{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SX5HNSSXRKS5HG3YT67LH2HCHA","short_pith_number":"pith:SX5HNSSX","schema_version":"1.0","canonical_sha256":"95fa76ca578aa5d39b789fbeb3e8e238008e15a8de92b02668d71f420120006d","source":{"kind":"arxiv","id":"2506.06537","version":1},"attestation_state":"computed","paper":{"title":"Bridging Audio and Vision: Zero-Shot Audiovisual Segmentation by Connecting Pretrained Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Paul Hongsuck Seo, Seung-Jae Lee","submitted_at":"2025-06-06T21:06:35Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.06537","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-06T21:06:35Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"81ba3d22cf141ee78e4d4db01ce4e1f8c5f73d22feaae7b74bec756a5cffc268","abstract_canon_sha256":"634c1c1858c9f7e478da43fd6df81f507007851cd474b6469cbcd03df9442acd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:51.840665Z","signature_b64":"rd7sW4sM45WbEmyv1WMk6FxuT5QJ0AaiXlceR+WqQqUVuUOloBkTcAr24xajWSKwj6KhqOPYACVBNOJcwN4EBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95fa76ca578aa5d39b789fbeb3e8e238008e15a8de92b02668d71f420120006d","last_reissued_at":"2026-07-05T11:17:51.840165Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:51.840165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging Audio and Vision: Zero-Shot Audiovisual Segmentation by Connecting Pretrained Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Paul Hongsuck Seo, Seung-Jae Lee","submitted_at":"2025-06-06T21:06:35Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06537","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/2506.06537/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.06537","created_at":"2026-07-05T11:17:51.840220+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.06537v1","created_at":"2026-07-05T11:17:51.840220+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06537","created_at":"2026-07-05T11:17:51.840220+00:00"},{"alias_kind":"pith_short_12","alias_value":"SX5HNSSXRKS5","created_at":"2026-07-05T11:17:51.840220+00:00"},{"alias_kind":"pith_short_16","alias_value":"SX5HNSSXRKS5HG3Y","created_at":"2026-07-05T11:17:51.840220+00:00"},{"alias_kind":"pith_short_8","alias_value":"SX5HNSSX","created_at":"2026-07-05T11:17:51.840220+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.06537","citing_title":"Bridging Audio and Vision: Zero-Shot Audiovisual Segmentation by Connecting Pretrained Models","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SX5HNSSXRKS5HG3YT67LH2HCHA","json":"https://pith.science/pith/SX5HNSSXRKS5HG3YT67LH2HCHA.json","graph_json":"https://pith.science/api/pith-number/SX5HNSSXRKS5HG3YT67LH2HCHA/graph.json","events_json":"https://pith.science/api/pith-number/SX5HNSSXRKS5HG3YT67LH2HCHA/events.json","paper":"https://pith.science/paper/SX5HNSSX"},"agent_actions":{"view_html":"https://pith.science/pith/SX5HNSSXRKS5HG3YT67LH2HCHA","download_json":"https://pith.science/pith/SX5HNSSXRKS5HG3YT67LH2HCHA.json","view_paper":"https://pith.science/paper/SX5HNSSX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.06537&json=true","fetch_graph":"https://pith.science/api/pith-number/SX5HNSSXRKS5HG3YT67LH2HCHA/graph.json","fetch_events":"https://pith.science/api/pith-number/SX5HNSSXRKS5HG3YT67LH2HCHA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SX5HNSSXRKS5HG3YT67LH2HCHA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SX5HNSSXRKS5HG3YT67LH2HCHA/action/storage_attestation","attest_author":"https://pith.science/pith/SX5HNSSXRKS5HG3YT67LH2HCHA/action/author_attestation","sign_citation":"https://pith.science/pith/SX5HNSSXRKS5HG3YT67LH2HCHA/action/citation_signature","submit_replication":"https://pith.science/pith/SX5HNSSXRKS5HG3YT67LH2HCHA/action/replication_record"}},"created_at":"2026-07-05T11:17:51.840220+00:00","updated_at":"2026-07-05T11:17:51.840220+00:00"}