{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:WNJMYKUHRMYOU4JFIHWAGQCGKQ","short_pith_number":"pith:WNJMYKUH","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"},"canonical_sha256":"b352cc2a878b30ea712541ec034046542b1bd306334e037d928eed7efad67082","source":{"kind":"arxiv","id":"1608.07017","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.07017","created_at":"2026-05-18T00:55:57Z"},{"alias_kind":"arxiv_version","alias_value":"1608.07017v2","created_at":"2026-05-18T00:55:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.07017","created_at":"2026-05-18T00:55:57Z"},{"alias_kind":"pith_short_12","alias_value":"WNJMYKUHRMYO","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_16","alias_value":"WNJMYKUHRMYOU4JF","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_8","alias_value":"WNJMYKUH","created_at":"2026-05-18T12:30:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:WNJMYKUHRMYOU4JFIHWAGQCGKQ","target":"record","payload":{"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"},"canonical_sha256":"b352cc2a878b30ea712541ec034046542b1bd306334e037d928eed7efad67082","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"},"source_kind":"arxiv","source_id":"1608.07017","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:55:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DKhvLF/oTdALl6NwsEOhUQwQznRuetgfPFZdkgrmsyCuN2WPlvLaHZ46lSdMVpM+6yunOFNB4U0VpKtisC6JDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T04:05:32.314331Z"},"content_sha256":"e4a69a62900ab34db5a69ac696a22572bfd6d7ed6b4f50dba7988371d817f849","schema_version":"1.0","event_id":"sha256:e4a69a62900ab34db5a69ac696a22572bfd6d7ed6b4f50dba7988371d817f849"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:WNJMYKUHRMYOU4JFIHWAGQCGKQ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:55:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/ptQf80+Dn0scpC9NrtS5J6398ebAjh20LTml6ht9+ongvnhCG5me6iHpgt/oqklIuJk92yGEgJegJ+7B1T6AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T04:05:32.314681Z"},"content_sha256":"f23291ca5128e6570ee3fb04d6450fe4024052e899897058b3ec5cb8cb30dc5c","schema_version":"1.0","event_id":"sha256:f23291ca5128e6570ee3fb04d6450fe4024052e899897058b3ec5cb8cb30dc5c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WNJMYKUHRMYOU4JFIHWAGQCGKQ/bundle.json","state_url":"https://pith.science/pith/WNJMYKUHRMYOU4JFIHWAGQCGKQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WNJMYKUHRMYOU4JFIHWAGQCGKQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T04:05:32Z","links":{"resolver":"https://pith.science/pith/WNJMYKUHRMYOU4JFIHWAGQCGKQ","bundle":"https://pith.science/pith/WNJMYKUHRMYOU4JFIHWAGQCGKQ/bundle.json","state":"https://pith.science/pith/WNJMYKUHRMYOU4JFIHWAGQCGKQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WNJMYKUHRMYOU4JFIHWAGQCGKQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:WNJMYKUHRMYOU4JFIHWAGQCGKQ","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":"d0d00d7d40865ef4db53bd9e36e83424a4a4490a6c652e2717c6fd5a31c22b80","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-08-25T04:50:16Z","title_canon_sha256":"8a0e02de52e66aa1f44e9d3b394b4162af42110998def95ab7f48651d38c52a3"},"schema_version":"1.0","source":{"id":"1608.07017","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.07017","created_at":"2026-05-18T00:55:57Z"},{"alias_kind":"arxiv_version","alias_value":"1608.07017v2","created_at":"2026-05-18T00:55:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.07017","created_at":"2026-05-18T00:55:57Z"},{"alias_kind":"pith_short_12","alias_value":"WNJMYKUHRMYO","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_16","alias_value":"WNJMYKUHRMYOU4JF","created_at":"2026-05-18T12:30:48Z"},{"alias_kind":"pith_short_8","alias_value":"WNJMYKUH","created_at":"2026-05-18T12:30:48Z"}],"graph_snapshots":[{"event_id":"sha256:f23291ca5128e6570ee3fb04d6450fe4024052e899897058b3ec5cb8cb30dc5c","target":"graph","created_at":"2026-05-18T00:55:57Z","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"},"paper":{"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","authors_text":"Andrew Owens, Antonio Torralba, Jiajun Wu, Josh H. McDermott, William T. Freeman","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-08-25T04:50:16Z","title":"Ambient Sound Provides Supervision for Visual Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.07017","kind":"arxiv","version":2},"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:e4a69a62900ab34db5a69ac696a22572bfd6d7ed6b4f50dba7988371d817f849","target":"record","created_at":"2026-05-18T00:55:57Z","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":"d0d00d7d40865ef4db53bd9e36e83424a4a4490a6c652e2717c6fd5a31c22b80","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-08-25T04:50:16Z","title_canon_sha256":"8a0e02de52e66aa1f44e9d3b394b4162af42110998def95ab7f48651d38c52a3"},"schema_version":"1.0","source":{"id":"1608.07017","kind":"arxiv","version":2}},"canonical_sha256":"b352cc2a878b30ea712541ec034046542b1bd306334e037d928eed7efad67082","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b352cc2a878b30ea712541ec034046542b1bd306334e037d928eed7efad67082","first_computed_at":"2026-05-18T00:55:57.721652Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:55:57.721652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cO7KT7g4gjNubHDy33uma0S1s0NIN0yoJvLOrqg+goHOcGs+sYSRa/O5osZdG9JyWI97EKPFwn1qBn1Rr3VjDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:55:57.722204Z","signed_message":"canonical_sha256_bytes"},"source_id":"1608.07017","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4a69a62900ab34db5a69ac696a22572bfd6d7ed6b4f50dba7988371d817f849","sha256:f23291ca5128e6570ee3fb04d6450fe4024052e899897058b3ec5cb8cb30dc5c"],"state_sha256":"ed0038f5c8532a1ef913bc2900e2986f5cdb43b5a6f65676b1de4c4a73025bd5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lq6w6lRESYi6v7y/Es551d0I6lCdlgD8bd34wTTVkkE5fWgp/vl3og8LlT7BR9MYyEUi4ufMkMf8dcyuOrUpCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T04:05:32.316722Z","bundle_sha256":"e21489ba729b622c6ba0773745959b870552c5cfc8b311aef69c4345a603177b"}}