{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WQUI5UL6U2ZPCZ4FRD5JOR55TJ","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":"d362edc9ad11976f05b1f549f57eb3bd8168c80335e96f9a14680e72868de9cb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T03:20:20Z","title_canon_sha256":"ed8fa7a7f4a94ee0adc612c479ed3a59d5896125451ec96d1a6d6a2fc7dcee08"},"schema_version":"1.0","source":{"id":"2501.07810","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.07810","created_at":"2026-07-05T10:00:50Z"},{"alias_kind":"arxiv_version","alias_value":"2501.07810v1","created_at":"2026-07-05T10:00:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.07810","created_at":"2026-07-05T10:00:50Z"},{"alias_kind":"pith_short_12","alias_value":"WQUI5UL6U2ZP","created_at":"2026-07-05T10:00:50Z"},{"alias_kind":"pith_short_16","alias_value":"WQUI5UL6U2ZPCZ4F","created_at":"2026-07-05T10:00:50Z"},{"alias_kind":"pith_short_8","alias_value":"WQUI5UL6","created_at":"2026-07-05T10:00:50Z"}],"graph_snapshots":[{"event_id":"sha256:d2e7688a2cbe820d4d9077457aa9531de8374e7464f7d8702772aba901d26f3f","target":"graph","created_at":"2026-07-05T10:00:50Z","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/2501.07810/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The essence of audio-visual segmentation (AVS) lies in locating and delineating sound-emitting objects within a video stream. While Transformer-based methods have shown promise, their handling of long-range dependencies struggles due to quadratic computational costs, presenting a bottleneck in complex scenarios. To overcome this limitation and facilitate complex multi-modal comprehension with linear complexity, we introduce AVS-Mamba, a selective state space model to address the AVS task. Our framework incorporates two key components for video understanding and cross-modal learning: Temporal M","authors_text":"Huchuan Lu, Lijun Wang, Lu Zhang, Pingping Zhang, Sitong Gong, Yifan Wang, Yunzhi Zhuge","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T03:20:20Z","title":"AVS-Mamba: Exploring Temporal and Multi-modal Mamba for Audio-Visual Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.07810","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":"sha256:979d333834d5748b3fc25a49971281cf42eaccc357e77e27af71382197b163fd","target":"record","created_at":"2026-07-05T10:00:50Z","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":"d362edc9ad11976f05b1f549f57eb3bd8168c80335e96f9a14680e72868de9cb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T03:20:20Z","title_canon_sha256":"ed8fa7a7f4a94ee0adc612c479ed3a59d5896125451ec96d1a6d6a2fc7dcee08"},"schema_version":"1.0","source":{"id":"2501.07810","kind":"arxiv","version":1}},"canonical_sha256":"b4288ed17ea6b2f1678588fa9747bd9a422a60bcad61f4c9861d860e8dd99e3b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4288ed17ea6b2f1678588fa9747bd9a422a60bcad61f4c9861d860e8dd99e3b","first_computed_at":"2026-07-05T10:00:50.493521Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:00:50.493521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Svdy0AifZUhile/nAOwhHDxRLtHE3UQaegv48aoUNcJF8ee4gkKfJPdE4MoUkbK3bY2RVhgPS7AyJ9hVLL7gDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:00:50.494014Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.07810","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:979d333834d5748b3fc25a49971281cf42eaccc357e77e27af71382197b163fd","sha256:d2e7688a2cbe820d4d9077457aa9531de8374e7464f7d8702772aba901d26f3f"],"state_sha256":"6570240e74bffb51ad395b26b3a7103df9b9038943f9b6be30ff708d87987162"}