{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:MSVRDPTHH47R4RXXOBUJNAHDZX","short_pith_number":"pith:MSVRDPTH","canonical_record":{"source":{"id":"2103.17154","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-31T15:19:19Z","cross_cats_sorted":[],"title_canon_sha256":"2b36fb9a35c9b000e542262adde846793c61a431ec97059a132bb2a9565a41b1","abstract_canon_sha256":"f6818f21349a0307eb77221cae6ac0d71f7f2e1b5d564ec7b26f1b5ea8fba284"},"schema_version":"1.0"},"canonical_sha256":"64ab11be673f3f1e46f770689680e3cdea4a71627d5b9995bafa6510da0e9930","source":{"kind":"arxiv","id":"2103.17154","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.17154","created_at":"2026-07-05T02:28:13Z"},{"alias_kind":"arxiv_version","alias_value":"2103.17154v1","created_at":"2026-07-05T02:28:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.17154","created_at":"2026-07-05T02:28:13Z"},{"alias_kind":"pith_short_12","alias_value":"MSVRDPTHH47R","created_at":"2026-07-05T02:28:13Z"},{"alias_kind":"pith_short_16","alias_value":"MSVRDPTHH47R4RXX","created_at":"2026-07-05T02:28:13Z"},{"alias_kind":"pith_short_8","alias_value":"MSVRDPTH","created_at":"2026-07-05T02:28:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:MSVRDPTHH47R4RXXOBUJNAHDZX","target":"record","payload":{"canonical_record":{"source":{"id":"2103.17154","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-31T15:19:19Z","cross_cats_sorted":[],"title_canon_sha256":"2b36fb9a35c9b000e542262adde846793c61a431ec97059a132bb2a9565a41b1","abstract_canon_sha256":"f6818f21349a0307eb77221cae6ac0d71f7f2e1b5d564ec7b26f1b5ea8fba284"},"schema_version":"1.0"},"canonical_sha256":"64ab11be673f3f1e46f770689680e3cdea4a71627d5b9995bafa6510da0e9930","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:28:13.367380Z","signature_b64":"QthSxH4TSbYXcflnuIhVHNkwD0H/YEl5mBqPVg57yKoNNI03ZZ9QpfN+haSwN5vtxZ4Xj+BF4E/swHBckeIqBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64ab11be673f3f1e46f770689680e3cdea4a71627d5b9995bafa6510da0e9930","last_reissued_at":"2026-07-05T02:28:13.367001Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:28:13.367001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.17154","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":"2026-07-05T02:28:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VHGRo8dRlwY9cgKPn1HanLYITJEL6pmtA2GGpraD+6k2V7yYEoEKnLln8HZR9n/1tQxkHtxOht9bmf4MmzTVBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:50:04.623556Z"},"content_sha256":"aa52799e93e440eda929a64b24840788dc3d0c2a5e0eeee391b6e6c84134fa55","schema_version":"1.0","event_id":"sha256:aa52799e93e440eda929a64b24840788dc3d0c2a5e0eeee391b6e6c84134fa55"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:MSVRDPTHH47R4RXXOBUJNAHDZX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Spatio-Temporal Transformer for Visual Tracking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Yan, Dong Wang, Houwen Peng, Huchuan Lu, Jianlong Fu","submitted_at":"2021-03-31T15:19:19Z","abstract_excerpt":"In this paper, we present a new tracking architecture with an encoder-decoder transformer as the key component. The encoder models the global spatio-temporal feature dependencies between target objects and search regions, while the decoder learns a query embedding to predict the spatial positions of the target objects. Our method casts object tracking as a direct bounding box prediction problem, without using any proposals or predefined anchors. With the encoder-decoder transformer, the prediction of objects just uses a simple fully-convolutional network, which estimates the corners of objects"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.17154","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/2103.17154/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":"2026-07-05T02:28:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cTA7NyR4enYftWP8LQ9Yq8ImUZaI1PcV80ZLKPFh2flgeqruxvi/r3dDmBVRFqBFKXm+7hcRXma61kF0CZmjCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:50:04.624073Z"},"content_sha256":"baf1651551e42854c09a171793eb45f296fd76e216e7e024ca9175e207e2ec3c","schema_version":"1.0","event_id":"sha256:baf1651551e42854c09a171793eb45f296fd76e216e7e024ca9175e207e2ec3c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MSVRDPTHH47R4RXXOBUJNAHDZX/bundle.json","state_url":"https://