{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6XXC7U76Y6ANAGAM4XMUQ3IG54","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":"0f4105b4f9d14f0a0079e72fd918ed852d2daeb6d9db432cd195b24675522be4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-10T10:53:23Z","title_canon_sha256":"fb7b615420823a0d9be541e17e69aa23b78122fa6ee00f771644a77743cb49a7"},"schema_version":"1.0","source":{"id":"2406.06163","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.06163","created_at":"2026-07-05T08:29:38Z"},{"alias_kind":"arxiv_version","alias_value":"2406.06163v1","created_at":"2026-07-05T08:29:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06163","created_at":"2026-07-05T08:29:38Z"},{"alias_kind":"pith_short_12","alias_value":"6XXC7U76Y6AN","created_at":"2026-07-05T08:29:38Z"},{"alias_kind":"pith_short_16","alias_value":"6XXC7U76Y6ANAGAM","created_at":"2026-07-05T08:29:38Z"},{"alias_kind":"pith_short_8","alias_value":"6XXC7U76","created_at":"2026-07-05T08:29:38Z"}],"graph_snapshots":[{"event_id":"sha256:01953e7eefd326772ae7ea3694b351b0ee0248fe99d21cf24fdb5c213f123805","target":"graph","created_at":"2026-07-05T08:29:38Z","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/2406.06163/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-visual segmentation (AVS) aims to segment sound sources in the video sequence, requiring a pixel-level understanding of audio-visual correspondence. As the Segment Anything Model (SAM) has strongly impacted extensive fields of dense prediction problems, prior works have investigated the introduction of SAM into AVS with audio as a new modality of the prompt. Nevertheless, constrained by SAM's single-frame segmentation scheme, the temporal context across multiple frames of audio-visual data remains insufficiently utilized. To this end, we study the extension of SAM's capabilities to the s","authors_text":"Juhyeong Seon, Jumin Lee, Sebin Lee, Sung-Eui Yoon, Woobin Im","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-10T10:53:23Z","title":"Extending Segment Anything Model into Auditory and Temporal Dimensions for Audio-Visual Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06163","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":"sha256:28ddf6f2657240ccc47a5e6381a66db423865de925f7cfe65033e2149e602d12","target":"record","created_at":"2026-07-05T08:29:38Z","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":"0f4105b4f9d14f0a0079e72fd918ed852d2daeb6d9db432cd195b24675522be4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-10T10:53:23Z","title_canon_sha256":"fb7b615420823a0d9be541e17e69aa23b78122fa6ee00f771644a77743cb49a7"},"schema_version":"1.0","source":{"id":"2406.06163","kind":"arxiv","version":1}},"canonical_sha256":"f5ee2fd3fec780d0180ce5d9486d06ef2d28991cab4fb44a3dec751f5ebb22fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5ee2fd3fec780d0180ce5d9486d06ef2d28991cab4fb44a3dec751f5ebb22fd","first_computed_at":"2026-07-05T08:29:38.596216Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:38.596216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K+PHNhoUk6dnGA6jOj9oaw5FEneIPDcMQc0qHE6bDMRWwSBLEdcoSI8SqFl6xyg1UFKgYehlb0E4f189CwYIDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:38.596662Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.06163","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28ddf6f2657240ccc47a5e6381a66db423865de925f7cfe65033e2149e602d12","sha256:01953e7eefd326772ae7ea3694b351b0ee0248fe99d21cf24fdb5c213f123805"],"state_sha256":"1f3ce8dc2d7218e9ae5e227d7d9a97756ae1a9ad8294c5ddf6b393466ed9fcc0"}