{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3457N2QLN3GRELAIVIXMTPUE75","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":"4a8f24f66b75e5b69b6ddeb7cb353df98f5919b36bede70aac863957914798d8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-29T04:58:33Z","title_canon_sha256":"e59021b4baf0531d1309f9987175beefea2736a7c00abf3c8804c7585a3f4133"},"schema_version":"1.0","source":{"id":"2403.19975","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.19975","created_at":"2026-07-05T08:02:11Z"},{"alias_kind":"arxiv_version","alias_value":"2403.19975v1","created_at":"2026-07-05T08:02:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19975","created_at":"2026-07-05T08:02:11Z"},{"alias_kind":"pith_short_12","alias_value":"3457N2QLN3GR","created_at":"2026-07-05T08:02:11Z"},{"alias_kind":"pith_short_16","alias_value":"3457N2QLN3GRELAI","created_at":"2026-07-05T08:02:11Z"},{"alias_kind":"pith_short_8","alias_value":"3457N2QL","created_at":"2026-07-05T08:02:11Z"}],"graph_snapshots":[{"event_id":"sha256:5b8d7c03355f51b62c4f318259ab43099ac528497d45ae6c13f39b9715156a5c","target":"graph","created_at":"2026-07-05T08:02:11Z","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/2403.19975/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tracking by natural language specification (TNL) aims to consistently localize a target in a video sequence given a linguistic description in the initial frame. Existing methodologies perform language-based and template-based matching for target reasoning separately and merge the matching results from two sources, which suffer from tracking drift when language and visual templates miss-align with the dynamic target state and ambiguity in the later merging stage. To tackle the issues, we propose a joint multi-modal tracking framework with 1) a prompt modulation module to leverage the complement","authors_text":"Jiming Chen, Qi Ye, Shuting He, Wenhan Luo, Yanyan Shao, Yuchao Feng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-29T04:58:33Z","title":"Context-Aware Integration of Language and Visual References for Natural Language Tracking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19975","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:f10758a14c9942f810cf852f05d5715a24d302342aa95b59176c2c94439f3220","target":"record","created_at":"2026-07-05T08:02:11Z","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":"4a8f24f66b75e5b69b6ddeb7cb353df98f5919b36bede70aac863957914798d8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-29T04:58:33Z","title_canon_sha256":"e59021b4baf0531d1309f9987175beefea2736a7c00abf3c8804c7585a3f4133"},"schema_version":"1.0","source":{"id":"2403.19975","kind":"arxiv","version":1}},"canonical_sha256":"df3bf6ea0b6ecd122c08aa2ec9be84ff6b24b214e3c2756c92fe7100c22abb20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df3bf6ea0b6ecd122c08aa2ec9be84ff6b24b214e3c2756c92fe7100c22abb20","first_computed_at":"2026-07-05T08:02:11.449803Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:11.449803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wJZxBq5IHWrmNP2SeIMNT8y98KEa8ZmA4lg2ZEGr9jnGLRNtuMLGcIvVcBdD1HMbpreh6SUL/gvh+QnuTryoDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:11.450224Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.19975","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f10758a14c9942f810cf852f05d5715a24d302342aa95b59176c2c94439f3220","sha256:5b8d7c03355f51b62c4f318259ab43099ac528497d45ae6c13f39b9715156a5c"],"state_sha256":"22541255eb24c69603d9163906e3859f79c677b787a3afe3d12ed1dd9bd0baf4"}