{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L4UHJG72QKDAE7EIO2PAFTPRBF","short_pith_number":"pith:L4UHJG72","schema_version":"1.0","canonical_sha256":"5f28749bfa8286027c88769e02cdf1095963f99d66801c780072e051a845340e","source":{"kind":"arxiv","id":"2508.04418","version":1},"attestation_state":"computed","paper":{"title":"Think Before You Segment: An Object-aware Reasoning Agent for Referring Audio-Visual Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MA","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Hisham Cholakkal, Jinxing Zhou, Mingfei Han, Rao Muhammad Anwer, Tong Wang, Xiaojun Chang, Yanghao Zhou","submitted_at":"2025-08-06T13:05:09Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2508.04418","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-08-06T13:05:09Z","cross_cats_sorted":["cs.CV","cs.MA","cs.SD","eess.AS"],"title_canon_sha256":"3f4c10638c17d1e3b0fd49a05c9e7b28fe346d331f46dd27b55defa168abbcc2","abstract_canon_sha256":"81656333de1aac669eb91d1a63806864b35375461fa5f52f14e6f62fa6c992b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:36.907164Z","signature_b64":"hN1Q0Jpd/oPeb4OjfgsfX5azbV+dgY7E7tcOFwjhFHCOM5zWy7USxOdrnbWTa0HLVfsqhnUovd7ZHL/9ogttAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f28749bfa8286027c88769e02cdf1095963f99d66801c780072e051a845340e","last_reissued_at":"2026-07-05T11:49:36.906735Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:36.906735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Think Before You Segment: An Object-aware Reasoning Agent for Referring Audio-Visual Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.MA","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Hisham Cholakkal, Jinxing Zhou, Mingfei Han, Rao Muhammad Anwer, Tong Wang, Xiaojun Chang, Yanghao Zhou","submitted_at":"2025-08-06T13:05:09Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04418","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.04418/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2508.04418","created_at":"2026-07-05T11:49:36.906791+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.04418v1","created_at":"2026-07-05T11:49:36.906791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04418","created_at":"2026-07-05T11:49:36.906791+00:00"},{"alias_kind":"pith_short_12","alias_value":"L4UHJG72QKDA","created_at":"2026-07-05T11:49:36.906791+00:00"},{"alias_kind":"pith_short_16","alias_value":"L4UHJG72QKDAE7EI","created_at":"2026-07-05T11:49:36.906791+00:00"},{"alias_kind":"pith_short_8","alias_value":"L4UHJG72","created_at":"2026-07-05T11:49:36.906791+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07154","citing_title":"PRIMED: Adaptive Modality Suppression for Referring Audio-Visual Segmentation via Biased Competition","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L4UHJG72QKDAE7EIO2PAFTPRBF","json":"https://pith.science/pith/L4UHJG72QKDAE7EIO2PAFTPRBF.json","graph_json":"https://pith.science/api/pith-number/L4UHJG72QKDAE7EIO2PAFTPRBF/graph.json","events_json":"https://pith.science/api/pith-number/L4UHJG72QKDAE7EIO2PAFTPRBF/events.json","paper":"https://pith.science/paper/L4UHJG72"},"agent_actions":{"view_html":"https://pith.science/pith/L4UHJG72QKDAE7EIO2PAFTPRBF","download_json":"https://pith.science/pith/L4UHJG72QKDAE7EIO2PAFTPRBF.json","view_paper":"https://pith.science/paper/L4UHJG72","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.04418&json=true","fetch_graph":"https://pith.science/api/pith-number/L4UHJG72QKDAE7EIO2PAFTPRBF/graph.json","fetch_events":"https://pith.science/api/pith-number/L4UHJG72QKDAE7EIO2PAFTPRBF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L4UHJG72QKDAE7EIO2PAFTPRBF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L4UHJG72QKDAE7EIO2PAFTPRBF/action/storage_attestation","attest_author":"https://pith.science/pith/L4UHJG72QKDAE7EIO2PAFTPRBF/action/author_attestation","sign_citation":"https://pith.science/pith/L4UHJG72QKDAE7EIO2PAFTPRBF/action/citation_signature","submit_replication":"https://pith.science/pith/L4UHJG72QKDAE7EIO2PAFTPRBF/action/replication_record"}},"created_at":"2026-07-05T11:49:36.906791+00:00","updated_at":"2026-07-05T11:49:36.906791+00:00"}