{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:G6W5L54UGRCHR7WZOSNB6PTDET","short_pith_number":"pith:G6W5L54U","schema_version":"1.0","canonical_sha256":"37add5f794344478fed9749a1f3e6324fa87f8268c66259c772fc222266e080b","source":{"kind":"arxiv","id":"2308.10175","version":1},"attestation_state":"computed","paper":{"title":"BAVS: Bootstrapping Audio-Visual Segmentation by Integrating Foundation Knowledge","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Liu, Dadong Wang, Hu Zhang, Lincheng Li, Peike Li, Xin Yu, Zi Huang","submitted_at":"2023-08-20T06:48:08Z","abstract_excerpt":"Given an audio-visual pair, audio-visual segmentation (AVS) aims to locate sounding sources by predicting pixel-wise maps. Previous methods assume that each sound component in an audio signal always has a visual counterpart in the image. However, this assumption overlooks that off-screen sounds and background noise often contaminate the audio recordings in real-world scenarios. They impose significant challenges on building a consistent semantic mapping between audio and visual signals for AVS models and thus impede precise sound localization. In this work, we propose a two-stage bootstrapping"},"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":"2308.10175","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-20T06:48:08Z","cross_cats_sorted":[],"title_canon_sha256":"0db1fb57d8840032f02d6a14530d51e166fd2c914f0b074a5923b6f9afc90b78","abstract_canon_sha256":"d5641162238dc4717b66215cd69bdc4596555a7145df0707db5fe97ba9d785bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:52.787843Z","signature_b64":"w0gf99KIkXshQCSw/hfPTx01iMBcvD5HvMENmG6IckknqZHkEZni9vmdRZNfnYANDixjP2RFVuezB0yBNAZ3Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37add5f794344478fed9749a1f3e6324fa87f8268c66259c772fc222266e080b","last_reissued_at":"2026-07-05T06:42:52.787348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:52.787348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BAVS: Bootstrapping Audio-Visual Segmentation by Integrating Foundation Knowledge","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Liu, Dadong Wang, Hu Zhang, Lincheng Li, Peike Li, Xin Yu, Zi Huang","submitted_at":"2023-08-20T06:48:08Z","abstract_excerpt":"Given an audio-visual pair, audio-visual segmentation (AVS) aims to locate sounding sources by predicting pixel-wise maps. Previous methods assume that each sound component in an audio signal always has a visual counterpart in the image. However, this assumption overlooks that off-screen sounds and background noise often contaminate the audio recordings in real-world scenarios. They impose significant challenges on building a consistent semantic mapping between audio and visual signals for AVS models and thus impede precise sound localization. In this work, we propose a two-stage bootstrapping"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10175","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/2308.10175/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":"2308.10175","created_at":"2026-07-05T06:42:52.787407+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.10175v1","created_at":"2026-07-05T06:42:52.787407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10175","created_at":"2026-07-05T06:42:52.787407+00:00"},{"alias_kind":"pith_short_12","alias_value":"G6W5L54UGRCH","created_at":"2026-07-05T06:42:52.787407+00:00"},{"alias_kind":"pith_short_16","alias_value":"G6W5L54UGRCHR7WZ","created_at":"2026-07-05T06:42:52.787407+00:00"},{"alias_kind":"pith_short_8","alias_value":"G6W5L54U","created_at":"2026-07-05T06:42:52.787407+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.01015","citing_title":"AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G6W5L54UGRCHR7WZOSNB6PTDET","json":"https://pith.science/pith/G6W5L54UGRCHR7WZOSNB6PTDET.json","graph_json":"https://pith.science/api/pith-number/G6W5L54UGRCHR7WZOSNB6PTDET/graph.json","events_json":"https://pith.science/api/pith-number/G6W5L54UGRCHR7WZOSNB6PTDET/events.json","paper":"https://pith.science/paper/G6W5L54U"},"agent_actions":{"view_html":"https://pith.science/pith/G6W5L54UGRCHR7WZOSNB6PTDET","download_json":"https://pith.science/pith/G6W5L54UGRCHR7WZOSNB6PTDET.json","view_paper":"https://pith.science/paper/G6W5L54U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.10175&json=true","fetch_graph":"https://pith.science/api/pith-number/G6W5L54UGRCHR7WZOSNB6PTDET/graph.json","fetch_events":"https://pith.science/api/pith-number/G6W5L54UGRCHR7WZOSNB6PTDET/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G6W5L54UGRCHR7WZOSNB6PTDET/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G6W5L54UGRCHR7WZOSNB6PTDET/action/storage_attestation","attest_author":"https://pith.science/pith/G6W5L54UGRCHR7WZOSNB6PTDET/action/author_attestation","sign_citation":"https://pith.science/pith/G6W5L54UGRCHR7WZOSNB6PTDET/action/citation_signature","submit_replication":"https://pith.science/pith/G6W5L54UGRCHR7WZOSNB6PTDET/action/replication_record"}},"created_at":"2026-07-05T06:42:52.787407+00:00","updated_at":"2026-07-05T06:42:52.787407+00:00"}