{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:35K6TYOCKKV7DM46W6BVJVFOX7","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":"8c65f5657649eccfe08c8a8524e802b1549ccdb9b61fea5f222e2b52db2db42e","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-05T17:30:41Z","title_canon_sha256":"a459a3e7b14c9fb8f26677ee833f306c206ad3aed7e8be28dceadc56e9656efe"},"schema_version":"1.0","source":{"id":"2104.02026","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.02026","created_at":"2026-07-05T02:29:06Z"},{"alias_kind":"arxiv_version","alias_value":"2104.02026v1","created_at":"2026-07-05T02:29:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.02026","created_at":"2026-07-05T02:29:06Z"},{"alias_kind":"pith_short_12","alias_value":"35K6TYOCKKV7","created_at":"2026-07-05T02:29:06Z"},{"alias_kind":"pith_short_16","alias_value":"35K6TYOCKKV7DM46","created_at":"2026-07-05T02:29:06Z"},{"alias_kind":"pith_short_8","alias_value":"35K6TYOC","created_at":"2026-07-05T02:29:06Z"}],"graph_snapshots":[{"event_id":"sha256:c11002caf12355bb972182235a0be7a8cad91e7a150498642ae9b7f8170f1bf2","target":"graph","created_at":"2026-07-05T02:29:06Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2104.02026/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There are rich synchronized audio and visual events in our daily life. Inside the events, audio scenes are associated with the corresponding visual objects; meanwhile, sounding objects can indicate and help to separate their individual sounds in the audio track. Based on this observation, in this paper, we propose a cyclic co-learning (CCoL) paradigm that can jointly learn sounding object visual grounding and audio-visual sound separation in a unified framework. Concretely, we can leverage grounded object-sound relations to improve the results of sound separation. Meanwhile, benefiting from di","authors_text":"Chenliang Xu, Di Hu, Yapeng Tian","cross_cats":["cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-05T17:30:41Z","title":"Cyclic Co-Learning of Sounding Object Visual Grounding and Sound Separation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.02026","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":"sha256:80eac029b17a2390e9217994bae42dbfd1c750b70ceec5ce12a41c0794a568f4","target":"record","created_at":"2026-07-05T02:29:06Z","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":"8c65f5657649eccfe08c8a8524e802b1549ccdb9b61fea5f222e2b52db2db42e","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-05T17:30:41Z","title_canon_sha256":"a459a3e7b14c9fb8f26677ee833f306c206ad3aed7e8be28dceadc56e9656efe"},"schema_version":"1.0","source":{"id":"2104.02026","kind":"arxiv","version":1}},"canonical_sha256":"df55e9e1c252abf1b39eb78354d4aebfe82aeb70fccd69f59b01c10f7ced56dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df55e9e1c252abf1b39eb78354d4aebfe82aeb70fccd69f59b01c10f7ced56dc","first_computed_at":"2026-07-05T02:29:06.481801Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:29:06.481801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R7iknXLfAO9P0XL+R9vaFuR30KhqD8ZNRboqhSL+N9YWKWLlJ0vzDP/I4xBA/16ChtYSrQCv8JcuWJvpLRZBCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:29:06.482276Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.02026","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80eac029b17a2390e9217994bae42dbfd1c750b70ceec5ce12a41c0794a568f4","sha256:c11002caf12355bb972182235a0be7a8cad91e7a150498642ae9b7f8170f1bf2"],"state_sha256":"f1149ba7b2fba310a526bc3f8d6be8dbf8a472ee1514caf9a8a23312b0199bc3"}