{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IBSUOLKJLDAYRN3UNOK6Y6AG5J","short_pith_number":"pith:IBSUOLKJ","canonical_record":{"source":{"id":"2412.12561","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T05:43:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8ecbf71efbf538b68bd215e09073e142284eddb26c94eb68b309d2d8aacae1bc","abstract_canon_sha256":"bad275fa63fac1f5988053f3cec554adf37d9dd009145e9f3ff6f6922866a05c"},"schema_version":"1.0"},"canonical_sha256":"4065472d4958c188b7746b95ec7806ea71aa1744a52e3eaf958f28d742b559a8","source":{"kind":"arxiv","id":"2412.12561","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12561","created_at":"2026-07-05T11:43:08Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12561v3","created_at":"2026-07-05T11:43:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12561","created_at":"2026-07-05T11:43:08Z"},{"alias_kind":"pith_short_12","alias_value":"IBSUOLKJLDAY","created_at":"2026-07-05T11:43:08Z"},{"alias_kind":"pith_short_16","alias_value":"IBSUOLKJLDAYRN3U","created_at":"2026-07-05T11:43:08Z"},{"alias_kind":"pith_short_8","alias_value":"IBSUOLKJ","created_at":"2026-07-05T11:43:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IBSUOLKJLDAYRN3UNOK6Y6AG5J","target":"record","payload":{"canonical_record":{"source":{"id":"2412.12561","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T05:43:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8ecbf71efbf538b68bd215e09073e142284eddb26c94eb68b309d2d8aacae1bc","abstract_canon_sha256":"bad275fa63fac1f5988053f3cec554adf37d9dd009145e9f3ff6f6922866a05c"},"schema_version":"1.0"},"canonical_sha256":"4065472d4958c188b7746b95ec7806ea71aa1744a52e3eaf958f28d742b559a8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:08.616245Z","signature_b64":"8CPUzjhONJfZ9TmK5Am5BmJxP1JTcVbnKJLfsRfaJPUAyqlatf9URvq5stDSYL+cfEnD3v+Qv7jqoQxT+qGQBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4065472d4958c188b7746b95ec7806ea71aa1744a52e3eaf958f28d742b559a8","last_reissued_at":"2026-07-05T11:43:08.615827Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:08.615827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.12561","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:43:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V/0uYrfEeUpwreiWgsdZMbOjcWAOatG2fMMO/r9qW52HmhjT0AT4iVHtl9FDdhy3GReuu3ffLkbS7d/WLGt7Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:19:33.397647Z"},"content_sha256":"28db03cef31ea6f95737001313dbfd0f7c863ff870461c3e19c3fdcf0dcc1b85","schema_version":"1.0","event_id":"sha256:28db03cef31ea6f95737001313dbfd0f7c863ff870461c3e19c3fdcf0dcc1b85"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IBSUOLKJLDAYRN3UNOK6Y6AG5J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tell Me What to Track: Infusing Robust Language Guidance for Enhanced Referring Multi-Object Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hanning Chen, Ian Bryant, Mohsen Imani, Wenjun Huang, Yang Ni, Yezi Liu, Yirui He","submitted_at":"2024-12-17T05:43:35Z","abstract_excerpt":"Referring multi-object tracking (RMOT) is an emerging cross-modal task that aims to localize an arbitrary number of targets based on a language expression and continuously track them in a video. This intricate task involves reasoning on multi-modal data and precise target localization with temporal association. However, prior studies overlook the imbalanced data distribution between newborn targets and existing targets due to the nature of the task. In addition, they only indirectly fuse multi-modal features, struggling to deliver clear guidance on newborn target detection. To solve the above "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12561","kind":"arxiv","version":3},"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/2412.12561/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:43:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2H49ruwtzJFOJVl1gBte4jdf4yUk5kXpQD9D91APqb1ndkmuUWlmJKi+YUNq6zzh99nJ983aH0qrtRRkFQG6AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:19:33.398258Z"},"content_sha256":"df4799b45436b20f7b58bbbb2d9b633c4886a378f2ce7f70fd66a8b82ac1589c","schema_version":"1.0","event_id":"sha256:df4799b45436b20f7b58bbbb2d9b633c4886a378f2ce7f70fd66a8b82ac1589c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IBSUOLKJLDAYRN3UNOK6Y6AG5J/bundle.json","state_url":"https://pith.science/pith/