pith.science/pith/MSVRDPTHH47R4RXXOBUJNAHDZX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MSVRDPTHH47R4RXXOBUJNAHDZX/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":"2026-08-04T20:50:04Z","links":{"resolver":"https://pith.science/pith/MSVRDPTHH47R4RXXOBUJNAHDZX","bundle":"https://pith.science/pith/MSVRDPTHH47R4RXXOBUJNAHDZX/bundle.json","state":"https://pith.science/pith/MSVRDPTHH47R4RXXOBUJNAHDZX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MSVRDPTHH47R4RXXOBUJNAHDZX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MSVRDPTHH47R4RXXOBUJNAHDZX","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":"f6818f21349a0307eb77221cae6ac0d71f7f2e1b5d564ec7b26f1b5ea8fba284","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-31T15:19:19Z","title_canon_sha256":"2b36fb9a35c9b000e542262adde846793c61a431ec97059a132bb2a9565a41b1"},"schema_version":"1.0","source":{"id":"2103.17154","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.17154","created_at":"2026-07-05T02:28:13Z"},{"alias_kind":"arxiv_version","alias_value":"2103.17154v1","created_at":"2026-07-05T02:28:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.17154","created_at":"2026-07-05T02:28:13Z"},{"alias_kind":"pith_short_12","alias_value":"MSVRDPTHH47R","created_at":"2026-07-05T02:28:13Z"},{"alias_kind":"pith_short_16","alias_value":"MSVRDPTHH47R4RXX","created_at":"2026-07-05T02:28:13Z"},{"alias_kind":"pith_short_8","alias_value":"MSVRDPTH","created_at":"2026-07-05T02:28:13Z"}],"graph_snapshots":[{"event_id":"sha256:baf1651551e42854c09a171793eb45f296fd76e216e7e024ca9175e207e2ec3c","target":"graph","created_at":"2026-07-05T02:28:13Z","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/2103.17154/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present a new tracking architecture with an encoder-decoder transformer as the key component. The encoder models the global spatio-temporal feature dependencies between target objects and search regions, while the decoder learns a query embedding to predict the spatial positions of the target objects. Our method casts object tracking as a direct bounding box prediction problem, without using any proposals or predefined anchors. With the encoder-decoder transformer, the prediction of objects just uses a simple fully-convolutional network, which estimates the corners of objects","authors_text":"Bin Yan, Dong Wang, Houwen Peng, Huchuan Lu, Jianlong Fu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-31T15:19:19Z","title":"Learning Spatio-Temporal Transformer for Visual Tracking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.17154","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:aa52799e93e440eda929a64b24840788dc3d0c2a5e0eeee391b6e6c84134fa55","target":"record","created_at":"2026-07-05T02:28:13Z","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":"f6818f21349a0307eb77221cae6ac0d71f7f2e1b5d564ec7b26f1b5ea8fba284","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-31T15:19:19Z","title_canon_sha256":"2b36fb9a35c9b000e542262adde846793c61a431ec97059a132bb2a9565a41b1"},"schema_version":"1.0","source":{"id":"2103.17154","kind":"arxiv","version":1}},"canonical_sha256":"64ab11be673f3f1e46f770689680e3cdea4a71627d5b9995bafa6510da0e9930","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"64ab11be673f3f1e46f770689680e3cdea4a71627d5b9995bafa6510da0e9930","first_computed_at":"2026-07-05T02:28:13.367001Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:28:13.367001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QthSxH4TSbYXcflnuIhVHNkwD0H/YEl5mBqPVg57yKoNNI03ZZ9QpfN+haSwN5vtxZ4Xj+BF4E/swHBckeIqBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:28:13.367380Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.17154","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa52799e93e440eda929a64b24840788dc3d0c2a5e0eeee391b6e6c84134fa55","sha256:baf1651551e42854c09a171793eb45f296fd76e216e7e024ca9175e207e2ec3c"],"state_sha256":"8dd0c91923e110c343ef048a0f9b99fd72ecfcfcd8fabb1176d25a897f8e1cea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UuA3e/WQyp903QtXAUY8qWE6FB1JNI344HwVYMOtwJdXC31cLyYPeBQg5/ezXTVqCJfGK8O2jwYDwopqVo7TBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T20:50:04.628618Z","bundle_sha256":"fbde511b423fb8e29e9f4b5f99580390e6b1bbe2b4e989f0cb0a96ad8d9d6c01"}}