{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:VHEJ7UQDFUDETF7BRQJ4BNHH6O","short_pith_number":"pith:VHEJ7UQD","canonical_record":{"source":{"id":"1807.03094","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-09T13:13:10Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"6dce7085ddf5d9a50eb6b20708e790a9d5ce970e5fdc1694ffe5e0c1a68b473a","abstract_canon_sha256":"75df81e2dba691c46e03cdedf5f63f32de155a0a281a81f02639fb63563f3076"},"schema_version":"1.0"},"canonical_sha256":"a9c89fd2032d064997e18c13c0b4e7f3839382a5bd9d7f062cf8f5cf48057a8f","source":{"kind":"arxiv","id":"1807.03094","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.03094","created_at":"2026-05-17T23:48:11Z"},{"alias_kind":"arxiv_version","alias_value":"1807.03094v3","created_at":"2026-05-17T23:48:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.03094","created_at":"2026-05-17T23:48:11Z"},{"alias_kind":"pith_short_12","alias_value":"VHEJ7UQDFUDE","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VHEJ7UQDFUDETF7B","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VHEJ7UQD","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:VHEJ7UQDFUDETF7BRQJ4BNHH6O","target":"record","payload":{"canonical_record":{"source":{"id":"1807.03094","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-09T13:13:10Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"6dce7085ddf5d9a50eb6b20708e790a9d5ce970e5fdc1694ffe5e0c1a68b473a","abstract_canon_sha256":"75df81e2dba691c46e03cdedf5f63f32de155a0a281a81f02639fb63563f3076"},"schema_version":"1.0"},"canonical_sha256":"a9c89fd2032d064997e18c13c0b4e7f3839382a5bd9d7f062cf8f5cf48057a8f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:11.609008Z","signature_b64":"GJHEfVOON9xhW9apIurCFnYGNXOu8iJp2B8hpOpk0fMTWUZ8IbwS1YO3zHrXRi0jRM0ppkXrIp48BZWt0s5TDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9c89fd2032d064997e18c13c0b4e7f3839382a5bd9d7f062cf8f5cf48057a8f","last_reissued_at":"2026-05-17T23:48:11.608346Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:11.608346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.03094","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:48:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c28LiOjhQ/aQRs2pa5jYQEpi+mz1STFQScW3OO7DNpoywyJNR3qny3kY8V2J2N3k8cHGPrXTTnJWIFa30Q/sBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T09:07:35.494940Z"},"content_sha256":"65cf5ae9074a519cb1bedb6b34f401303656e2910a24d32fb2352d5c7cb97d2e","schema_version":"1.0","event_id":"sha256:65cf5ae9074a519cb1bedb6b34f401303656e2910a24d32fb2352d5c7cb97d2e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:VHEJ7UQDFUDETF7BRQJ4BNHH6O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Multimodal Clustering for Unsupervised Audiovisual Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Di Hu, Feiping Nie, Xuelong Li","submitted_at":"2018-07-09T13:13:10Z","abstract_excerpt":"The seen birds twitter, the running cars accompany with noise, etc. These naturally audiovisual correspondences provide the possibilities to explore and understand the outside world. However, the mixed multiple objects and sounds make it intractable to perform efficient matching in the unconstrained environment. To settle this problem, we propose to adequately excavate audio and visual components and perform elaborate correspondence learning among them. Concretely, a novel unsupervised audiovisual learning model is proposed, named as \\Deep Multimodal Clustering (DMC), that synchronously perfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.03094","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":""},"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":"2026-05-17T23:48:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hwKpG1VNE55fNBA7G4Gy1GggHHyz1zZLLXkXqNDkwk/OM9j/Tq5pfykZRT0dmmpMKbF9LB7zeJTYqDYu4jTUCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T09:07:35.495303Z"},"content_sha256":"e5d07a27750e33a3b3d78187bb2dac7fa8262218fa0f0eb4b2cc7e1de60acf06","schema_version":"1.0","event_id":"sha256:e5d07a27750e33a3b3d78187bb2dac7fa8262218fa0f0eb4b2cc7e1de60acf06"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VHEJ7UQDFUDETF7BRQJ4BNHH6O/bundle.json","state_url":"https://pith.science