{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6V4OIEM6DBP2VPGSYYCU2QBQHL","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":"bf27da4c0bf2e598aef0ad7dcfa82e12a4f12f0abb8503a223bb5c50efcd1a91","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-07T13:20:21Z","title_canon_sha256":"909648826baa35c5d9ba34c4b8e9b60ba66597554ac5b2a1cee2daaa8d74ff1d"},"schema_version":"1.0","source":{"id":"2407.05358","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.05358","created_at":"2026-07-05T09:13:05Z"},{"alias_kind":"arxiv_version","alias_value":"2407.05358v3","created_at":"2026-07-05T09:13:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05358","created_at":"2026-07-05T09:13:05Z"},{"alias_kind":"pith_short_12","alias_value":"6V4OIEM6DBP2","created_at":"2026-07-05T09:13:05Z"},{"alias_kind":"pith_short_16","alias_value":"6V4OIEM6DBP2VPGS","created_at":"2026-07-05T09:13:05Z"},{"alias_kind":"pith_short_8","alias_value":"6V4OIEM6","created_at":"2026-07-05T09:13:05Z"}],"graph_snapshots":[{"event_id":"sha256:ecb3d5c1c368dd7fbfa3b70d0724ffd175537cc6f9a29f45548f451d39d98238","target":"graph","created_at":"2026-07-05T09:13:05Z","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/2407.05358/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-visual segmentation (AVS) is an emerging task that aims to accurately segment sounding objects based on audio-visual cues. The success of AVS learning systems depends on the effectiveness of cross-modal interaction. Such a requirement can be naturally fulfilled by leveraging transformer-based segmentation architecture due to its inherent ability to capture long-range dependencies and flexibility in handling different modalities. However, the inherent training issues of transformer-based methods, such as the low efficacy of cross-attention and unstable bipartite matching, can be amplified","authors_text":"Chong Wang, Gustavo Carneiro, Hu Wang, Yuanhong Chen, Yuyuan Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-07T13:20:21Z","title":"CPM: Class-conditional Prompting Machine for Audio-visual Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05358","kind":"arxiv","version":3},"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":"sha256:3cf60b82d8014913f03d808ec9328fd18300e58489a0af6dcb7b5b9bf9252c68","target":"record","created_at":"2026-07-05T09:13:05Z","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":"bf27da4c0bf2e598aef0ad7dcfa82e12a4f12f0abb8503a223bb5c50efcd1a91","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-07T13:20:21Z","title_canon_sha256":"909648826baa35c5d9ba34c4b8e9b60ba66597554ac5b2a1cee2daaa8d74ff1d"},"schema_version":"1.0","source":{"id":"2407.05358","kind":"arxiv","version":3}},"canonical_sha256":"f578e4119e185faabcd2c6054d40303ac09afb2713272f257896d55821ad3712","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f578e4119e185faabcd2c6054d40303ac09afb2713272f257896d55821ad3712","first_computed_at":"2026-07-05T09:13:05.675146Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:13:05.675146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1qhEBUlgwz/oMQk9hVcEKklmUG9M89DnRDJ1HamJpSE6qZW4yrS0ezYTDuwpz1qiDdbWcuNc1qRGcrrUd0dMDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:13:05.675627Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.05358","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3cf60b82d8014913f03d808ec9328fd18300e58489a0af6dcb7b5b9bf9252c68","sha256:ecb3d5c1c368dd7fbfa3b70d0724ffd175537cc6f9a29f45548f451d39d98238"],"state_sha256":"e138136ca2aa2d1bd5d6f5834ec9fb11e8f8b7d4f9df8a48243631b0b9b3286e"}