{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CQRXD2KQA3YBVCQPYVIB2L3NEJ","short_pith_number":"pith:CQRXD2KQ","canonical_record":{"source":{"id":"2403.14203","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T07:56:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eda6c55cc9d69a7cb24eca17a54dc46aad853a3cea437671577554e6451ab86b","abstract_canon_sha256":"1e7a9164019a81516881e1130235582bc85b0222d398275c7c176560e2a4916d"},"schema_version":"1.0"},"canonical_sha256":"142371e95006f01a8a0fc5501d2f6d226dc55ad75999e5af1be55e3bb9329d44","source":{"kind":"arxiv","id":"2403.14203","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.14203","created_at":"2026-07-05T07:58:55Z"},{"alias_kind":"arxiv_version","alias_value":"2403.14203v1","created_at":"2026-07-05T07:58:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14203","created_at":"2026-07-05T07:58:55Z"},{"alias_kind":"pith_short_12","alias_value":"CQRXD2KQA3YB","created_at":"2026-07-05T07:58:55Z"},{"alias_kind":"pith_short_16","alias_value":"CQRXD2KQA3YBVCQP","created_at":"2026-07-05T07:58:55Z"},{"alias_kind":"pith_short_8","alias_value":"CQRXD2KQ","created_at":"2026-07-05T07:58:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CQRXD2KQA3YBVCQPYVIB2L3NEJ","target":"record","payload":{"canonical_record":{"source":{"id":"2403.14203","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T07:56:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eda6c55cc9d69a7cb24eca17a54dc46aad853a3cea437671577554e6451ab86b","abstract_canon_sha256":"1e7a9164019a81516881e1130235582bc85b0222d398275c7c176560e2a4916d"},"schema_version":"1.0"},"canonical_sha256":"142371e95006f01a8a0fc5501d2f6d226dc55ad75999e5af1be55e3bb9329d44","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:55.896423Z","signature_b64":"HIHu4qZPfMWaA5Qq6Cs9avL+zEJRRanm9WjwOXU0dLv2U/pFPqGyDOjqA89GK2gUBp1jbPUf3ZbkIyMp21ZKAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"142371e95006f01a8a0fc5501d2f6d226dc55ad75999e5af1be55e3bb9329d44","last_reissued_at":"2026-07-05T07:58:55.895938Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:55.895938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.14203","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":"2026-07-05T07:58:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZKpl04xF0EUI4A9TtwPAlBuuMtEIVaNL0U2+XDMbm+6wu7Oky60l8nVlgxrseVefWrzLCMI3XFAYc+tDJGmdDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T11:37:47.793956Z"},"content_sha256":"437af26e9b3032ef399969533fb5f05606054271911457399b2b08f0f1433980","schema_version":"1.0","event_id":"sha256:437af26e9b3032ef399969533fb5f05606054271911457399b2b08f0f1433980"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CQRXD2KQA3YBVCQPYVIB2L3NEJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Audio-Visual Segmentation with Modality Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Diptesh Kanojia, Haosen Yang, Jiangkang Deng, Swapnil Bhosale, Xiatian Zhu","submitted_at":"2024-03-21T07:56:09Z","abstract_excerpt":"Audio-Visual Segmentation (AVS) aims to identify, at the pixel level, the object in a visual scene that produces a given sound. Current AVS methods rely on costly fine-grained annotations of mask-audio pairs, making them impractical for scalability. To address this, we introduce unsupervised AVS, eliminating the need for such expensive annotation. To tackle this more challenging problem, we propose an unsupervised learning method, named Modality Correspondence Alignment (MoCA), which seamlessly integrates off-the-shelf foundation models like DINO, SAM, and ImageBind. This approach leverages th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14203","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/2403.14203/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":"2026-07-05T07:58:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W0XlbhD1IBA425hNQWo0gMLq4ivxFNSEVq2lrCoTKAcFLWrLpTSZwn8R8PoqecP34M4fQnm/AIfbiZCYPnWWCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T11:37:47.794352Z"},"content_sha256":"10662f043d73d1345ca5a17a353b960d7b20108b26e647abd32924698935fd2e","schema_version":"1.0","event_id":"sha256:10662f043d73d1345ca5a17a353b960d7b20108b26e647abd32924698935fd2e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CQRXD2KQA3YBVCQPYVIB2L3NEJ/bundle.json","state_url":"https://pith.science