/pith/VHEJ7UQDFUDETF7BRQJ4BNHH6O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VHEJ7UQDFUDETF7BRQJ4BNHH6O/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":"2026-06-06T09:07:35Z","links":{"resolver":"https://pith.science/pith/VHEJ7UQDFUDETF7BRQJ4BNHH6O","bundle":"https://pith.science/pith/VHEJ7UQDFUDETF7BRQJ4BNHH6O/bundle.json","state":"https://pith.science/pith/VHEJ7UQDFUDETF7BRQJ4BNHH6O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VHEJ7UQDFUDETF7BRQJ4BNHH6O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:VHEJ7UQDFUDETF7BRQJ4BNHH6O","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":"75df81e2dba691c46e03cdedf5f63f32de155a0a281a81f02639fb63563f3076","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-09T13:13:10Z","title_canon_sha256":"6dce7085ddf5d9a50eb6b20708e790a9d5ce970e5fdc1694ffe5e0c1a68b473a"},"schema_version":"1.0","source":{"id":"1807.03094","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.03094","created_at":"2026-05-17T23:48:11Z"},{"alias_kind":"arxiv_version","alias_value":"1807.03094v3","created_at":"2026-05-17T23:48:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.03094","created_at":"2026-05-17T23:48:11Z"},{"alias_kind":"pith_short_12","alias_value":"VHEJ7UQDFUDE","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"VHEJ7UQDFUDETF7B","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"VHEJ7UQD","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:e5d07a27750e33a3b3d78187bb2dac7fa8262218fa0f0eb4b2cc7e1de60acf06","target":"graph","created_at":"2026-05-17T23:48:11Z","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 seen birds twitter, the running cars accompany with noise, etc. These naturally audiovisual correspondences provide the possibilities to explore and understand the outside world. However, the mixed multiple objects and sounds make it intractable to perform efficient matching in the unconstrained environment. To settle this problem, we propose to adequately excavate audio and visual components and perform elaborate correspondence learning among them. Concretely, a novel unsupervised audiovisual learning model is proposed, named as \\Deep Multimodal Clustering (DMC), that synchronously perfor","authors_text":"Di Hu, Feiping Nie, Xuelong Li","cross_cats":["cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-09T13:13:10Z","title":"Deep Multimodal Clustering for Unsupervised Audiovisual Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.03094","kind":"arxiv","version":3},"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":"sha256:65cf5ae9074a519cb1bedb6b34f401303656e2910a24d32fb2352d5c7cb97d2e","target":"record","created_at":"2026-05-17T23:48:11Z","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":"75df81e2dba691c46e03cdedf5f63f32de155a0a281a81f02639fb63563f3076","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-09T13:13:10Z","title_canon_sha256":"6dce7085ddf5d9a50eb6b20708e790a9d5ce970e5fdc1694ffe5e0c1a68b473a"},"schema_version":"1.0","source":{"id":"1807.03094","kind":"arxiv","version":3}},"canonical_sha256":"a9c89fd2032d064997e18c13c0b4e7f3839382a5bd9d7f062cf8f5cf48057a8f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9c89fd2032d064997e18c13c0b4e7f3839382a5bd9d7f062cf8f5cf48057a8f","first_computed_at":"2026-05-17T23:48:11.608346Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:11.608346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GJHEfVOON9xhW9apIurCFnYGNXOu8iJp2B8hpOpk0fMTWUZ8IbwS1YO3zHrXRi0jRM0ppkXrIp48BZWt0s5TDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:11.609008Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.03094","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65cf5ae9074a519cb1bedb6b34f401303656e2910a24d32fb2352d5c7cb97d2e","sha256:e5d07a27750e33a3b3d78187bb2dac7fa8262218fa0f0eb4b2cc7e1de60acf06"],"state_sha256":"2965c7509a5899f259a6e6282e2bccfd016bc4caef085ec3609ce070eba18f62"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OGQq7s8pLYRblMIuQfGuXjo6lnazMRk7lCXtScQ5CKN6f51CUUMZDsBp+Psbmt0c6SgG4RaejvanEotKpG2uCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T09:07:35.497238Z","bundle_sha256":"122f402028627052e2877903b1aab65620dac8129ac3e7fe6041ca52030d632b"}}