{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:YDXFKJBA5EZSJXWK3XL73LUKGC","short_pith_number":"pith:YDXFKJBA","canonical_record":{"source":{"id":"2205.15495","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-31T01:19:18Z","cross_cats_sorted":[],"title_canon_sha256":"9719297a30b129090079e2aca1e03012c6810878b845025d669ea05a14725dd3","abstract_canon_sha256":"df81d45c886ab581da7edc31308c2834e3d9d9d25978ce1d0001d4798f79d062"},"schema_version":"1.0"},"canonical_sha256":"c0ee552420e93324decaddd7fdae8a30a16acc8b9417b6076533aee51a875c04","source":{"kind":"arxiv","id":"2205.15495","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.15495","created_at":"2026-07-05T04:27:33Z"},{"alias_kind":"arxiv_version","alias_value":"2205.15495v1","created_at":"2026-07-05T04:27:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15495","created_at":"2026-07-05T04:27:33Z"},{"alias_kind":"pith_short_12","alias_value":"YDXFKJBA5EZS","created_at":"2026-07-05T04:27:33Z"},{"alias_kind":"pith_short_16","alias_value":"YDXFKJBA5EZSJXWK","created_at":"2026-07-05T04:27:33Z"},{"alias_kind":"pith_short_8","alias_value":"YDXFKJBA","created_at":"2026-07-05T04:27:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:YDXFKJBA5EZSJXWK3XL73LUKGC","target":"record","payload":{"canonical_record":{"source":{"id":"2205.15495","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-31T01:19:18Z","cross_cats_sorted":[],"title_canon_sha256":"9719297a30b129090079e2aca1e03012c6810878b845025d669ea05a14725dd3","abstract_canon_sha256":"df81d45c886ab581da7edc31308c2834e3d9d9d25978ce1d0001d4798f79d062"},"schema_version":"1.0"},"canonical_sha256":"c0ee552420e93324decaddd7fdae8a30a16acc8b9417b6076533aee51a875c04","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:33.428970Z","signature_b64":"doGEQ5HuaBogP+4se4I+Pw0oVADFJbdvV2R2ulKFAn2ujaroUgOwNBCVF1ZcRi1sEY8ZyBmOiv22RpPtDxNmAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0ee552420e93324decaddd7fdae8a30a16acc8b9417b6076533aee51a875c04","last_reissued_at":"2026-07-05T04:27:33.428378Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:33.428378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.15495","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":"2026-07-05T04:27:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"25seYh4Y8DqC6XALQSUyxngIdG3ZpC1iky+A24oyX+eEodkxiOGlXsR9IHDfwGI9QntUCuvusyVzGi1znrbxAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T01:10:29.790904Z"},"content_sha256":"4ac8cb134c8dbb1defcd089f15c3c6ab391e369db380c7f1f422f4daf1cda353","schema_version":"1.0","event_id":"sha256:4ac8cb134c8dbb1defcd089f15c3c6ab391e369db380c7f1f422f4daf1cda353"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:YDXFKJBA5EZSJXWK3XL73LUKGC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Joint Spatial-Temporal and Appearance Modeling with Transformer for Multiple Object Tracking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changshui Zhang, Peng Dai, Renliang Weng, Yiqiang Feng","submitted_at":"2022-05-31T01:19:18Z","abstract_excerpt":"The recent trend in multiple object tracking (MOT) is heading towards leveraging deep learning to boost the tracking performance. In this paper, we propose a novel solution named TransSTAM, which leverages Transformer to effectively model both the appearance features of each object and the spatial-temporal relationships among objects. TransSTAM consists of two major parts: (1) The encoder utilizes the powerful self-attention mechanism of Transformer to learn discriminative features for each tracklet; (2) The decoder adopts the standard cross-attention mechanism to model the affinities between "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15495","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/2205.15495/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":"2026-07-05T04:27:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+10cjd3W5ZOhJmHUXAXh7UBBj321OThuQTqe91uHR+799cg6w2CyVQHMKYNLhTBb3oK/dNpSpQuW1xFxtVccBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T01:10:29.791445Z"},"content_sha256":"367696259493b8a28cbcc52516dee7eb34497a51ca710c878423ae34da219925","schema_version":"1.0","event_id":"sha256:367696259493b8a28cbcc52516dee7eb34497a51ca710c878423ae34da219925"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YDXFKJBA5EZSJXWK3XL73LUKGC/bundle.json","state_url":"https://pith