{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3N7RFUYDXT3XZD5W56HVKBIZBA","short_pith_number":"pith:3N7RFUYD","schema_version":"1.0","canonical_sha256":"db7f12d303bcf77c8fb6ef8f550519080be15b462438fbb43ee0c3029f879aa9","source":{"kind":"arxiv","id":"2512.23273","version":2},"attestation_state":"computed","paper":{"title":"YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection","license":"","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiawen Zhu, Jinlong Peng, Jun Liu, Xu Lin, Zhenye Gan","submitted_at":"2025-12-29T07:54:49Z","abstract_excerpt":"Existing Real-Time Object Detection (RTOD) methods commonly adopt YOLO-like architectures for their favorable trade-off between accuracy and speed. However, these models rely on static dense computation that applies uniform processing to all inputs, misallocating representational capacity and computational resources such as over-allocating on trivial scenes while under-serving complex ones. This mismatch results in both computational redundancy and suboptimal detection performance. To overcome this limitation, we propose YOLO-Master, a novel YOLO-like framework that introduces instance-conditi"},"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":"2512.23273","kind":"arxiv","version":2},"metadata":{"license":"","primary_cat":"cs.CV","submitted_at":"2025-12-29T07:54:49Z","cross_cats_sorted":[],"title_canon_sha256":"979d91779e657fe289f4c6cad3dfdebeed869ec31592acd1d6b3b564235f3440","abstract_canon_sha256":"bc72230d324d2fc906374a4a8e4dac9889f1b4d82e873cb4cdbd4a6484e80404"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T08:42:23.818144Z","signature_b64":"YlHN4b5k2GjuhdGTU1ULALzwbHS52qXEtyTl4hvrbr32DaD4e/KdDcB6LygvcG7VCf547GVEspKqct2H+xKSDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db7f12d303bcf77c8fb6ef8f550519080be15b462438fbb43ee0c3029f879aa9","last_reissued_at":"2026-07-02T08:42:23.817672Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T08:42:23.817672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection","license":"","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiawen Zhu, Jinlong Peng, Jun Liu, Xu Lin, Zhenye Gan","submitted_at":"2025-12-29T07:54:49Z","abstract_excerpt":"Existing Real-Time Object Detection (RTOD) methods commonly adopt YOLO-like architectures for their favorable trade-off between accuracy and speed. However, these models rely on static dense computation that applies uniform processing to all inputs, misallocating representational capacity and computational resources such as over-allocating on trivial scenes while under-serving complex ones. This mismatch results in both computational redundancy and suboptimal detection performance. To overcome this limitation, we propose YOLO-Master, a novel YOLO-like framework that introduces instance-conditi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.23273","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/2512.23273/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":"2512.23273","created_at":"2026-07-02T08:42:23.817728+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.23273v2","created_at":"2026-07-02T08:42:23.817728+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.23273","created_at":"2026-07-02T08:42:23.817728+00:00"},{"alias_kind":"pith_short_12","alias_value":"3N7RFUYDXT3X","created_at":"2026-07-02T08:42:23.817728+00:00"},{"alias_kind":"pith_short_16","alias_value":"3N7RFUYDXT3XZD5W","created_at":"2026-07-02T08:42:23.817728+00:00"},{"alias_kind":"pith_short_8","alias_value":"3N7RFUYD","created_at":"2026-07-02T08:42:23.817728+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.04127","citing_title":"SARES-DEIM: Sparse Mixture-of-Experts Meets DETR for Robust SAR Ship Detection","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3N7RFUYDXT3XZD5W56HVKBIZBA","json":"https://pith.science/pith/3N7RFUYDXT3XZD5W56HVKBIZBA.json","graph_json":"https://pith.science/api/pith-number/3N7RFUYDXT3XZD5W56HVKBIZBA/graph.json","events_json":"https://pith.science/api/pith-number/3N7RFUYDXT3XZD5W56HVKBIZBA/events.json","paper":"https://pith.science/paper/3N7RFUYD"},"agent_actions":{"view_html":"https://pith.science/pith/3N7RFUYDXT3XZD5W56HVKBIZBA","download_json":"https://pith.science/pith/3N7RFUYDXT3XZD5W56HVKBIZBA.json","view_paper":"https://pith.science/paper/3N7RFUYD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.23273&json=true","fetch_graph":"https://pith.science/api/pith-number/3N7RFUYDXT3XZD5W56HVKBIZBA/graph.json","fetch_events":"https://pith.science/api/pith-number/3N7RFUYDXT3XZD5W56HVKBIZBA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3N7RFUYDXT3XZD5W56HVKBIZBA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3N7RFUYDXT3XZD5W56HVKBIZBA/action/storage_attestation","attest_author":"https://pith.science/pith/3N7RFUYDXT3XZD5W56HVKBIZBA/action/author_attestation","sign_citation":"https://pith.science/pith/3N7RFUYDXT3XZD5W56HVKBIZBA/action/citation_signature","submit_replication":"https://pith.science/pith/3N7RFUYDXT3XZD5W56HVKBIZBA/action/replication_record"}},"created_at":"2026-07-02T08:42:23.817728+00:00","updated_at":"2026-07-02T08:42:23.817728+00:00"}