{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ZPCYQ2YDUOUNCVIUG57XLQ5JXJ","short_pith_number":"pith:ZPCYQ2YD","canonical_record":{"source":{"id":"1804.01665","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-05T04:06:46Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"21726b302d57e03720ff43f3cb89c5b113270fe9cccb0bb8ac003ed3a8d20576","abstract_canon_sha256":"2116d29a9a7ff5776370b680712c89d36a64cdf0535e2c07def84ca263aa3515"},"schema_version":"1.0"},"canonical_sha256":"cbc5886b03a3a8d15514377f75c3a9ba78f3043be47e28f5049da6c11996a524","source":{"kind":"arxiv","id":"1804.01665","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.01665","created_at":"2026-05-18T00:09:47Z"},{"alias_kind":"arxiv_version","alias_value":"1804.01665v2","created_at":"2026-05-18T00:09:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.01665","created_at":"2026-05-18T00:09:47Z"},{"alias_kind":"pith_short_12","alias_value":"ZPCYQ2YDUOUN","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZPCYQ2YDUOUNCVIU","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZPCYQ2YD","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ZPCYQ2YDUOUNCVIUG57XLQ5JXJ","target":"record","payload":{"canonical_record":{"source":{"id":"1804.01665","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-05T04:06:46Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"21726b302d57e03720ff43f3cb89c5b113270fe9cccb0bb8ac003ed3a8d20576","abstract_canon_sha256":"2116d29a9a7ff5776370b680712c89d36a64cdf0535e2c07def84ca263aa3515"},"schema_version":"1.0"},"canonical_sha256":"cbc5886b03a3a8d15514377f75c3a9ba78f3043be47e28f5049da6c11996a524","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:47.129892Z","signature_b64":"NwTPyPMJIvP8k0z5TIrBy/HObEw9mnpA0apkloLi7CU3ROCKhuurpKMsftbE2F80s/yGwCz6as6K6uAcNJkOAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbc5886b03a3a8d15514377f75c3a9ba78f3043be47e28f5049da6c11996a524","last_reissued_at":"2026-05-18T00:09:47.129378Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:47.129378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.01665","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":"2026-05-18T00:09:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y0CDkfQlJ71Fp/Eh95ijW40TMzDuIuUIRPgcUS3xNK+OpvE28LJvofQyuw039HkZXDv2PcW0ncX0lHwd5HNqCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T06:35:17.302910Z"},"content_sha256":"fcec243db4db3331d05398366afb2704680a85b4c3c34002b58ee61be48f8876","schema_version":"1.0","event_id":"sha256:fcec243db4db3331d05398366afb2704680a85b4c3c34002b58ee61be48f8876"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ZPCYQ2YDUOUNCVIUG57XLQ5JXJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Separate Object Sounds by Watching Unlabeled Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Kristen Grauman, Rogerio Feris, Ruohan Gao","submitted_at":"2018-04-05T04:06:46Z","abstract_excerpt":"Perceiving a scene most fully requires all the senses. Yet modeling how objects look and sound is challenging: most natural scenes and events contain multiple objects, and the audio track mixes all the sound sources together. We propose to learn audio-visual object models from unlabeled video, then exploit the visual context to perform audio source separation in novel videos. Our approach relies on a deep multi-instance multi-label learning framework to disentangle the audio frequency bases that map to individual visual objects, even without observing/hearing those objects in isolation. We sho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.01665","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":"2026-05-18T00:09:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kiHJ8zKJ2tiO9xgKqEhja/DBH6glIOKQ3echUQPq4PCILP5c3mT9Twmc87jwfnw+iBsWcR2rMLU0U/L30S1sBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T06:35:17.303777Z"},"content_sha256":"63ae389f09704cdb1a4422f732591ca4ef4574225b41656f0382c0a6c64a1528","schema_version":"1.0","event_id":"sha256:63ae389f09704cdb1a4422f732591ca4ef4574225b41656f0382c0a6c64a1528"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZPCYQ2YDUOUNCVIUG57XLQ5JXJ/bundle.json","state_url":"https://pith.science/pith/ZPCYQ2YDUOUNCVIUG57XLQ5JXJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZPCYQ2YDUOUNCVIUG57XLQ5JXJ/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":"2026-08-12T06:35:17Z","links":{"resolver":"https://pith.science/pith/ZPCYQ2YDUOUNCVIUG57XLQ5JXJ","bundle":"https://pith.science/pith/ZPCYQ2YDUOUNCVIUG57XLQ5JXJ/bundle.json","state":"https://pith.science/pith/ZPCYQ2YDUOUNCVIUG57XLQ5JXJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZPCYQ2YDUOUNCVIUG57XLQ5JXJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ZPCYQ2YDUOUNCVIUG57XLQ5JXJ","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":"2116d29a9a7ff5776370b680712c89d36a64cdf0535e2c07def84ca263aa3515","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-05T04:06:46Z","title_canon_sha256":"21726b302d57e03720ff43f3cb89c5b113270fe9cccb0bb8ac003ed3a8d20576"},"schema_version":"1.0","source":{"id":"1804.01665","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.01665","created_at":"2026-05-18T00:09:47Z"},{"alias_kind":"arxiv_version","alias_value":"1804.01665v2","created_at":"2026-05-18T00:09:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.01665","created_at":"2026-05-18T00:09:47Z"},{"alias_kind":"pith_short_12","alias_value":"ZPCYQ2YDUOUN","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZPCYQ2YDUOUNCVIU","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZPCYQ2YD","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:63ae389f09704cdb1a4422f732591ca4ef4574225b41656f0382c0a6c64a1528","target":"graph","created_at":"2026-05-18T00:09:47Z","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":"Perceiving a scene most fully requires all the senses. Yet modeling how objects look and sound is challenging: most natural scenes and events contain multiple objects, and the audio track mixes all the sound sources together. We propose to learn audio-visual object models from unlabeled video, then exploit the visual context to perform audio source separation in novel videos. Our approach relies on a deep multi-instance multi-label learning framework to disentangle the audio frequency bases that map to individual visual objects, even without observing/hearing those objects in isolation. We sho","authors_text":"Kristen Grauman, Rogerio Feris, Ruohan Gao","cross_cats":["cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-05T04:06:46Z","title":"Learning to Separate Object Sounds by Watching Unlabeled Video"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.01665","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:fcec243db4db3331d05398366afb2704680a85b4c3c34002b58ee61be48f8876","target":"record","created_at":"2026-05-18T00:09:47Z","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":"2116d29a9a7ff5776370b680712c89d36a64cdf0535e2c07def84ca263aa3515","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-05T04:06:46Z","title_canon_sha256":"21726b302d57e03720ff43f3cb89c5b113270fe9cccb0bb8ac003ed3a8d20576"},"schema_version":"1.0","source":{"id":"1804.01665","kind":"arxiv","version":2}},"canonical_sha256":"cbc5886b03a3a8d15514377f75c3a9ba78f3043be47e28f5049da6c11996a524","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cbc5886b03a3a8d15514377f75c3a9ba78f3043be47e28f5049da6c11996a524","first_computed_at":"2026-05-18T00:09:47.129378Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:09:47.129378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NwTPyPMJIvP8k0z5TIrBy/HObEw9mnpA0apkloLi7CU3ROCKhuurpKMsftbE2F80s/yGwCz6as6K6uAcNJkOAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:09:47.129892Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.01665","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fcec243db4db3331d05398366afb2704680a85b4c3c34002b58ee61be48f8876","sha256:63ae389f09704cdb1a4422f732591ca4ef4574225b41656f0382c0a6c64a1528"],"state_sha256":"6e70064e61be0c563e33bcd20778137875df9ba444da991fd48bcdaf7a4bd9bc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6vy3lsgb/OhR4S/1pE5kFbFc2MGpzA2uCO+lDpoQySoEo536r7/+bqF8gFRebi8OY6/EqkZOXXjVyi8W/TosCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T06:35:17.309698Z","bundle_sha256":"a0568723214e3a62de68669310f7cf8ed80519de299c4a010f4c38f415d932c1"}}