{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:L4UHJG72QKDAE7EIO2PAFTPRBF","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":"81656333de1aac669eb91d1a63806864b35375461fa5f52f14e6f62fa6c992b3","cross_cats_sorted":["cs.CV","cs.MA","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-08-06T13:05:09Z","title_canon_sha256":"3f4c10638c17d1e3b0fd49a05c9e7b28fe346d331f46dd27b55defa168abbcc2"},"schema_version":"1.0","source":{"id":"2508.04418","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.04418","created_at":"2026-07-05T11:49:36Z"},{"alias_kind":"arxiv_version","alias_value":"2508.04418v1","created_at":"2026-07-05T11:49:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04418","created_at":"2026-07-05T11:49:36Z"},{"alias_kind":"pith_short_12","alias_value":"L4UHJG72QKDA","created_at":"2026-07-05T11:49:36Z"},{"alias_kind":"pith_short_16","alias_value":"L4UHJG72QKDAE7EI","created_at":"2026-07-05T11:49:36Z"},{"alias_kind":"pith_short_8","alias_value":"L4UHJG72","created_at":"2026-07-05T11:49:36Z"}],"graph_snapshots":[{"event_id":"sha256:2eed60872342b88ac7779cefe0c56e27876c537c19852556846c801fbbc802ac","target":"graph","created_at":"2026-07-05T11:49:36Z","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/2508.04418/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Referring Audio-Visual Segmentation (Ref-AVS) aims to segment target objects in audible videos based on given reference expressions. Prior works typically rely on learning latent embeddings via multimodal fusion to prompt a tunable SAM/SAM2 decoder for segmentation, which requires strong pixel-level supervision and lacks interpretability. From a novel perspective of explicit reference understanding, we propose TGS-Agent, which decomposes the task into a Think-Ground-Segment process, mimicking the human reasoning procedure by first identifying the referred object through multimodal analysis, fo","authors_text":"Hisham Cholakkal, Jinxing Zhou, Mingfei Han, Rao Muhammad Anwer, Tong Wang, Xiaojun Chang, Yanghao Zhou","cross_cats":["cs.CV","cs.MA","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-08-06T13:05:09Z","title":"Think Before You Segment: An Object-aware Reasoning Agent for Referring Audio-Visual Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04418","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":"sha256:92df6be08def18218f82bd9a36e764b8e703b52564f2f5169b6aab11999d372e","target":"record","created_at":"2026-07-05T11:49:36Z","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":"81656333de1aac669eb91d1a63806864b35375461fa5f52f14e6f62fa6c992b3","cross_cats_sorted":["cs.CV","cs.MA","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-08-06T13:05:09Z","title_canon_sha256":"3f4c10638c17d1e3b0fd49a05c9e7b28fe346d331f46dd27b55defa168abbcc2"},"schema_version":"1.0","source":{"id":"2508.04418","kind":"arxiv","version":1}},"canonical_sha256":"5f28749bfa8286027c88769e02cdf1095963f99d66801c780072e051a845340e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f28749bfa8286027c88769e02cdf1095963f99d66801c780072e051a845340e","first_computed_at":"2026-07-05T11:49:36.906735Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:36.906735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hN1Q0Jpd/oPeb4OjfgsfX5azbV+dgY7E7tcOFwjhFHCOM5zWy7USxOdrnbWTa0HLVfsqhnUovd7ZHL/9ogttAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:36.907164Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.04418","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92df6be08def18218f82bd9a36e764b8e703b52564f2f5169b6aab11999d372e","sha256:2eed60872342b88ac7779cefe0c56e27876c537c19852556846c801fbbc802ac"],"state_sha256":"b33418632d340d88dadd4cca36e8751e1e6c61cc00632f481b0dd4a299717b03"}