{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SACDP7U7DLVQRLILFZRPPNFLJH","short_pith_number":"pith:SACDP7U7","canonical_record":{"source":{"id":"2309.06728","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-13T05:05:47Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"cba5b60f6cdaaa94134f9d9e47bf555f8dd461d53a50f513fc885de2b226637e","abstract_canon_sha256":"589e7de9585099074a62d6b062eac5714dd1e40540d3543941e975e97b4e026e"},"schema_version":"1.0"},"canonical_sha256":"900437fe9f1aeb08ad0b2e62f7b4ab49e16aaab2ecffb429df4fafdf99481496","source":{"kind":"arxiv","id":"2309.06728","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.06728","created_at":"2026-07-05T06:50:21Z"},{"alias_kind":"arxiv_version","alias_value":"2309.06728v1","created_at":"2026-07-05T06:50:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.06728","created_at":"2026-07-05T06:50:21Z"},{"alias_kind":"pith_short_12","alias_value":"SACDP7U7DLVQ","created_at":"2026-07-05T06:50:21Z"},{"alias_kind":"pith_short_16","alias_value":"SACDP7U7DLVQRLIL","created_at":"2026-07-05T06:50:21Z"},{"alias_kind":"pith_short_8","alias_value":"SACDP7U7","created_at":"2026-07-05T06:50:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SACDP7U7DLVQRLILFZRPPNFLJH","target":"record","payload":{"canonical_record":{"source":{"id":"2309.06728","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-13T05:05:47Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"cba5b60f6cdaaa94134f9d9e47bf555f8dd461d53a50f513fc885de2b226637e","abstract_canon_sha256":"589e7de9585099074a62d6b062eac5714dd1e40540d3543941e975e97b4e026e"},"schema_version":"1.0"},"canonical_sha256":"900437fe9f1aeb08ad0b2e62f7b4ab49e16aaab2ecffb429df4fafdf99481496","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:50:21.796509Z","signature_b64":"QZRgE4wklzoawrEl52BVxljQ4lHrWsR8LKlMjlUVuNrbNi2pmCcrZLCfEeKhGEkna1tkOPPZgUKWdeZ26/f7CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"900437fe9f1aeb08ad0b2e62f7b4ab49e16aaab2ecffb429df4fafdf99481496","last_reissued_at":"2026-07-05T06:50:21.796092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:50:21.796092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.06728","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":"2026-07-05T06:50:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OazR+FLn1+AhIsRiK9STKFcXYNQPLw9p3d7KE6hVnY7BTYIq+mpOGXWhraJr49GV8NDcKmCGc6AKkkwMTYaqAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:46:19.266047Z"},"content_sha256":"12d7de058cfb14aba239868f345fa8b03870bd03d4924c1d3fbffa40f1f3ee47","schema_version":"1.0","event_id":"sha256:12d7de058cfb14aba239868f345fa8b03870bd03d4924c1d3fbffa40f1f3ee47"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SACDP7U7DLVQRLILFZRPPNFLJH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Foundation models for Unsupervised Audio-Visual Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Diptesh Kanojia, Haosen Yang, Swapnil Bhosale, Xiatian Zhu","submitted_at":"2023-09-13T05:05:47Z","abstract_excerpt":"Audio-Visual Segmentation (AVS) aims to precisely outline audible objects in a visual scene at the pixel level. Existing AVS methods require fine-grained annotations of audio-mask pairs in supervised learning fashion. This limits their scalability since it is time consuming and tedious to acquire such cross-modality pixel level labels. To overcome this obstacle, in this work we introduce unsupervised audio-visual segmentation with no need for task-specific data annotations and model training. For tackling this newly proposed problem, we formulate a novel Cross-Modality Semantic Filtering (CMSF"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.06728","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/2309.06728/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":"2026-07-05T06:50:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X2a7UFVOOPi/uY4FwRxeHEEdX/0k+/3Dxf0tSeO2xD9tHrrLmNttETMr5lyXwbmYhiEaZajXrSH2lDEKzaMjAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:46:19.266739Z"},"content_sha256":"0c9f017ffa831249bc94cadee7f5db06e296e091aca760e491765369a77bfdfa","schema_version":"1.0","event_id":"sha256:0c9f017ffa831249bc94cadee7f5db06e296e091aca760e491765369a77bfdfa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SACDP7U7DLVQRLILFZRPPNFLJH/bundle.json","state_url":"https://pith.science/pith