{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PVK43AEAWPEHNPYM2MXIQI2ERR","short_pith_number":"pith:PVK43AEA","schema_version":"1.0","canonical_sha256":"7d55cd8080b3c876bf0cd32e8823448c7d88a4180e41c70e3286b6c1ad766ee2","source":{"kind":"arxiv","id":"2303.05015","version":2},"attestation_state":"computed","paper":{"title":"Smooth and Stepwise Self-Distillation for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Derek Aguiar, Hao Tian, Jieren Deng, Xin Zhou, Zhihong Pan","submitted_at":"2023-03-09T03:33:56Z","abstract_excerpt":"Distilling the structured information captured in feature maps has contributed to improved results for object detection tasks, but requires careful selection of baseline architectures and substantial pre-training. Self-distillation addresses these limitations and has recently achieved state-of-the-art performance for object detection despite making several simplifying architectural assumptions. Building on this work, we propose Smooth and Stepwise Self-Distillation (SSSD) for object detection. Our SSSD architecture forms an implicit teacher from object labels and a feature pyramid network back"},"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":"2303.05015","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-09T03:33:56Z","cross_cats_sorted":[],"title_canon_sha256":"63ba76e75327b80a0f3c4515491614e344dd95942526c6d55286e4a5836582b7","abstract_canon_sha256":"af566f50a2623e8d8c7f77dc18abd61af4adf56f7cc1f413a6b06149aac46f55"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:18.287205Z","signature_b64":"xBagMEC32249C2fTCjHmRoOc5oFQ/Qp3NNZPwM2xNg5XrkRSXFBY5LeIyWLxwbo9Bg+3/CFoWqdye+KYJ2biDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d55cd8080b3c876bf0cd32e8823448c7d88a4180e41c70e3286b6c1ad766ee2","last_reissued_at":"2026-07-05T07:35:18.286660Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:18.286660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Smooth and Stepwise Self-Distillation for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Derek Aguiar, Hao Tian, Jieren Deng, Xin Zhou, Zhihong Pan","submitted_at":"2023-03-09T03:33:56Z","abstract_excerpt":"Distilling the structured information captured in feature maps has contributed to improved results for object detection tasks, but requires careful selection of baseline architectures and substantial pre-training. Self-distillation addresses these limitations and has recently achieved state-of-the-art performance for object detection despite making several simplifying architectural assumptions. Building on this work, we propose Smooth and Stepwise Self-Distillation (SSSD) for object detection. Our SSSD architecture forms an implicit teacher from object labels and a feature pyramid network back"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.05015","kind":"arxiv","version":2},"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/2303.05015/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":"2303.05015","created_at":"2026-07-05T07:35:18.286734+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.05015v2","created_at":"2026-07-05T07:35:18.286734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.05015","created_at":"2026-07-05T07:35:18.286734+00:00"},{"alias_kind":"pith_short_12","alias_value":"PVK43AEAWPEH","created_at":"2026-07-05T07:35:18.286734+00:00"},{"alias_kind":"pith_short_16","alias_value":"PVK43AEAWPEHNPYM","created_at":"2026-07-05T07:35:18.286734+00:00"},{"alias_kind":"pith_short_8","alias_value":"PVK43AEA","created_at":"2026-07-05T07:35:18.286734+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.08339","citing_title":"SHeRL-FL: When Representation Learning Meets Split Learning in Hierarchical Federated Learning","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PVK43AEAWPEHNPYM2MXIQI2ERR","json":"https://pith.science/pith/PVK43AEAWPEHNPYM2MXIQI2ERR.json","graph_json":"https://pith.science/api/pith-number/PVK43AEAWPEHNPYM2MXIQI2ERR/graph.json","events_json":"https://pith.science/api/pith-number/PVK43AEAWPEHNPYM2MXIQI2ERR/events.json","paper":"https://pith.science/paper/PVK43AEA"},"agent_actions":{"view_html":"https://pith.science/pith/PVK43AEAWPEHNPYM2MXIQI2ERR","download_json":"https://pith.science/pith/PVK43AEAWPEHNPYM2MXIQI2ERR.json","view_paper":"https://pith.science/paper/PVK43AEA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.05015&json=true","fetch_graph":"https://pith.science/api/pith-number/PVK43AEAWPEHNPYM2MXIQI2ERR/graph.json","fetch_events":"https://pith.science/api/pith-number/PVK43AEAWPEHNPYM2MXIQI2ERR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PVK43AEAWPEHNPYM2MXIQI2ERR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PVK43AEAWPEHNPYM2MXIQI2ERR/action/storage_attestation","attest_author":"https://pith.science/pith/PVK43AEAWPEHNPYM2MXIQI2ERR/action/author_attestation","sign_citation":"https://pith.science/pith/PVK43AEAWPEHNPYM2MXIQI2ERR/action/citation_signature","submit_replication":"https://pith.science/pith/PVK43AEAWPEHNPYM2MXIQI2ERR/action/replication_record"}},"created_at":"2026-07-05T07:35:18.286734+00:00","updated_at":"2026-07-05T07:35:18.286734+00:00"}