeled stereo sounds, resulting in a model that performs on par with supervised methods on \"in the wild\" internet recordings. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.12489","kind":"arxiv","version":3},"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/2204.12489/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":"2204.12489","created_at":"2026-07-05T05:36:30.215898+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.12489v3","created_at":"2026-07-05T05:36:30.215898+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.12489","created_at":"2026-07-05T05:36:30.215898+00:00"},{"alias_kind":"pith_short_12","alias_value":"WITV6MUA5QM4","created_at":"2026-07-05T05:36:30.215898+00:00"},{"alias_kind":"pith_short_16","alias_value":"WITV6MUA5QM4G52O","created_at":"2026-07-05T05:36:30.215898+00:00"},{"alias_kind":"pith_short_8","alias_value":"WITV6MUA","created_at":"2026-07-05T05:36:30.215898+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/WITV6MUA5QM4G52O546CD47DCY","json":"https://pith.science/pith/WITV6MUA5QM4G52O546CD47DCY.json","graph_json":"https://pith.science/api/pith-number/WITV6MUA5QM4G52O546CD47DCY/graph.json","events_json":"https://pith.science/api/pith-number/WITV6MUA5QM4G52O546CD47DCY/events.json","paper":"https://pith.science/paper/WITV6MUA"},"agent_actions":{"view_html":"https://pith.science/pith/WITV6MUA5QM4G52O546CD47DCY","download_json":"https://pith.science/pith/WITV6MUA5QM4G52O546CD47DCY.json","view_paper":"https://pith.science/paper/WITV6MUA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.12489&json=true","fetch_graph":"https://pith.science/api/pith-number/WITV6MUA5QM4G52O546CD47DCY/graph.json","fetch_events":"https://pith.science/api/pith-number/WITV6MUA5QM4G52O546CD47DCY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WITV6MUA5QM4G52O546CD47DCY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WITV6MUA5QM4G52O546CD47DCY/action/storage_attestation","attest_author":"https://pith.science/pith/WITV6MUA5QM4G52O546CD47DCY/action/author_attestation","sign_citation":"https://pith.science/pith/WITV6MUA5QM4G52O546CD47DCY/action/citation_signature","submit_replication":"https://pith.science/pith/WITV6MUA5QM4G52O546CD47DCY/action/replication_record"}},"created_at":"2026-07-05T05:36:30.215898+00:00","updated_at":"2026-07-05T05:36:30.215898+00:00"}