/pith/CQRXD2KQA3YBVCQPYVIB2L3NEJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CQRXD2KQA3YBVCQPYVIB2L3NEJ/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":"2026-07-26T11:37:47Z","links":{"resolver":"https://pith.science/pith/CQRXD2KQA3YBVCQPYVIB2L3NEJ","bundle":"https://pith.science/pith/CQRXD2KQA3YBVCQPYVIB2L3NEJ/bundle.json","state":"https://pith.science/pith/CQRXD2KQA3YBVCQPYVIB2L3NEJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CQRXD2KQA3YBVCQPYVIB2L3NEJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CQRXD2KQA3YBVCQPYVIB2L3NEJ","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":"1e7a9164019a81516881e1130235582bc85b0222d398275c7c176560e2a4916d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T07:56:09Z","title_canon_sha256":"eda6c55cc9d69a7cb24eca17a54dc46aad853a3cea437671577554e6451ab86b"},"schema_version":"1.0","source":{"id":"2403.14203","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.14203","created_at":"2026-07-05T07:58:55Z"},{"alias_kind":"arxiv_version","alias_value":"2403.14203v1","created_at":"2026-07-05T07:58:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.14203","created_at":"2026-07-05T07:58:55Z"},{"alias_kind":"pith_short_12","alias_value":"CQRXD2KQA3YB","created_at":"2026-07-05T07:58:55Z"},{"alias_kind":"pith_short_16","alias_value":"CQRXD2KQA3YBVCQP","created_at":"2026-07-05T07:58:55Z"},{"alias_kind":"pith_short_8","alias_value":"CQRXD2KQ","created_at":"2026-07-05T07:58:55Z"}],"graph_snapshots":[{"event_id":"sha256:10662f043d73d1345ca5a17a353b960d7b20108b26e647abd32924698935fd2e","target":"graph","created_at":"2026-07-05T07:58:55Z","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/2403.14203/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-Visual Segmentation (AVS) aims to identify, at the pixel level, the object in a visual scene that produces a given sound. Current AVS methods rely on costly fine-grained annotations of mask-audio pairs, making them impractical for scalability. To address this, we introduce unsupervised AVS, eliminating the need for such expensive annotation. To tackle this more challenging problem, we propose an unsupervised learning method, named Modality Correspondence Alignment (MoCA), which seamlessly integrates off-the-shelf foundation models like DINO, SAM, and ImageBind. This approach leverages th","authors_text":"Diptesh Kanojia, Haosen Yang, Jiangkang Deng, Swapnil Bhosale, Xiatian Zhu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T07:56:09Z","title":"Unsupervised Audio-Visual Segmentation with Modality Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.14203","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":"sha256:437af26e9b3032ef399969533fb5f05606054271911457399b2b08f0f1433980","target":"record","created_at":"2026-07-05T07:58:55Z","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":"1e7a9164019a81516881e1130235582bc85b0222d398275c7c176560e2a4916d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-21T07:56:09Z","title_canon_sha256":"eda6c55cc9d69a7cb24eca17a54dc46aad853a3cea437671577554e6451ab86b"},"schema_version":"1.0","source":{"id":"2403.14203","kind":"arxiv","version":1}},"canonical_sha256":"142371e95006f01a8a0fc5501d2f6d226dc55ad75999e5af1be55e3bb9329d44","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"142371e95006f01a8a0fc5501d2f6d226dc55ad75999e5af1be55e3bb9329d44","first_computed_at":"2026-07-05T07:58:55.895938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:58:55.895938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HIHu4qZPfMWaA5Qq6Cs9avL+zEJRRanm9WjwOXU0dLv2U/pFPqGyDOjqA89GK2gUBp1jbPUf3ZbkIyMp21ZKAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:58:55.896423Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.14203","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:437af26e9b3032ef399969533fb5f05606054271911457399b2b08f0f1433980","sha256:10662f043d73d1345ca5a17a353b960d7b20108b26e647abd32924698935fd2e"],"state_sha256":"a42c66d2b9ba2c9a6b27ce3daedcfc4f0746486078cc3e294fb329ac2814f0ea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+uqE5JQIMo3sUn5G8ZyAJLtbGBArWEirUkBkhTc0idmXcfssU/IAqHsksjKwkudBYjGgOKpNmyWPt6F589VoAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-26T11:37:47.796537Z","bundle_sha256":"2261f1e3fb87da083488190d04f07974583d866857096a4435d7d252b62e98d2"}}