{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YBK54A3S7RSXIZ5U6I63MMMVKI","short_pith_number":"pith:YBK54A3S","canonical_record":{"source":{"id":"2507.20177","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-27T08:47:42Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"77277abe4a8dce453b1d06e3bc810fa40eac771dcd9e169db10feda186b8ee18","abstract_canon_sha256":"2422b3a643c46b1e791c5baf848ffe19f873d76dd8378dc1e86c4f6b3d62150d"},"schema_version":"1.0"},"canonical_sha256":"c055de0372fc657467b4f23db6319552245e0b696d102f58d6f9013f7be1873c","source":{"kind":"arxiv","id":"2507.20177","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.20177","created_at":"2026-07-05T11:44:53Z"},{"alias_kind":"arxiv_version","alias_value":"2507.20177v1","created_at":"2026-07-05T11:44:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20177","created_at":"2026-07-05T11:44:53Z"},{"alias_kind":"pith_short_12","alias_value":"YBK54A3S7RSX","created_at":"2026-07-05T11:44:53Z"},{"alias_kind":"pith_short_16","alias_value":"YBK54A3S7RSXIZ5U","created_at":"2026-07-05T11:44:53Z"},{"alias_kind":"pith_short_8","alias_value":"YBK54A3S","created_at":"2026-07-05T11:44:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YBK54A3S7RSXIZ5U6I63MMMVKI","target":"record","payload":{"canonical_record":{"source":{"id":"2507.20177","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-27T08:47:42Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"77277abe4a8dce453b1d06e3bc810fa40eac771dcd9e169db10feda186b8ee18","abstract_canon_sha256":"2422b3a643c46b1e791c5baf848ffe19f873d76dd8378dc1e86c4f6b3d62150d"},"schema_version":"1.0"},"canonical_sha256":"c055de0372fc657467b4f23db6319552245e0b696d102f58d6f9013f7be1873c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:53.418817Z","signature_b64":"B9tS1dJuUUjg7PVBMlvmONBuaFPJZNhEx9hu9Uq0dzVHh1UH85Ldm8Mulix5v9POpGJhsUVQDX5pZKhhsXPwDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c055de0372fc657467b4f23db6319552245e0b696d102f58d6f9013f7be1873c","last_reissued_at":"2026-07-05T11:44:53.418392Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:53.418392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.20177","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:44:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6XVS0BtZucVwdKNhWS6A/L7uT9N+oDUsaIcbC0Vsn2mhuYA84p4qL3F6j74EFEsm+KMsd6+tHhSr3D09H7/cAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T16:14:47.891006Z"},"content_sha256":"84719ab5b3fcdbd2176cfa80571d0dc15dd55d7d2d7c7ae141991ea49aac695f","schema_version":"1.0","event_id":"sha256:84719ab5b3fcdbd2176cfa80571d0dc15dd55d7d2d7c7ae141991ea49aac695f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YBK54A3S7RSXIZ5U6I63MMMVKI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Universal Modal Tracking with Online Dense Temporal Token Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Bineng Zhong, Guorong Li, Qihua Liang, Rongrong Ji, Shengping Zhang, Xianxian Li, Yaozong Zheng","submitted_at":"2025-07-27T08:47:42Z","abstract_excerpt":"We propose a universal video-level modality-awareness tracking model with online dense temporal token learning (called {\\modaltracker}). It is designed to support various tracking tasks, including RGB, RGB+Thermal, RGB+Depth, and RGB+Event, utilizing the same model architecture and parameters. Specifically, our model is designed with three core goals: \\textbf{Video-level Sampling}. We expand the model's inputs to a video sequence level, aiming to see a richer video context from an near-global perspective. \\textbf{Video-level Association}. Furthermore, we introduce two simple yet effective onli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20177","kind":"arxiv","version":1},"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/2507.20177/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":"2026-07-05T11:44:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vuElTc/+5nwhkksGa3dsKA7gU9alrqk+BML8Yn1d0jKP2Kj9SP3fcgoC+DHZ+QBUFWXDv9rfWtCqbiX1yQJeBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T16:14:47.891974Z"},"content_sha256":"9a159b50f821aedfaf031fd5b5d2e12a431756053862016da636cbdaa76e9cef","schema_version":"1.0","event_id":"sha256:9a159b50f821aedfaf031fd5b5d2e12a431756053862016da636cbdaa76e9cef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YBK54A3S7RSXIZ5U6I63MMMVKI/bundle.json","state_url":"https