{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SX5HNSSXRKS5HG3YT67LH2HCHA","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":"634c1c1858c9f7e478da43fd6df81f507007851cd474b6469cbcd03df9442acd","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-06T21:06:35Z","title_canon_sha256":"81ba3d22cf141ee78e4d4db01ce4e1f8c5f73d22feaae7b74bec756a5cffc268"},"schema_version":"1.0","source":{"id":"2506.06537","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06537","created_at":"2026-07-05T11:17:51Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06537v1","created_at":"2026-07-05T11:17:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06537","created_at":"2026-07-05T11:17:51Z"},{"alias_kind":"pith_short_12","alias_value":"SX5HNSSXRKS5","created_at":"2026-07-05T11:17:51Z"},{"alias_kind":"pith_short_16","alias_value":"SX5HNSSXRKS5HG3Y","created_at":"2026-07-05T11:17:51Z"},{"alias_kind":"pith_short_8","alias_value":"SX5HNSSX","created_at":"2026-07-05T11:17:51Z"}],"graph_snapshots":[{"event_id":"sha256:243473b2e0a14bff807e56aaa3ec29bb67c95f1500bb95e27ee945f34de1c729","target":"graph","created_at":"2026-07-05T11:17:51Z","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/2506.06537/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audiovisual segmentation (AVS) aims to identify visual regions corresponding to sound sources, playing a vital role in video understanding, surveillance, and human-computer interaction. Traditional AVS methods depend on large-scale pixel-level annotations, which are costly and time-consuming to obtain. To address this, we propose a novel zero-shot AVS framework that eliminates task-specific training by leveraging multiple pretrained models. Our approach integrates audio, vision, and text representations to bridge modality gaps, enabling precise sound source segmentation without AVS-specific an","authors_text":"Paul Hongsuck Seo, Seung-Jae Lee","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-06T21:06:35Z","title":"Bridging Audio and Vision: Zero-Shot Audiovisual Segmentation by Connecting Pretrained Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06537","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":"sha256:9d2abe34de70fd877ad9dc4ab95e991406caeed305b43a9de134bb6d67480605","target":"record","created_at":"2026-07-05T11:17:51Z","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":"634c1c1858c9f7e478da43fd6df81f507007851cd474b6469cbcd03df9442acd","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-06T21:06:35Z","title_canon_sha256":"81ba3d22cf141ee78e4d4db01ce4e1f8c5f73d22feaae7b74bec756a5cffc268"},"schema_version":"1.0","source":{"id":"2506.06537","kind":"arxiv","version":1}},"canonical_sha256":"95fa76ca578aa5d39b789fbeb3e8e238008e15a8de92b02668d71f420120006d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95fa76ca578aa5d39b789fbeb3e8e238008e15a8de92b02668d71f420120006d","first_computed_at":"2026-07-05T11:17:51.840165Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:51.840165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rd7sW4sM45WbEmyv1WMk6FxuT5QJ0AaiXlceR+WqQqUVuUOloBkTcAr24xajWSKwj6KhqOPYACVBNOJcwN4EBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:51.840665Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.06537","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d2abe34de70fd877ad9dc4ab95e991406caeed305b43a9de134bb6d67480605","sha256:243473b2e0a14bff807e56aaa3ec29bb67c95f1500bb95e27ee945f34de1c729"],"state_sha256":"085c07c0590996a11850ad14ffd23e973ad69c212bd7770f39ad25225bfa75cb"}