{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5UZWKUUA2XH3LTRKISNMWCYMEW","short_pith_number":"pith:5UZWKUUA","canonical_record":{"source":{"id":"2507.21606","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T09:04:03Z","cross_cats_sorted":[],"title_canon_sha256":"c6d4f525f127f9ed5589acda0fcaa799d256ce00b767d70a5a8b2da9a1fbbce9","abstract_canon_sha256":"b4099cd98b39d81f05519ee5228796eef2a8d3d446bd0f6b38c8d24f9af0d680"},"schema_version":"1.0"},"canonical_sha256":"ed33655280d5cfb5ce2a449acb0b0c25a11dae455f03c6c447b6f59ed64ba0ac","source":{"kind":"arxiv","id":"2507.21606","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.21606","created_at":"2026-07-05T11:45:03Z"},{"alias_kind":"arxiv_version","alias_value":"2507.21606v1","created_at":"2026-07-05T11:45:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21606","created_at":"2026-07-05T11:45:03Z"},{"alias_kind":"pith_short_12","alias_value":"5UZWKUUA2XH3","created_at":"2026-07-05T11:45:03Z"},{"alias_kind":"pith_short_16","alias_value":"5UZWKUUA2XH3LTRK","created_at":"2026-07-05T11:45:03Z"},{"alias_kind":"pith_short_8","alias_value":"5UZWKUUA","created_at":"2026-07-05T11:45:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5UZWKUUA2XH3LTRKISNMWCYMEW","target":"record","payload":{"canonical_record":{"source":{"id":"2507.21606","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T09:04:03Z","cross_cats_sorted":[],"title_canon_sha256":"c6d4f525f127f9ed5589acda0fcaa799d256ce00b767d70a5a8b2da9a1fbbce9","abstract_canon_sha256":"b4099cd98b39d81f05519ee5228796eef2a8d3d446bd0f6b38c8d24f9af0d680"},"schema_version":"1.0"},"canonical_sha256":"ed33655280d5cfb5ce2a449acb0b0c25a11dae455f03c6c447b6f59ed64ba0ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:03.050502Z","signature_b64":"hNa8+hP8qRttxGUQW+FaObwZ5nnnD6D+4AW9qx0BM+TQoRBfGWN+vzFop8wkjR8RSuqMvJ9Em1gjwoIq92uXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed33655280d5cfb5ce2a449acb0b0c25a11dae455f03c6c447b6f59ed64ba0ac","last_reissued_at":"2026-07-05T11:45:03.050057Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:03.050057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.21606","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":"2026-07-05T11:45:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N3W62Norlnn9eWEQP3ScRBYyfdYgggxyuGvmTNwADcth6iWfbLkalUFZV+v5bT6Q0/LFOjrKhltKh5ZQTdAFDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:59:50.279217Z"},"content_sha256":"16d841b11eb5307a4c9ba0cf25bea2a1b9cf4679c354e88d67d8f6b08a853dfa","schema_version":"1.0","event_id":"sha256:16d841b11eb5307a4c9ba0cf25bea2a1b9cf4679c354e88d67d8f6b08a853dfa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5UZWKUUA2XH3LTRKISNMWCYMEW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Decoupled Spatio-Temporal Consistency Learning for Self-Supervised Tracking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bineng Zhong, Ning Li, Qihua Liang, Shuxiang Song, Yaozong Zheng","submitted_at":"2025-07-29T09:04:03Z","abstract_excerpt":"The success of visual tracking has been largely driven by datasets with manual box annotations. However, these box annotations require tremendous human effort, limiting the scale and diversity of existing tracking datasets. In this work, we present a novel Self-Supervised Tracking framework named \\textbf{{\\tracker}}, designed to eliminate the need of box annotations. Specifically, a decoupled spatio-temporal consistency training framework is proposed to learn rich target information across timestamps through global spatial localization and local temporal association. This allows for the simula"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21606","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/2507.21606/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":"2026-07-05T11:45:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kx7vUTRCZXlR2cj9d8p3vs84k9OWEqLb9S3eiCuwzefw4LiWDqf1cFcGgUYBiAqUPfqv58UBsRioEfy+5nTeBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:59:50.279864Z"},"content_sha256":"965d4038f7aac09e7e82b2eba3014c09e7e53d1101dbde3bf1b380b2a1ce24d3","schema_version":"1.0","event_id":"sha256:965d4038f7aac09e7e82b2eba3014c09e7e53d1101dbde3bf1b380b2a1ce24d3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5UZWKUUA2XH3LTRKISNMWCYMEW/bundle.json","state_url":"https://pith.science/