://pith.science/pith/YBK54A3S7RSXIZ5U6I63MMMVKI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YBK54A3S7RSXIZ5U6I63MMMVKI/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":"2026-08-16T16:14:47Z","links":{"resolver":"https://pith.science/pith/YBK54A3S7RSXIZ5U6I63MMMVKI","bundle":"https://pith.science/pith/YBK54A3S7RSXIZ5U6I63MMMVKI/bundle.json","state":"https://pith.science/pith/YBK54A3S7RSXIZ5U6I63MMMVKI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YBK54A3S7RSXIZ5U6I63MMMVKI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YBK54A3S7RSXIZ5U6I63MMMVKI","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":"2422b3a643c46b1e791c5baf848ffe19f873d76dd8378dc1e86c4f6b3d62150d","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-27T08:47:42Z","title_canon_sha256":"77277abe4a8dce453b1d06e3bc810fa40eac771dcd9e169db10feda186b8ee18"},"schema_version":"1.0","source":{"id":"2507.20177","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.20177","created_at":"2026-07-05T11:44:53Z"},{"alias_kind":"arxiv_version","alias_value":"2507.20177v1","created_at":"2026-07-05T11:44:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20177","created_at":"2026-07-05T11:44:53Z"},{"alias_kind":"pith_short_12","alias_value":"YBK54A3S7RSX","created_at":"2026-07-05T11:44:53Z"},{"alias_kind":"pith_short_16","alias_value":"YBK54A3S7RSXIZ5U","created_at":"2026-07-05T11:44:53Z"},{"alias_kind":"pith_short_8","alias_value":"YBK54A3S","created_at":"2026-07-05T11:44:53Z"}],"graph_snapshots":[{"event_id":"sha256:9a159b50f821aedfaf031fd5b5d2e12a431756053862016da636cbdaa76e9cef","target":"graph","created_at":"2026-07-05T11:44:53Z","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/2507.20177/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a universal video-level modality-awareness tracking model with online dense temporal token learning (called {\\modaltracker}). It is designed to support various tracking tasks, including RGB, RGB+Thermal, RGB+Depth, and RGB+Event, utilizing the same model architecture and parameters. Specifically, our model is designed with three core goals: \\textbf{Video-level Sampling}. We expand the model's inputs to a video sequence level, aiming to see a richer video context from an near-global perspective. \\textbf{Video-level Association}. Furthermore, we introduce two simple yet effective onli","authors_text":"Bineng Zhong, Guorong Li, Qihua Liang, Rongrong Ji, Shengping Zhang, Xianxian Li, Yaozong Zheng","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-27T08:47:42Z","title":"Towards Universal Modal Tracking with Online Dense Temporal Token Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20177","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":"sha256:84719ab5b3fcdbd2176cfa80571d0dc15dd55d7d2d7c7ae141991ea49aac695f","target":"record","created_at":"2026-07-05T11:44:53Z","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":"2422b3a643c46b1e791c5baf848ffe19f873d76dd8378dc1e86c4f6b3d62150d","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-27T08:47:42Z","title_canon_sha256":"77277abe4a8dce453b1d06e3bc810fa40eac771dcd9e169db10feda186b8ee18"},"schema_version":"1.0","source":{"id":"2507.20177","kind":"arxiv","version":1}},"canonical_sha256":"c055de0372fc657467b4f23db6319552245e0b696d102f58d6f9013f7be1873c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c055de0372fc657467b4f23db6319552245e0b696d102f58d6f9013f7be1873c","first_computed_at":"2026-07-05T11:44:53.418392Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:53.418392Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B9tS1dJuUUjg7PVBMlvmONBuaFPJZNhEx9hu9Uq0dzVHh1UH85Ldm8Mulix5v9POpGJhsUVQDX5pZKhhsXPwDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:53.418817Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.20177","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84719ab5b3fcdbd2176cfa80571d0dc15dd55d7d2d7c7ae141991ea49aac695f","sha256:9a159b50f821aedfaf031fd5b5d2e12a431756053862016da636cbdaa76e9cef"],"state_sha256":"497e9c81497e0ca8e9f934b0938a24fc0701a038c678426100a06f0ed7c44c3c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ixZ3MTJimVM5OYqEnhQPGwlm3eMh7SwWRD1H/5f5sq4QtuT5OjxiHl/l/kXvoPsziprTl6UdPgBCsm5Scps/Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T16:14:47.898117Z","bundle_sha256":"36b5d7cf4a6ed08d4c203850cab4560986fbf4c6a67cd86b7ba19a89ec37d11e"}}