{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PXA2AY2RZMC3R6JQQKNZPZ36DV","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":"f6350818a4dfb17f551a1b143a72a3ed6bc2b5b439f9ce6e47804aaa2b701010","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T05:20:35Z","title_canon_sha256":"412c00b1b6501332128142aa0bddddd33b034cf57b3a54f5ea8b2af2daf27f72"},"schema_version":"1.0","source":{"id":"2412.01136","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01136","created_at":"2026-07-05T10:39:23Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01136v2","created_at":"2026-07-05T10:39:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01136","created_at":"2026-07-05T10:39:23Z"},{"alias_kind":"pith_short_12","alias_value":"PXA2AY2RZMC3","created_at":"2026-07-05T10:39:23Z"},{"alias_kind":"pith_short_16","alias_value":"PXA2AY2RZMC3R6JQ","created_at":"2026-07-05T10:39:23Z"},{"alias_kind":"pith_short_8","alias_value":"PXA2AY2R","created_at":"2026-07-05T10:39:23Z"}],"graph_snapshots":[{"event_id":"sha256:4594b4ba5ad8a31f045e7b95a58176f6af2e47876e68c5a3bed3a7511a57bae4","target":"graph","created_at":"2026-07-05T10:39:23Z","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/2412.01136/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Referring video object segmentation (RVOS) requires tracking and segmenting an object throughout a video according to a given natural language expression, demanding both complex motion understanding and the alignment of visual representations with language descriptions. Given these challenges, the recently proposed Segment Anything Model 2 (SAM2) emerges as a potential candidate due to its ability to generate coherent segmentation mask tracks across video frames, and provide an inherent spatio-temporal objectness in its object token representations. In this paper, we introduce SOLA (Selection ","authors_text":"Heeji Yoon, Hyunwook Choi, Sangbeom Lim, Seongchan Kim, Seungryong Kim, Woojeong Jin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T05:20:35Z","title":"Referring Video Object Segmentation via Language-aligned Track Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01136","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":"sha256:7ce027dc634a71f283ec0b0771011d40939311f54f1568eb38685029377aeb30","target":"record","created_at":"2026-07-05T10:39:23Z","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":"f6350818a4dfb17f551a1b143a72a3ed6bc2b5b439f9ce6e47804aaa2b701010","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T05:20:35Z","title_canon_sha256":"412c00b1b6501332128142aa0bddddd33b034cf57b3a54f5ea8b2af2daf27f72"},"schema_version":"1.0","source":{"id":"2412.01136","kind":"arxiv","version":2}},"canonical_sha256":"7dc1a06351cb05b8f930829b97e77e1d78e43ac4b43d85563d8c8c35760d10bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7dc1a06351cb05b8f930829b97e77e1d78e43ac4b43d85563d8c8c35760d10bd","first_computed_at":"2026-07-05T10:39:23.644296Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:39:23.644296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DWQd8LSWWOVoa5mZpmrmoc1GjQ51ut2XOxyzGR0WaZK5DqDemKZvxM2Q219DPM0pg0qbM4FCKuwEsSzVGXDqAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:39:23.644800Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.01136","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ce027dc634a71f283ec0b0771011d40939311f54f1568eb38685029377aeb30","sha256:4594b4ba5ad8a31f045e7b95a58176f6af2e47876e68c5a3bed3a7511a57bae4"],"state_sha256":"87c808aadfe8dc1e5d5e7962cd8cd33ad0a38f2b609e0064b6f2f90462234410"}