{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WDW73WAAGFFVCTVZTLPWV3MYVN","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":"86406ccdd5d7226b535e0787a94a83a6f5a0fea3984da6f38f8894d60b41f8ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-28T15:47:32Z","title_canon_sha256":"cb1e6995549887080ff81a6068a977709cdf2485f7898708e4effd636def6714"},"schema_version":"1.0","source":{"id":"2408.15876","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.15876","created_at":"2026-07-05T09:53:04Z"},{"alias_kind":"arxiv_version","alias_value":"2408.15876v2","created_at":"2026-07-05T09:53:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15876","created_at":"2026-07-05T09:53:04Z"},{"alias_kind":"pith_short_12","alias_value":"WDW73WAAGFFV","created_at":"2026-07-05T09:53:04Z"},{"alias_kind":"pith_short_16","alias_value":"WDW73WAAGFFVCTVZ","created_at":"2026-07-05T09:53:04Z"},{"alias_kind":"pith_short_8","alias_value":"WDW73WAA","created_at":"2026-07-05T09:53:04Z"}],"graph_snapshots":[{"event_id":"sha256:15218274972ae1d6d922250a18813fece1d3a8cc229d0ed7e82547a1d4906001","target":"graph","created_at":"2026-07-05T09:53:04Z","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/2408.15876/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose an Audio-Language-Referenced SAM 2 (AL-Ref-SAM 2) pipeline to explore the training-free paradigm for audio and language-referenced video object segmentation, namely AVS and RVOS tasks. The intuitive solution leverages GroundingDINO to identify the target object from a single frame and SAM 2 to segment the identified object throughout the video, which is less robust to spatiotemporal variations due to a lack of video context exploration. Thus, in our AL-Ref-SAM 2 pipeline, we propose a novel GPT-assisted Pivot Selection (GPT-PS) module to instruct GPT-4 to perform two-","authors_text":"Hongyu Li, Jizhong Han, Rui Ling, Shaofei Huang, Si Liu, Tianrui Hui, Xiaoming Wei, Zongheng Tang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-28T15:47:32Z","title":"Unleashing the Temporal-Spatial Reasoning Capacity of GPT for Training-Free Audio and Language Referenced Video Object Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15876","kind":"arxiv","version":2},"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":"sha256:8a25ab5ecaa0cc111cd83c30cfcb8be19718d93752d4337bfc95cbf8fec2b88d","target":"record","created_at":"2026-07-05T09:53:04Z","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":"86406ccdd5d7226b535e0787a94a83a6f5a0fea3984da6f38f8894d60b41f8ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-28T15:47:32Z","title_canon_sha256":"cb1e6995549887080ff81a6068a977709cdf2485f7898708e4effd636def6714"},"schema_version":"1.0","source":{"id":"2408.15876","kind":"arxiv","version":2}},"canonical_sha256":"b0edfdd800314b514eb99adf6aed98ab699b209a4a329c1e73d67ee8408edf2f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0edfdd800314b514eb99adf6aed98ab699b209a4a329c1e73d67ee8408edf2f","first_computed_at":"2026-07-05T09:53:04.187325Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:04.187325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oQ1x+QtbExMcNKSS467SwOvDFJPDzA5pXKkYCXWXOtJEbxAFk7RcqkQrxlvyLeQlCl6hqYQqsAUhLc0KPiTGBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:04.187815Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.15876","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a25ab5ecaa0cc111cd83c30cfcb8be19718d93752d4337bfc95cbf8fec2b88d","sha256:15218274972ae1d6d922250a18813fece1d3a8cc229d0ed7e82547a1d4906001"],"state_sha256":"923036d435f0a18ff832f1dc00b576b8359c375df2f1b7ae177e0897fac1a206"}