{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4POUT6BDXZG2X2ZSAKPL4ZANE6","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":"e6c8f67c4b0797437da14be1012638bfd6571f8d0408f8faa245070a7583c1e1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-29T03:22:18Z","title_canon_sha256":"64dace7e3110aeca026ed5e21114134b59545aac8110711a0279c85b34831f03"},"schema_version":"1.0","source":{"id":"2312.17448","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.17448","created_at":"2026-07-05T07:28:52Z"},{"alias_kind":"arxiv_version","alias_value":"2312.17448v1","created_at":"2026-07-05T07:28:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.17448","created_at":"2026-07-05T07:28:52Z"},{"alias_kind":"pith_short_12","alias_value":"4POUT6BDXZG2","created_at":"2026-07-05T07:28:52Z"},{"alias_kind":"pith_short_16","alias_value":"4POUT6BDXZG2X2ZS","created_at":"2026-07-05T07:28:52Z"},{"alias_kind":"pith_short_8","alias_value":"4POUT6BD","created_at":"2026-07-05T07:28:52Z"}],"graph_snapshots":[{"event_id":"sha256:b668d1d3d6290a5149a1e38e60ce9eb1c67352dbbdebdc596075cd86b71349b9","target":"graph","created_at":"2026-07-05T07:28:52Z","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/2312.17448/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Advances in perception modeling have significantly improved the performance of object tracking. However, the current methods for specifying the target object in the initial frame are either by 1) using a box or mask template, or by 2) providing an explicit language description. These manners are cumbersome and do not allow the tracker to have self-reasoning ability. Therefore, this work proposes a new tracking task -- Instruction Tracking, which involves providing implicit tracking instructions that require the trackers to perform tracking automatically in video frames. To achieve this, we inv","authors_text":"Bin Luo, Chenyang Li, Huchuan Lu, Jiawen Zhu, Jun-Yan He, Xuansong Xie, Yifeng Geng, Zhi-Qi Cheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-29T03:22:18Z","title":"Tracking with Human-Intent Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.17448","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":"sha256:98786a48eab4076272b2db8c78a3c8fc0e7897cf5ecb131d52f1c23934d58c06","target":"record","created_at":"2026-07-05T07:28:52Z","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":"e6c8f67c4b0797437da14be1012638bfd6571f8d0408f8faa245070a7583c1e1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-29T03:22:18Z","title_canon_sha256":"64dace7e3110aeca026ed5e21114134b59545aac8110711a0279c85b34831f03"},"schema_version":"1.0","source":{"id":"2312.17448","kind":"arxiv","version":1}},"canonical_sha256":"e3dd49f823be4dabeb32029ebe640d2786b5cfaeac1481c1f247718c87ce3237","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3dd49f823be4dabeb32029ebe640d2786b5cfaeac1481c1f247718c87ce3237","first_computed_at":"2026-07-05T07:28:52.080236Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:28:52.080236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1MwL2mf4oqLA5PMMy17YeRTMVe/uVrtxPRBRmN1MvXceABRTv/fgXvERh5veQRh5xCdoeP233B9ZA8TdYBy0Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:28:52.080705Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.17448","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98786a48eab4076272b2db8c78a3c8fc0e7897cf5ecb131d52f1c23934d58c06","sha256:b668d1d3d6290a5149a1e38e60ce9eb1c67352dbbdebdc596075cd86b71349b9"],"state_sha256":"e6721f11b9eaf4ec5b810ccaf1e710e9ae4b42c00ed2cc044685121f0d992b9e"}