{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MKEHJDR5AWAOUEK5N2RKBNZGNA","short_pith_number":"pith:MKEHJDR5","canonical_record":{"source":{"id":"2405.14200","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T05:58:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bdf32a40a421849abcfb45077384a4060f7bebfc9d02cd23c7a2dfb11bac1f7d","abstract_canon_sha256":"8c0240bb382defbcb15906753e0905ed0ed62cc2f80afcf8670036c30f5fa3ef"},"schema_version":"1.0"},"canonical_sha256":"6288748e3d0580ea115d6ea2a0b72668099330c7b7a9d459530a5e06181ee1e2","source":{"kind":"arxiv","id":"2405.14200","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.14200","created_at":"2026-07-05T08:25:34Z"},{"alias_kind":"arxiv_version","alias_value":"2405.14200v2","created_at":"2026-07-05T08:25:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14200","created_at":"2026-07-05T08:25:34Z"},{"alias_kind":"pith_short_12","alias_value":"MKEHJDR5AWAO","created_at":"2026-07-05T08:25:34Z"},{"alias_kind":"pith_short_16","alias_value":"MKEHJDR5AWAOUEK5","created_at":"2026-07-05T08:25:34Z"},{"alias_kind":"pith_short_8","alias_value":"MKEHJDR5","created_at":"2026-07-05T08:25:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MKEHJDR5AWAOUEK5N2RKBNZGNA","target":"record","payload":{"canonical_record":{"source":{"id":"2405.14200","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T05:58:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bdf32a40a421849abcfb45077384a4060f7bebfc9d02cd23c7a2dfb11bac1f7d","abstract_canon_sha256":"8c0240bb382defbcb15906753e0905ed0ed62cc2f80afcf8670036c30f5fa3ef"},"schema_version":"1.0"},"canonical_sha256":"6288748e3d0580ea115d6ea2a0b72668099330c7b7a9d459530a5e06181ee1e2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:34.487992Z","signature_b64":"dPkfwK1U0MENpZkP85wY8CuaHBa8s9KAB6SRJWY42MhtqUBDm3IEnONU17jI6smnE49EReKQvxvso4WQK1aFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6288748e3d0580ea115d6ea2a0b72668099330c7b7a9d459530a5e06181ee1e2","last_reissued_at":"2026-07-05T08:25:34.487567Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:34.487567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.14200","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:25:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ev0IZnpNSxB/gGgoAvD02iqHf34PYfSfzDUiOrkAGX3b0qD3XGAongSrSNe06Neps6SbROtLgd/f5fnhRb/BCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:20:33.439898Z"},"content_sha256":"6f769e3f55f392c5772ea5c862df257188cddeff27447748c7d929fd3dc1c64a","schema_version":"1.0","event_id":"sha256:6f769e3f55f392c5772ea5c862df257188cddeff27447748c7d929fd3dc1c64a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MKEHJDR5AWAOUEK5N2RKBNZGNA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Awesome Multi-modal Object Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chunhui Zhang, Hao Wen, Li Liu, Xi Zhou, Yanfeng Wang","submitted_at":"2024-05-23T05:58:10Z","abstract_excerpt":"Multi-modal object tracking (MMOT) is an emerging field that combines data from various modalities, \\eg vision (RGB), depth, thermal infrared, event, language and audio, to estimate the state of an arbitrary object in a video sequence. It is of great significance for many applications such as autonomous driving and intelligent surveillance. In recent years, MMOT has received more and more attention. However, existing MMOT algorithms mainly focus on two modalities (\\eg RGB+depth, RGB+thermal infrared, and RGB+language). To leverage more modalities, some recent efforts have been made to learn a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14200","kind":"arxiv","version":2},"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/2405.14200/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":"2026-07-05T08:25:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9MuyVk7baopCo1uk5AKLyMoSf7qTXQLI/vDakU0AgP6D7DyYvBwdm60sT2cSB7jyc2TAXigj4oPGuU+rqhFPCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:20:33.440426Z"},"content_sha256":"96ddbf8a61530f75f6a4699231197fc570184d2489864aa271fb1f94ee81a7da","schema_version":"1.0","event_id":"sha256:96ddbf8a61530f75f6a4699231197fc570184d2489864aa271fb1f94ee81a7da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MKEHJDR5AWAOUEK5N2RKBNZGNA/bundle.json","state_url":"https