{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:G6W5L54UGRCHR7WZOSNB6PTDET","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":"d5641162238dc4717b66215cd69bdc4596555a7145df0707db5fe97ba9d785bf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-20T06:48:08Z","title_canon_sha256":"0db1fb57d8840032f02d6a14530d51e166fd2c914f0b074a5923b6f9afc90b78"},"schema_version":"1.0","source":{"id":"2308.10175","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.10175","created_at":"2026-07-05T06:42:52Z"},{"alias_kind":"arxiv_version","alias_value":"2308.10175v1","created_at":"2026-07-05T06:42:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10175","created_at":"2026-07-05T06:42:52Z"},{"alias_kind":"pith_short_12","alias_value":"G6W5L54UGRCH","created_at":"2026-07-05T06:42:52Z"},{"alias_kind":"pith_short_16","alias_value":"G6W5L54UGRCHR7WZ","created_at":"2026-07-05T06:42:52Z"},{"alias_kind":"pith_short_8","alias_value":"G6W5L54U","created_at":"2026-07-05T06:42:52Z"}],"graph_snapshots":[{"event_id":"sha256:76f9a8622c6fe0f95670f3f7049a4535f722d1980376fb7d13db3729739a6c3c","target":"graph","created_at":"2026-07-05T06:42:52Z","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/2308.10175/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chen Liu, Dadong Wang, Hu Zhang, Lincheng Li, Peike Li, Xin Yu, Zi Huang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-20T06:48:08Z","title":"BAVS: Bootstrapping Audio-Visual Segmentation by Integrating Foundation Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10175","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:e0326b3268d5c9e3409334e54ac1ac290bc7af42223e9b7126b520c4c27de448","target":"record","created_at":"2026-07-05T06:42:52Z","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":"d5641162238dc4717b66215cd69bdc4596555a7145df0707db5fe97ba9d785bf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-20T06:48:08Z","title_canon_sha256":"0db1fb57d8840032f02d6a14530d51e166fd2c914f0b074a5923b6f9afc90b78"},"schema_version":"1.0","source":{"id":"2308.10175","kind":"arxiv","version":1}},"canonical_sha256":"37add5f794344478fed9749a1f3e6324fa87f8268c66259c772fc222266e080b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"37add5f794344478fed9749a1f3e6324fa87f8268c66259c772fc222266e080b","first_computed_at":"2026-07-05T06:42:52.787348Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:42:52.787348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w0gf99KIkXshQCSw/hfPTx01iMBcvD5HvMENmG6IckknqZHkEZni9vmdRZNfnYANDixjP2RFVuezB0yBNAZ3Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:42:52.787843Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.10175","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e0326b3268d5c9e3409334e54ac1ac290bc7af42223e9b7126b520c4c27de448","sha256:76f9a8622c6fe0f95670f3f7049a4535f722d1980376fb7d13db3729739a6c3c"],"state_sha256":"196916822e4ddf55e75ac75008bcfa9355a2e928bc56910b665e67682a9d0228"}