{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:R6GHAHY77IUSZD7VVHB6NZZEYW","short_pith_number":"pith:R6GHAHY7","canonical_record":{"source":{"id":"1712.07271","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-20T00:10:40Z","cross_cats_sorted":[],"title_canon_sha256":"6b1caabf8f4b215bb06ee8be96145715ff407d8cc0b5f1dbfeb3d3faf0262d9a","abstract_canon_sha256":"75aa9b828aa952e46a37cb61cd69de7d2e6883493527497fa83cdb390670e81e"},"schema_version":"1.0"},"canonical_sha256":"8f8c701f1ffa292c8ff5a9c3e6e724c5b0722232114a85eeaa58f4eedd1043d7","source":{"kind":"arxiv","id":"1712.07271","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.07271","created_at":"2026-05-18T00:27:35Z"},{"alias_kind":"arxiv_version","alias_value":"1712.07271v1","created_at":"2026-05-18T00:27:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.07271","created_at":"2026-05-18T00:27:35Z"},{"alias_kind":"pith_short_12","alias_value":"R6GHAHY77IUS","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"R6GHAHY77IUSZD7V","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"R6GHAHY7","created_at":"2026-05-18T12:31:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:R6GHAHY77IUSZD7VVHB6NZZEYW","target":"record","payload":{"canonical_record":{"source":{"id":"1712.07271","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-20T00:10:40Z","cross_cats_sorted":[],"title_canon_sha256":"6b1caabf8f4b215bb06ee8be96145715ff407d8cc0b5f1dbfeb3d3faf0262d9a","abstract_canon_sha256":"75aa9b828aa952e46a37cb61cd69de7d2e6883493527497fa83cdb390670e81e"},"schema_version":"1.0"},"canonical_sha256":"8f8c701f1ffa292c8ff5a9c3e6e724c5b0722232114a85eeaa58f4eedd1043d7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:35.012399Z","signature_b64":"Ce/QwQPXeWzCJ106BbQZ4235In1S7A2/06jNqLlryILXL9Tflqgei/7b7ksDvkuysC9WwVSjy+qO2kKdqgRDDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f8c701f1ffa292c8ff5a9c3e6e724c5b0722232114a85eeaa58f4eedd1043d7","last_reissued_at":"2026-05-18T00:27:35.011867Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:35.011867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.07271","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:27:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J/Wnf+gNnTLmpKmPbgutNJV6wglzXoYwY0iiwiAmr9pT/txC+BMF2EE5qbOVaqDmNP72LBWOFUyZf5km8R9hAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T17:27:31.290333Z"},"content_sha256":"ee4cb5d24fecd153fdbfdeaae7c07ae49d47e7af59eeb496ac492817315f15f0","schema_version":"1.0","event_id":"sha256:ee4cb5d24fecd153fdbfdeaae7c07ae49d47e7af59eeb496ac492817315f15f0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:R6GHAHY77IUSZD7VVHB6NZZEYW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Sight from Sound: 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":"2017-12-20T00:10:40Z","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":"1712.07271","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":""},"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":"2026-05-18T00:27:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qxYLqHndrq1Qpa/K5If69vyC5kkHUMZx4b+IBH17bz8sA/Wp+Lk0OUOA1zqQzbc8tFlTYjNB9wdpbYySlAtzCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T17:27:31.290693Z"},"content_sha256":"9fd64fbec46394cb1d4fbab3854046c257536705f485e0382f8c756b79285669","schema_version":"1.0","event_id":"sha256:9fd64fbec46394cb1d4fbab3854046c257536705f485e0382f8c756b79285669"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R6GHAHY77IUSZD7VVHB6NZZEYW/bundle.json","state_url":"https://pith.science/pith/R6GHAHY77IUSZD7VVHB6NZZEYW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R6GHAHY77IUSZD7VVHB6NZZEYW/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":"2026-05-30T17:27:31Z","links":{"resolver":"https://pith.science/pith/R6GHAHY77IUSZD7VVHB6NZZEYW","bundle":"https://pith.science/pith/R6GHAHY77IUSZD7VVHB6NZZEYW/bundle.json","state":"https://pith.science/pith/R6GHAHY77IUSZD7VVHB6NZZEYW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R6GHAHY77IUSZD7VVHB6NZZEYW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:R6GHAHY77IUSZD7VVHB6NZZEYW","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":"75aa9b828aa952e46a37cb61cd69de7d2e6883493527497fa83cdb390670e81e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-20T00:10:40Z","title_canon_sha256":"6b1caabf8f4b215bb06ee8be96145715ff407d8cc0b5f1dbfeb3d3faf0262d9a"},"schema_version":"1.0","source":{"id":"1712.07271","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.07271","created_at":"2026-05-18T00:27:35Z"},{"alias_kind":"arxiv_version","alias_value":"1712.07271v1","created_at":"2026-05-18T00:27:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.07271","created_at":"2026-05-18T00:27:35Z"},{"alias_kind":"pith_short_12","alias_value":"R6GHAHY77IUS","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"R6GHAHY77IUSZD7V","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"R6GHAHY7","created_at":"2026-05-18T12:31:39Z"}],"graph_snapshots":[{"event_id":"sha256:9fd64fbec46394cb1d4fbab3854046c257536705f485e0382f8c756b79285669","target":"graph","created_at":"2026-05-18T00:27:35Z","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":"2017-12-20T00:10:40Z","title":"Learning Sight from Sound: Ambient Sound Provides Supervision for Visual Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.07271","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:ee4cb5d24fecd153fdbfdeaae7c07ae49d47e7af59eeb496ac492817315f15f0","target":"record","created_at":"2026-05-18T00:27:35Z","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":"75aa9b828aa952e46a37cb61cd69de7d2e6883493527497fa83cdb390670e81e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-20T00:10:40Z","title_canon_sha256":"6b1caabf8f4b215bb06ee8be96145715ff407d8cc0b5f1dbfeb3d3faf0262d9a"},"schema_version":"1.0","source":{"id":"1712.07271","kind":"arxiv","version":1}},"canonical_sha256":"8f8c701f1ffa292c8ff5a9c3e6e724c5b0722232114a85eeaa58f4eedd1043d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f8c701f1ffa292c8ff5a9c3e6e724c5b0722232114a85eeaa58f4eedd1043d7","first_computed_at":"2026-05-18T00:27:35.011867Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:27:35.011867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ce/QwQPXeWzCJ106BbQZ4235In1S7A2/06jNqLlryILXL9Tflqgei/7b7ksDvkuysC9WwVSjy+qO2kKdqgRDDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:27:35.012399Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.07271","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee4cb5d24fecd153fdbfdeaae7c07ae49d47e7af59eeb496ac492817315f15f0","sha256:9fd64fbec46394cb1d4fbab3854046c257536705f485e0382f8c756b79285669"],"state_sha256":"01103387fe59e85f1e779e022f116a0dcfa1740e8b912599820198aa32b38d11"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PjWjLlWcOuh8+toI1VfFxtuzzv57GyCKcF8ESJYnTroy+eDxCHB2nJPEsZqHkuj86N3owRfdGLI8tV9d7m4JAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T17:27:31.292786Z","bundle_sha256":"811177a599f9d1f8817124005af5d196072dede002120884be6259f58abd566a"}}