{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZAR2RQRACSF7ISEOVNBMIQVWWL","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":"aa13192b59d3b1a8ddd18523df16ec278c7064aba1e012daa7ed51dec8243873","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-28T11:46:35Z","title_canon_sha256":"67e339941b34b2693651bef61880f59d49fd4f85abe2ac07b862e8b7bdc1eca0"},"schema_version":"1.0","source":{"id":"2507.20740","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.20740","created_at":"2026-07-05T11:44:25Z"},{"alias_kind":"arxiv_version","alias_value":"2507.20740v1","created_at":"2026-07-05T11:44:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20740","created_at":"2026-07-05T11:44:25Z"},{"alias_kind":"pith_short_12","alias_value":"ZAR2RQRACSF7","created_at":"2026-07-05T11:44:25Z"},{"alias_kind":"pith_short_16","alias_value":"ZAR2RQRACSF7ISEO","created_at":"2026-07-05T11:44:25Z"},{"alias_kind":"pith_short_8","alias_value":"ZAR2RQRA","created_at":"2026-07-05T11:44:25Z"}],"graph_snapshots":[{"event_id":"sha256:05a074b307355d30743bbd564afe57c8256d7c12a27a1caaeb5a3aa791d8beca","target":"graph","created_at":"2026-07-05T11:44:25Z","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/2507.20740/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 objects in videos based on audio cues. Existing AVS methods are primarily designed to enhance interaction efficiency but pay limited attention to modality representation discrepancies and imbalances. To overcome this, we propose the implicit counterfactual framework (ICF) to achieve unbiased cross-modal understanding. Due to the lack of semantics, heterogeneous representations may lead to erroneous matches, especially in complex scenes with ambiguous visual content or interference from multiple audio sources. We introduce the multi-granularity im","authors_text":"Guoqing Wang, Heng Tao Shen, Mingfeng Zha, Peng Wang, Tianyu Li, Yang Yang, Yangyang Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-28T11:46:35Z","title":"Implicit Counterfactual Learning for Audio-Visual Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20740","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":"sha256:0b1951e91f1b403b79ded83792fa67c16a0a64fb351ca10b5872848a6df98538","target":"record","created_at":"2026-07-05T11:44:25Z","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":"aa13192b59d3b1a8ddd18523df16ec278c7064aba1e012daa7ed51dec8243873","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-28T11:46:35Z","title_canon_sha256":"67e339941b34b2693651bef61880f59d49fd4f85abe2ac07b862e8b7bdc1eca0"},"schema_version":"1.0","source":{"id":"2507.20740","kind":"arxiv","version":1}},"canonical_sha256":"c823a8c220148bf4488eab42c442b6b2e50a1311c381b764558d2dae7a8393e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c823a8c220148bf4488eab42c442b6b2e50a1311c381b764558d2dae7a8393e9","first_computed_at":"2026-07-05T11:44:25.075490Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:25.075490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8yL6udP175u+A99XwWoHVAXCmt66m95NCpku0jlbekOlUnpgStJl16XurWeOxuvKPJTS9w09xC7C3Hpte8ChCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:25.075923Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.20740","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b1951e91f1b403b79ded83792fa67c16a0a64fb351ca10b5872848a6df98538","sha256:05a074b307355d30743bbd564afe57c8256d7c12a27a1caaeb5a3aa791d8beca"],"state_sha256":"bc6f4e42ea853c92f16dec717d4fc69d2c59079492540506e31483c68b2bc8ed"}