{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:WNJMYKUHRMYOU4JFIHWAGQCGKQ","short_pith_number":"pith:WNJMYKUH","schema_version":"1.0","canonical_sha256":"b352cc2a878b30ea712541ec034046542b1bd306334e037d928eed7efad67082","source":{"kind":"arxiv","id":"1608.07017","version":2},"attestation_state":"computed","paper":{"title":"Ambient Sound Provides Supervision for Visual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Owens, Antonio Torralba, Jiajun Wu, Josh H. McDermott, William T. Freeman","submitted_at":"2016-08-25T04:50:16Z","abstract_excerpt":"The sound of crashing waves, the roar of fast-moving cars -- sound conveys important information about the objects in our surroundings. In this work, we show that ambient sounds can be used as a supervisory signal for learning visual models. To demonstrate this, we train a convolutional neural network to predict a statistical summary of the sound associated with a video frame. We show that, through this process, the network learns a representation that conveys information about objects and scenes. We evaluate this representation on several recognition tasks, finding that its performance is com"},"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":"1608.07017","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-08-25T04:50:16Z","cross_cats_sorted":[],"title_canon_sha256":"8a0e02de52e66aa1f44e9d3b394b4162af42110998def95ab7f48651d38c52a3","abstract_canon_sha256":"d0d00d7d40865ef4db53bd9e36e83424a4a4490a6c652e2717c6fd5a31c22b80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:55:57.722204Z","signature_b64":"cO7KT7g4gjNubHDy33uma0S1s0NIN0yoJvLOrqg+goHOcGs+sYSRa/O5osZdG9JyWI97EKPFwn1qBn1Rr3VjDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b352cc2a878b30ea712541ec034046542b1bd306334e037d928eed7efad67082","last_reissued_at":"2026-05-18T00:55:57.721652Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:55:57.721652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ambient Sound Provides Supervision for Visual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew Owens, Antonio Torralba, Jiajun Wu, Josh H. McDermott, William T. Freeman","submitted_at":"2016-08-25T04:50:16Z","abstract_excerpt":"The sound of crashing waves, the roar of fast-moving cars -- sound conveys important information about the objects in our surroundings. In this work, we show that ambient sounds can be used as a supervisory signal for learning visual models. To demonstrate this, we train a convolutional neural network to predict a statistical summary of the sound associated with a video frame. We show that, through this process, the network learns a representation that conveys information about objects and scenes. We evaluate this representation on several recognition tasks, finding that its performance is com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.07017","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1608.07017","created_at":"2026-05-18T00:55:57.721727+00:00"},{"alias_kind":"arxiv_version","alias_value":"1608.07017v2","created_at":"2026-05-18T00:55:57.721727+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.07017","created_at":"2026-05-18T00:55:57.721727+00:00"},{"alias_kind":"pith_short_12","alias_value":"WNJMYKUHRMYO","created_at":"2026-05-18T12:30:48.956258+00:00"},{"alias_kind":"pith_short_16","alias_value":"WNJMYKUHRMYOU4JF","created_at":"2026-05-18T12:30:48.956258+00:00"},{"alias_kind":"pith_short_8","alias_value":"WNJMYKUH","created_at":"2026-05-18T12:30:48.956258+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/WNJMYKUHRMYOU4JFIHWAGQCGKQ","json":"https://pith.science/pith/WNJMYKUHRMYOU4JFIHWAGQCGKQ.json","graph_json":"https://pith.science/api/pith-number/WNJMYKUHRMYOU4JFIHWAGQCGKQ/graph.json","events_json":"https://pith.science/api/pith-number/WNJMYKUHRMYOU4JFIHWAGQCGKQ/events.json","paper":"https://pith.science/paper/WNJMYKUH"},"agent_actions":{"view_html":"https://pith.science/pith/WNJMYKUHRMYOU4JFIHWAGQCGKQ","download_json":"https://pith.science/pith/WNJMYKUHRMYOU4JFIHWAGQCGKQ.json","view_paper":"https://pith.science/paper/WNJMYKUH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1608.07017&json=true","fetch_graph":"https://pith.science/api/pith-number/WNJMYKUHRMYOU4JFIHWAGQCGKQ/graph.json","fetch_events":"https://pith.science/api/pith-number/WNJMYKUHRMYOU4JFIHWAGQCGKQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WNJMYKUHRMYOU4JFIHWAGQCGKQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WNJMYKUHRMYOU4JFIHWAGQCGKQ/action/storage_attestation","attest_author":"https://pith.science/pith/WNJMYKUHRMYOU4JFIHWAGQCGKQ/action/author_attestation","sign_citation":"https://pith.science/pith/WNJMYKUHRMYOU4JFIHWAGQCGKQ/action/citation_signature","submit_replication":"https://pith.science/pith/WNJMYKUHRMYOU4JFIHWAGQCGKQ/action/replication_record"}},"created_at":"2026-05-18T00:55:57.721727+00:00","updated_at":"2026-05-18T00:55:57.721727+00:00"}