{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:35K6TYOCKKV7DM46W6BVJVFOX7","short_pith_number":"pith:35K6TYOC","canonical_record":{"source":{"id":"2104.02026","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-05T17:30:41Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"a459a3e7b14c9fb8f26677ee833f306c206ad3aed7e8be28dceadc56e9656efe","abstract_canon_sha256":"8c65f5657649eccfe08c8a8524e802b1549ccdb9b61fea5f222e2b52db2db42e"},"schema_version":"1.0"},"canonical_sha256":"df55e9e1c252abf1b39eb78354d4aebfe82aeb70fccd69f59b01c10f7ced56dc","source":{"kind":"arxiv","id":"2104.02026","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:35K6TYOCKKV7DM46W6BVJVFOX7","target":"record","payload":{"canonical_record":{"source":{"id":"2104.02026","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-04-05T17:30:41Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"a459a3e7b14c9fb8f26677ee833f306c206ad3aed7e8be28dceadc56e9656efe","abstract_canon_sha256":"8c65f5657649eccfe08c8a8524e802b1549ccdb9b61fea5f222e2b52db2db42e"},"schema_version":"1.0"},"canonical_sha256":"df55e9e1c252abf1b39eb78354d4aebfe82aeb70fccd69f59b01c10f7ced56dc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:29:06.482276Z","signature_b64":"R7iknXLfAO9P0XL+R9vaFuR30KhqD8ZNRboqhSL+N9YWKWLlJ0vzDP/I4xBA/16ChtYSrQCv8JcuWJvpLRZBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df55e9e1c252abf1b39eb78354d4aebfe82aeb70fccd69f59b01c10f7ced56dc","last_reissued_at":"2026-07-05T02:29:06.481801Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:29:06.481801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.02026","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":"2026-07-05T02:29:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LAnJfocLqAX3j7mTk+Lw40mfxFeGdy8Io36hbWKhUnMIuUG7ffxOW3eqa3R1LAO4MJoy+yKb1SiTEkhbKfo+Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:04:28.674464Z"},"content_sha256":"80eac029b17a2390e9217994bae42dbfd1c750b70ceec5ce12a41c0794a568f4","schema_version":"1.0","event_id":"sha256:80eac029b17a2390e9217994bae42dbfd1c750b70ceec5ce12a41c0794a568f4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:35K6TYOCKKV7DM46W6BVJVFOX7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cyclic Co-Learning of Sounding Object Visual Grounding and Sound Separation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Chenliang Xu, Di Hu, Yapeng Tian","submitted_at":"2021-04-05T17:30:41Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.02026","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2104.02026/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T02:29:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oqJcHpDRWhqu1Vtv+FCRgIwBxqf8q6cBOw6rQ4OiIr+w1n6yQytjoBDEEU0m7DwWuhCFDkpDW+QioANTeihCDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:04:28.674947Z"},"content_sha256":"c11002caf12355bb972182235a0be7a8cad91e7a150498642ae9b7f8170f1bf2","schema_version":"1.0","event_id":"sha256:c11002caf12355bb972182235a0be7a8cad91e7a150498642ae9b7f8170f1bf2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/35K6TYOCKKV7DM46W6BVJVFOX7/bundle.json","state_url":"https://pith.science/pith/35K6TYOCKKV7DM46W6BVJVFOX7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/35K6TYOCKKV7DM46W6BVJVFOX7/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":"2026-08-04T22:04:28Z","links":{"resolver":"https://pith.science/pith/35K6TYOCKKV7DM46W6BVJVFOX7","bundle":"https://pith.science/pith/35K6TYOCKKV7DM46W6BVJVFOX7/bundle.json","state":"https://pith.science/pith/35K6TYOCKKV7DM46W6BVJVFOX7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/35K6TYOCKKV7DM46W6BVJVFOX7/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vyw2ZHYpO2KrHz4wdTlajMcyB51fZPldUhrF4xn/ylUzWQyiZ779wU+7nFkePk6z3nGfn/ENAv8Ygq8j6mu3BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T22:04:28.680473Z","bundle_sha256":"5d36b7d4619d9ecd3d21d8ae9e999dcf18642d1d683eee5c05582be83c870f81"}}