/SACDP7U7DLVQRLILFZRPPNFLJH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SACDP7U7DLVQRLILFZRPPNFLJH/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":"2026-07-09T06:46:19Z","links":{"resolver":"https://pith.science/pith/SACDP7U7DLVQRLILFZRPPNFLJH","bundle":"https://pith.science/pith/SACDP7U7DLVQRLILFZRPPNFLJH/bundle.json","state":"https://pith.science/pith/SACDP7U7DLVQRLILFZRPPNFLJH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SACDP7U7DLVQRLILFZRPPNFLJH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SACDP7U7DLVQRLILFZRPPNFLJH","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":"589e7de9585099074a62d6b062eac5714dd1e40540d3543941e975e97b4e026e","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-13T05:05:47Z","title_canon_sha256":"cba5b60f6cdaaa94134f9d9e47bf555f8dd461d53a50f513fc885de2b226637e"},"schema_version":"1.0","source":{"id":"2309.06728","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.06728","created_at":"2026-07-05T06:50:21Z"},{"alias_kind":"arxiv_version","alias_value":"2309.06728v1","created_at":"2026-07-05T06:50:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.06728","created_at":"2026-07-05T06:50:21Z"},{"alias_kind":"pith_short_12","alias_value":"SACDP7U7DLVQ","created_at":"2026-07-05T06:50:21Z"},{"alias_kind":"pith_short_16","alias_value":"SACDP7U7DLVQRLIL","created_at":"2026-07-05T06:50:21Z"},{"alias_kind":"pith_short_8","alias_value":"SACDP7U7","created_at":"2026-07-05T06:50:21Z"}],"graph_snapshots":[{"event_id":"sha256:0c9f017ffa831249bc94cadee7f5db06e296e091aca760e491765369a77bfdfa","target":"graph","created_at":"2026-07-05T06:50:21Z","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/2309.06728/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-Visual Segmentation (AVS) aims to precisely outline audible objects in a visual scene at the pixel level. Existing AVS methods require fine-grained annotations of audio-mask pairs in supervised learning fashion. This limits their scalability since it is time consuming and tedious to acquire such cross-modality pixel level labels. To overcome this obstacle, in this work we introduce unsupervised audio-visual segmentation with no need for task-specific data annotations and model training. For tackling this newly proposed problem, we formulate a novel Cross-Modality Semantic Filtering (CMSF","authors_text":"Diptesh Kanojia, Haosen Yang, Swapnil Bhosale, Xiatian Zhu","cross_cats":["cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-13T05:05:47Z","title":"Leveraging Foundation models for Unsupervised Audio-Visual Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.06728","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":"sha256:12d7de058cfb14aba239868f345fa8b03870bd03d4924c1d3fbffa40f1f3ee47","target":"record","created_at":"2026-07-05T06:50:21Z","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":"589e7de9585099074a62d6b062eac5714dd1e40540d3543941e975e97b4e026e","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-13T05:05:47Z","title_canon_sha256":"cba5b60f6cdaaa94134f9d9e47bf555f8dd461d53a50f513fc885de2b226637e"},"schema_version":"1.0","source":{"id":"2309.06728","kind":"arxiv","version":1}},"canonical_sha256":"900437fe9f1aeb08ad0b2e62f7b4ab49e16aaab2ecffb429df4fafdf99481496","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"900437fe9f1aeb08ad0b2e62f7b4ab49e16aaab2ecffb429df4fafdf99481496","first_computed_at":"2026-07-05T06:50:21.796092Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:50:21.796092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QZRgE4wklzoawrEl52BVxljQ4lHrWsR8LKlMjlUVuNrbNi2pmCcrZLCfEeKhGEkna1tkOPPZgUKWdeZ26/f7CA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:50:21.796509Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.06728","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:12d7de058cfb14aba239868f345fa8b03870bd03d4924c1d3fbffa40f1f3ee47","sha256:0c9f017ffa831249bc94cadee7f5db06e296e091aca760e491765369a77bfdfa"],"state_sha256":"72910c046dc591f6ae2c7387de7376b2b87a0baa787afce600dd5564cf8fdd14"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cDWPOS7Aif6xl0Pn28RNS28qLvD5fEPUuVdF7g+JX81Lv13VSPHtWU5DInCnqknLYBNqy42C0CqB74P2EqPJDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T06:46:19.270123Z","bundle_sha256":"523c4e82b7118f4ebeb73d59c33b6ce98441c915265d3f447aaf48ba51ae82b9"}}