.science/pith/YDXFKJBA5EZSJXWK3XL73LUKGC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YDXFKJBA5EZSJXWK3XL73LUKGC/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":"2026-08-18T01:10:29Z","links":{"resolver":"https://pith.science/pith/YDXFKJBA5EZSJXWK3XL73LUKGC","bundle":"https://pith.science/pith/YDXFKJBA5EZSJXWK3XL73LUKGC/bundle.json","state":"https://pith.science/pith/YDXFKJBA5EZSJXWK3XL73LUKGC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YDXFKJBA5EZSJXWK3XL73LUKGC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YDXFKJBA5EZSJXWK3XL73LUKGC","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":"df81d45c886ab581da7edc31308c2834e3d9d9d25978ce1d0001d4798f79d062","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-31T01:19:18Z","title_canon_sha256":"9719297a30b129090079e2aca1e03012c6810878b845025d669ea05a14725dd3"},"schema_version":"1.0","source":{"id":"2205.15495","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.15495","created_at":"2026-07-05T04:27:33Z"},{"alias_kind":"arxiv_version","alias_value":"2205.15495v1","created_at":"2026-07-05T04:27:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15495","created_at":"2026-07-05T04:27:33Z"},{"alias_kind":"pith_short_12","alias_value":"YDXFKJBA5EZS","created_at":"2026-07-05T04:27:33Z"},{"alias_kind":"pith_short_16","alias_value":"YDXFKJBA5EZSJXWK","created_at":"2026-07-05T04:27:33Z"},{"alias_kind":"pith_short_8","alias_value":"YDXFKJBA","created_at":"2026-07-05T04:27:33Z"}],"graph_snapshots":[{"event_id":"sha256:367696259493b8a28cbcc52516dee7eb34497a51ca710c878423ae34da219925","target":"graph","created_at":"2026-07-05T04:27:33Z","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/2205.15495/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent trend in multiple object tracking (MOT) is heading towards leveraging deep learning to boost the tracking performance. In this paper, we propose a novel solution named TransSTAM, which leverages Transformer to effectively model both the appearance features of each object and the spatial-temporal relationships among objects. TransSTAM consists of two major parts: (1) The encoder utilizes the powerful self-attention mechanism of Transformer to learn discriminative features for each tracklet; (2) The decoder adopts the standard cross-attention mechanism to model the affinities between ","authors_text":"Changshui Zhang, Peng Dai, Renliang Weng, Yiqiang Feng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-31T01:19:18Z","title":"Joint Spatial-Temporal and Appearance Modeling with Transformer for Multiple Object Tracking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15495","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":"sha256:4ac8cb134c8dbb1defcd089f15c3c6ab391e369db380c7f1f422f4daf1cda353","target":"record","created_at":"2026-07-05T04:27:33Z","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":"df81d45c886ab581da7edc31308c2834e3d9d9d25978ce1d0001d4798f79d062","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-05-31T01:19:18Z","title_canon_sha256":"9719297a30b129090079e2aca1e03012c6810878b845025d669ea05a14725dd3"},"schema_version":"1.0","source":{"id":"2205.15495","kind":"arxiv","version":1}},"canonical_sha256":"c0ee552420e93324decaddd7fdae8a30a16acc8b9417b6076533aee51a875c04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0ee552420e93324decaddd7fdae8a30a16acc8b9417b6076533aee51a875c04","first_computed_at":"2026-07-05T04:27:33.428378Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:27:33.428378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"doGEQ5HuaBogP+4se4I+Pw0oVADFJbdvV2R2ulKFAn2ujaroUgOwNBCVF1ZcRi1sEY8ZyBmOiv22RpPtDxNmAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:27:33.428970Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.15495","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ac8cb134c8dbb1defcd089f15c3c6ab391e369db380c7f1f422f4daf1cda353","sha256:367696259493b8a28cbcc52516dee7eb34497a51ca710c878423ae34da219925"],"state_sha256":"02f35434bfebb58a11cfdab298f548bc3e5f742ca80431b49e6ea5f9ab202b23"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6ufB8lHjVZ162vzlYUmwZv3Muy6QahXitvO1TuZp7u2tyJn5moRyGLZH9ISwkbNEgSMxHVc68iRn5TQ0daNSAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T01:10:29.795237Z","bundle_sha256":"c56d0620164f09e613befe838dc80d7f57c4539d7faf7b04979a20c6372bd6e8"}}