pith/5UZWKUUA2XH3LTRKISNMWCYMEW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5UZWKUUA2XH3LTRKISNMWCYMEW/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":"2026-08-11T08:59:50Z","links":{"resolver":"https://pith.science/pith/5UZWKUUA2XH3LTRKISNMWCYMEW","bundle":"https://pith.science/pith/5UZWKUUA2XH3LTRKISNMWCYMEW/bundle.json","state":"https://pith.science/pith/5UZWKUUA2XH3LTRKISNMWCYMEW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5UZWKUUA2XH3LTRKISNMWCYMEW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5UZWKUUA2XH3LTRKISNMWCYMEW","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":"b4099cd98b39d81f05519ee5228796eef2a8d3d446bd0f6b38c8d24f9af0d680","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T09:04:03Z","title_canon_sha256":"c6d4f525f127f9ed5589acda0fcaa799d256ce00b767d70a5a8b2da9a1fbbce9"},"schema_version":"1.0","source":{"id":"2507.21606","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.21606","created_at":"2026-07-05T11:45:03Z"},{"alias_kind":"arxiv_version","alias_value":"2507.21606v1","created_at":"2026-07-05T11:45:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21606","created_at":"2026-07-05T11:45:03Z"},{"alias_kind":"pith_short_12","alias_value":"5UZWKUUA2XH3","created_at":"2026-07-05T11:45:03Z"},{"alias_kind":"pith_short_16","alias_value":"5UZWKUUA2XH3LTRK","created_at":"2026-07-05T11:45:03Z"},{"alias_kind":"pith_short_8","alias_value":"5UZWKUUA","created_at":"2026-07-05T11:45:03Z"}],"graph_snapshots":[{"event_id":"sha256:965d4038f7aac09e7e82b2eba3014c09e7e53d1101dbde3bf1b380b2a1ce24d3","target":"graph","created_at":"2026-07-05T11:45:03Z","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/2507.21606/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The success of visual tracking has been largely driven by datasets with manual box annotations. However, these box annotations require tremendous human effort, limiting the scale and diversity of existing tracking datasets. In this work, we present a novel Self-Supervised Tracking framework named \\textbf{{\\tracker}}, designed to eliminate the need of box annotations. Specifically, a decoupled spatio-temporal consistency training framework is proposed to learn rich target information across timestamps through global spatial localization and local temporal association. This allows for the simula","authors_text":"Bineng Zhong, Ning Li, Qihua Liang, Shuxiang Song, Yaozong Zheng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T09:04:03Z","title":"Decoupled Spatio-Temporal Consistency Learning for Self-Supervised Tracking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21606","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":"sha256:16d841b11eb5307a4c9ba0cf25bea2a1b9cf4679c354e88d67d8f6b08a853dfa","target":"record","created_at":"2026-07-05T11:45:03Z","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":"b4099cd98b39d81f05519ee5228796eef2a8d3d446bd0f6b38c8d24f9af0d680","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-29T09:04:03Z","title_canon_sha256":"c6d4f525f127f9ed5589acda0fcaa799d256ce00b767d70a5a8b2da9a1fbbce9"},"schema_version":"1.0","source":{"id":"2507.21606","kind":"arxiv","version":1}},"canonical_sha256":"ed33655280d5cfb5ce2a449acb0b0c25a11dae455f03c6c447b6f59ed64ba0ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed33655280d5cfb5ce2a449acb0b0c25a11dae455f03c6c447b6f59ed64ba0ac","first_computed_at":"2026-07-05T11:45:03.050057Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:45:03.050057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hNa8+hP8qRttxGUQW+FaObwZ5nnnD6D+4AW9qx0BM+TQoRBfGWN+vzFop8wkjR8RSuqMvJ9Em1gjwoIq92uXAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:45:03.050502Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.21606","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16d841b11eb5307a4c9ba0cf25bea2a1b9cf4679c354e88d67d8f6b08a853dfa","sha256:965d4038f7aac09e7e82b2eba3014c09e7e53d1101dbde3bf1b380b2a1ce24d3"],"state_sha256":"5b3ffc11312727978221a2fe3a9f9897d4ba97de1d4c94e5dcc7fc00185f9022"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lo+7xn+t6b6c94kxOVKr7z39rdGmhduEUsjCmRmuI+tadLnA+vthDEhPWF9GNtXIoL9A5XRuRcdiZjKU5kc3Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T08:59:50.285006Z","bundle_sha256":"2745f3bd94c12e236e250d09e891aaec3b54210533dba581721a4d422165a799"}}