://pith.science/pith/MKEHJDR5AWAOUEK5N2RKBNZGNA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MKEHJDR5AWAOUEK5N2RKBNZGNA/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":"2026-08-09T00:20:33Z","links":{"resolver":"https://pith.science/pith/MKEHJDR5AWAOUEK5N2RKBNZGNA","bundle":"https://pith.science/pith/MKEHJDR5AWAOUEK5N2RKBNZGNA/bundle.json","state":"https://pith.science/pith/MKEHJDR5AWAOUEK5N2RKBNZGNA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MKEHJDR5AWAOUEK5N2RKBNZGNA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MKEHJDR5AWAOUEK5N2RKBNZGNA","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":"8c0240bb382defbcb15906753e0905ed0ed62cc2f80afcf8670036c30f5fa3ef","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T05:58:10Z","title_canon_sha256":"bdf32a40a421849abcfb45077384a4060f7bebfc9d02cd23c7a2dfb11bac1f7d"},"schema_version":"1.0","source":{"id":"2405.14200","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.14200","created_at":"2026-07-05T08:25:34Z"},{"alias_kind":"arxiv_version","alias_value":"2405.14200v2","created_at":"2026-07-05T08:25:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14200","created_at":"2026-07-05T08:25:34Z"},{"alias_kind":"pith_short_12","alias_value":"MKEHJDR5AWAO","created_at":"2026-07-05T08:25:34Z"},{"alias_kind":"pith_short_16","alias_value":"MKEHJDR5AWAOUEK5","created_at":"2026-07-05T08:25:34Z"},{"alias_kind":"pith_short_8","alias_value":"MKEHJDR5","created_at":"2026-07-05T08:25:34Z"}],"graph_snapshots":[{"event_id":"sha256:96ddbf8a61530f75f6a4699231197fc570184d2489864aa271fb1f94ee81a7da","target":"graph","created_at":"2026-07-05T08:25:34Z","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/2405.14200/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal object tracking (MMOT) is an emerging field that combines data from various modalities, \\eg vision (RGB), depth, thermal infrared, event, language and audio, to estimate the state of an arbitrary object in a video sequence. It is of great significance for many applications such as autonomous driving and intelligent surveillance. In recent years, MMOT has received more and more attention. However, existing MMOT algorithms mainly focus on two modalities (\\eg RGB+depth, RGB+thermal infrared, and RGB+language). To leverage more modalities, some recent efforts have been made to learn a ","authors_text":"Chunhui Zhang, Hao Wen, Li Liu, Xi Zhou, Yanfeng Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T05:58:10Z","title":"Awesome Multi-modal Object Tracking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14200","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":"sha256:6f769e3f55f392c5772ea5c862df257188cddeff27447748c7d929fd3dc1c64a","target":"record","created_at":"2026-07-05T08:25:34Z","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":"8c0240bb382defbcb15906753e0905ed0ed62cc2f80afcf8670036c30f5fa3ef","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-23T05:58:10Z","title_canon_sha256":"bdf32a40a421849abcfb45077384a4060f7bebfc9d02cd23c7a2dfb11bac1f7d"},"schema_version":"1.0","source":{"id":"2405.14200","kind":"arxiv","version":2}},"canonical_sha256":"6288748e3d0580ea115d6ea2a0b72668099330c7b7a9d459530a5e06181ee1e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6288748e3d0580ea115d6ea2a0b72668099330c7b7a9d459530a5e06181ee1e2","first_computed_at":"2026-07-05T08:25:34.487567Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:34.487567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dPkfwK1U0MENpZkP85wY8CuaHBa8s9KAB6SRJWY42MhtqUBDm3IEnONU17jI6smnE49EReKQvxvso4WQK1aFAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:34.487992Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.14200","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f769e3f55f392c5772ea5c862df257188cddeff27447748c7d929fd3dc1c64a","sha256:96ddbf8a61530f75f6a4699231197fc570184d2489864aa271fb1f94ee81a7da"],"state_sha256":"615dbd9b102d4458a0f9bbc3967c6c885c75338f25c44d36f75eb598d87536aa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MwifU7Mlg+V/OSSNAxll0PPDWHCqsyA3hlgBlCYmelZu8qCaPujaTdPrDH4MvWopUk71To5kgjiAOGRJcrgeDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:20:33.446778Z","bundle_sha256":"a552dcfeb3007ee2b0e7ebecc848f3a442c8cf1f6e3468de78fa5a39e63b79f6"}}