{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PJT3ZOTLY5KVMU24IQ232EEQ3G","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":"c0662de7c7cb1043210c7c0cab7e713ceb6cdae89797e3e7433f1597b439a0f5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-16T15:08:30Z","title_canon_sha256":"436c1a598905d0fc0854c58264d530aa4e25d4ffce95ddc5d59df3526874bede"},"schema_version":"1.0","source":{"id":"2407.11820","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.11820","created_at":"2026-07-05T09:06:07Z"},{"alias_kind":"arxiv_version","alias_value":"2407.11820v3","created_at":"2026-07-05T09:06:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11820","created_at":"2026-07-05T09:06:07Z"},{"alias_kind":"pith_short_12","alias_value":"PJT3ZOTLY5KV","created_at":"2026-07-05T09:06:07Z"},{"alias_kind":"pith_short_16","alias_value":"PJT3ZOTLY5KVMU24","created_at":"2026-07-05T09:06:07Z"},{"alias_kind":"pith_short_8","alias_value":"PJT3ZOTL","created_at":"2026-07-05T09:06:07Z"}],"graph_snapshots":[{"event_id":"sha256:ca75fc246a9ac4a8198ed7c90ea34254ebd41fe7381c356eb89547fe377dbe2d","target":"graph","created_at":"2026-07-05T09:06:07Z","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/2407.11820/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-Visual Segmentation (AVS) aims to achieve pixel-level localization of sound sources in videos, while Audio-Visual Semantic Segmentation (AVSS), as an extension of AVS, further pursues semantic understanding of audio-visual scenes. However, since the AVSS task requires the establishment of audio-visual correspondence and semantic understanding simultaneously, we observe that previous methods have struggled to handle this mashup of objectives in end-to-end training, resulting in insufficient learning and sub-optimization. Therefore, we propose a two-stage training strategy called \\textit{S","authors_text":"Di Hu, Juncheng Ma, Peiwen Sun, Yaoting Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-16T15:08:30Z","title":"Stepping Stones: A Progressive Training Strategy for Audio-Visual Semantic Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11820","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":"sha256:6d34113f075eea26ccea24b5fa73870677307de21ccbfd6f82765a38e7420be5","target":"record","created_at":"2026-07-05T09:06:07Z","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":"c0662de7c7cb1043210c7c0cab7e713ceb6cdae89797e3e7433f1597b439a0f5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-16T15:08:30Z","title_canon_sha256":"436c1a598905d0fc0854c58264d530aa4e25d4ffce95ddc5d59df3526874bede"},"schema_version":"1.0","source":{"id":"2407.11820","kind":"arxiv","version":3}},"canonical_sha256":"7a67bcba6bc75556535c4435bd1090d98277fdc6a32e1f7ebec978fbfd8ba6c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a67bcba6bc75556535c4435bd1090d98277fdc6a32e1f7ebec978fbfd8ba6c4","first_computed_at":"2026-07-05T09:06:07.225326Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:06:07.225326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iPvGsHB9PJn10a/h4G/pRj3vQrL9SrwcCoqoPX65tuHvVPFvUtroZQ5+t53VTUd8y9raRV5MOUI7LtG5e5/mCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:06:07.225807Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.11820","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d34113f075eea26ccea24b5fa73870677307de21ccbfd6f82765a38e7420be5","sha256:ca75fc246a9ac4a8198ed7c90ea34254ebd41fe7381c356eb89547fe377dbe2d"],"state_sha256":"8240ec4fe38e834912679d1c4431edf9f5e8027f6c3168583dad43d4b38012fa"}