IBSUOLKJLDAYRN3UNOK6Y6AG5J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IBSUOLKJLDAYRN3UNOK6Y6AG5J/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T04:19:33Z","links":{"resolver":"https://pith.science/pith/IBSUOLKJLDAYRN3UNOK6Y6AG5J","bundle":"https://pith.science/pith/IBSUOLKJLDAYRN3UNOK6Y6AG5J/bundle.json","state":"https://pith.science/pith/IBSUOLKJLDAYRN3UNOK6Y6AG5J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IBSUOLKJLDAYRN3UNOK6Y6AG5J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IBSUOLKJLDAYRN3UNOK6Y6AG5J","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":"bad275fa63fac1f5988053f3cec554adf37d9dd009145e9f3ff6f6922866a05c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T05:43:35Z","title_canon_sha256":"8ecbf71efbf538b68bd215e09073e142284eddb26c94eb68b309d2d8aacae1bc"},"schema_version":"1.0","source":{"id":"2412.12561","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12561","created_at":"2026-07-05T11:43:08Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12561v3","created_at":"2026-07-05T11:43:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12561","created_at":"2026-07-05T11:43:08Z"},{"alias_kind":"pith_short_12","alias_value":"IBSUOLKJLDAY","created_at":"2026-07-05T11:43:08Z"},{"alias_kind":"pith_short_16","alias_value":"IBSUOLKJLDAYRN3U","created_at":"2026-07-05T11:43:08Z"},{"alias_kind":"pith_short_8","alias_value":"IBSUOLKJ","created_at":"2026-07-05T11:43:08Z"}],"graph_snapshots":[{"event_id":"sha256:df4799b45436b20f7b58bbbb2d9b633c4886a378f2ce7f70fd66a8b82ac1589c","target":"graph","created_at":"2026-07-05T11:43:08Z","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/2412.12561/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Referring multi-object tracking (RMOT) is an emerging cross-modal task that aims to localize an arbitrary number of targets based on a language expression and continuously track them in a video. This intricate task involves reasoning on multi-modal data and precise target localization with temporal association. However, prior studies overlook the imbalanced data distribution between newborn targets and existing targets due to the nature of the task. In addition, they only indirectly fuse multi-modal features, struggling to deliver clear guidance on newborn target detection. To solve the above ","authors_text":"Hanning Chen, Ian Bryant, Mohsen Imani, Wenjun Huang, Yang Ni, Yezi Liu, Yirui He","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T05:43:35Z","title":"Tell Me What to Track: Infusing Robust Language Guidance for Enhanced Referring Multi-Object Tracking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12561","kind":"arxiv","version":3},"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":"sha256:28db03cef31ea6f95737001313dbfd0f7c863ff870461c3e19c3fdcf0dcc1b85","target":"record","created_at":"2026-07-05T11:43:08Z","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":"bad275fa63fac1f5988053f3cec554adf37d9dd009145e9f3ff6f6922866a05c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-17T05:43:35Z","title_canon_sha256":"8ecbf71efbf538b68bd215e09073e142284eddb26c94eb68b309d2d8aacae1bc"},"schema_version":"1.0","source":{"id":"2412.12561","kind":"arxiv","version":3}},"canonical_sha256":"4065472d4958c188b7746b95ec7806ea71aa1744a52e3eaf958f28d742b559a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4065472d4958c188b7746b95ec7806ea71aa1744a52e3eaf958f28d742b559a8","first_computed_at":"2026-07-05T11:43:08.615827Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:08.615827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8CPUzjhONJfZ9TmK5Am5BmJxP1JTcVbnKJLfsRfaJPUAyqlatf9URvq5stDSYL+cfEnD3v+Qv7jqoQxT+qGQBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:08.616245Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.12561","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28db03cef31ea6f95737001313dbfd0f7c863ff870461c3e19c3fdcf0dcc1b85","sha256:df4799b45436b20f7b58bbbb2d9b633c4886a378f2ce7f70fd66a8b82ac1589c"],"state_sha256":"34535d535965bbfbf988b3f444d27091caa8604ff19d8d8e194f17ffd65ab0f4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2KcmC+0M0RN33CrIrjim6Vwxe1FQNcGfMKJ/H6lPdOJ/HwXFbYhsMLpSZXuaCMXxMEYG6XIIzpad/oLcBpy3Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T04:19:33.403222Z","bundle_sha256":"881f6867d6a7189b1303e16d9bbf09780c9c7f4305996309c0a88d57700a22b9"}}