{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GBDGXBZTQIXZW4PVKOSFA6VRBL","short_pith_number":"pith:GBDGXBZT","schema_version":"1.0","canonical_sha256":"30466b8733822f9b71f553a4507ab10add0c4d1bc43f4533ccff6c49609f2fc8","source":{"kind":"arxiv","id":"2404.03518","version":1},"attestation_state":"computed","paper":{"title":"SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jun Wang, Ke Fan, Lizhuang Ma, Peixian Chen, Ran Yi, Ruixin Zhang, Shouhong Ding, Sichen Chen, Siming Huang, Yingyi Zhang","submitted_at":"2024-04-04T15:23:14Z","abstract_excerpt":"Recently, transformer-based methods have achieved state-of-the-art prediction quality on human pose estimation(HPE). Nonetheless, most of these top-performing transformer-based models are too computation-consuming and storage-demanding to deploy on edge computing platforms. Those transformer-based models that require fewer resources are prone to under-fitting due to their smaller scale and thus perform notably worse than their larger counterparts. Given this conundrum, we introduce SDPose, a new self-distillation method for improving the performance of small transformer-based models. To mitiga"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2404.03518","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-04T15:23:14Z","cross_cats_sorted":[],"title_canon_sha256":"167f1de7cfd3c0d8b6b6e70f2c04fb06af2a13a5aa3a204ddbd78b4645f4dee9","abstract_canon_sha256":"d8053be49866675c4b3843c72e07355b88a8bc9411dd8e49ff329b24a21fc4c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:26.921091Z","signature_b64":"a7cK39j+1cna1wIIkf4SRYNBZifU/T9foqDze0YuqrFJawS5ADLXKokmauwOTro7mT6XcmGzK11SPzWA51c4BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30466b8733822f9b71f553a4507ab10add0c4d1bc43f4533ccff6c49609f2fc8","last_reissued_at":"2026-07-05T08:04:26.920747Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:26.920747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SDPose: Tokenized Pose Estimation via Circulation-Guide Self-Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jun Wang, Ke Fan, Lizhuang Ma, Peixian Chen, Ran Yi, Ruixin Zhang, Shouhong Ding, Sichen Chen, Siming Huang, Yingyi Zhang","submitted_at":"2024-04-04T15:23:14Z","abstract_excerpt":"Recently, transformer-based methods have achieved state-of-the-art prediction quality on human pose estimation(HPE). Nonetheless, most of these top-performing transformer-based models are too computation-consuming and storage-demanding to deploy on edge computing platforms. Those transformer-based models that require fewer resources are prone to under-fitting due to their smaller scale and thus perform notably worse than their larger counterparts. Given this conundrum, we introduce SDPose, a new self-distillation method for improving the performance of small transformer-based models. To mitiga"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03518","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/2404.03518/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2404.03518","created_at":"2026-07-05T08:04:26.920805+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.03518v1","created_at":"2026-07-05T08:04:26.920805+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03518","created_at":"2026-07-05T08:04:26.920805+00:00"},{"alias_kind":"pith_short_12","alias_value":"GBDGXBZTQIXZ","created_at":"2026-07-05T08:04:26.920805+00:00"},{"alias_kind":"pith_short_16","alias_value":"GBDGXBZTQIXZW4PV","created_at":"2026-07-05T08:04:26.920805+00:00"},{"alias_kind":"pith_short_8","alias_value":"GBDGXBZT","created_at":"2026-07-05T08:04:26.920805+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.11212","citing_title":"A Coarse-to-Fine Human Pose Estimation Method based on Two-stage Distillation and Progressive Graph Neural Network","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GBDGXBZTQIXZW4PVKOSFA6VRBL","json":"https://pith.science/pith/GBDGXBZTQIXZW4PVKOSFA6VRBL.json","graph_json":"https://pith.science/api/pith-number/GBDGXBZTQIXZW4PVKOSFA6VRBL/graph.json","events_json":"https://pith.science/api/pith-number/GBDGXBZTQIXZW4PVKOSFA6VRBL/events.json","paper":"https://pith.science/paper/GBDGXBZT"},"agent_actions":{"view_html":"https://pith.science/pith/GBDGXBZTQIXZW4PVKOSFA6VRBL","download_json":"https://pith.science/pith/GBDGXBZTQIXZW4PVKOSFA6VRBL.json","view_paper":"https://pith.science/paper/GBDGXBZT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.03518&json=true","fetch_graph":"https://pith.science/api/pith-number/GBDGXBZTQIXZW4PVKOSFA6VRBL/graph.json","fetch_events":"https://pith.science/api/pith-number/GBDGXBZTQIXZW4PVKOSFA6VRBL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GBDGXBZTQIXZW4PVKOSFA6VRBL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GBDGXBZTQIXZW4PVKOSFA6VRBL/action/storage_attestation","attest_author":"https://pith.science/pith/GBDGXBZTQIXZW4PVKOSFA6VRBL/action/author_attestation","sign_citation":"https://pith.science/pith/GBDGXBZTQIXZW4PVKOSFA6VRBL/action/citation_signature","submit_replication":"https://pith.science/pith/GBDGXBZTQIXZW4PVKOSFA6VRBL/action/replication_record"}},"created_at":"2026-07-05T08:04:26.920805+00:00","updated_at":"2026-07-05T08:04:26.920805+00:00"}