{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TLKD7UN6L5AZZDTIBYBIPFZ6WL","short_pith_number":"pith:TLKD7UN6","canonical_record":{"source":{"id":"2507.00049","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T22:35:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"55c827288e3817883c075effe6bfa7898700e2aea3ea0deaa103b964200571c3","abstract_canon_sha256":"3268c42061342e5c68626e0517bbe8714c033b40451cb646973a475c1aa7cb1c"},"schema_version":"1.0"},"canonical_sha256":"9ad43fd1be5f419c8e680e0287973eb2daccc818b367c385450cc39d6111f426","source":{"kind":"arxiv","id":"2507.00049","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00049","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00049v1","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00049","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_12","alias_value":"TLKD7UN6L5AZ","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_16","alias_value":"TLKD7UN6L5AZZDTI","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_8","alias_value":"TLKD7UN6","created_at":"2026-07-05T11:29:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TLKD7UN6L5AZZDTIBYBIPFZ6WL","target":"record","payload":{"canonical_record":{"source":{"id":"2507.00049","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T22:35:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"55c827288e3817883c075effe6bfa7898700e2aea3ea0deaa103b964200571c3","abstract_canon_sha256":"3268c42061342e5c68626e0517bbe8714c033b40451cb646973a475c1aa7cb1c"},"schema_version":"1.0"},"canonical_sha256":"9ad43fd1be5f419c8e680e0287973eb2daccc818b367c385450cc39d6111f426","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:35.790504Z","signature_b64":"mzXjQzaxHHQbvQynBNR3TF6ajPQpLvq6NhD02v+4LOj2sD804H22M5A3bosKEUgtMcCNYlKdOCkHep+oOiyEBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ad43fd1be5f419c8e680e0287973eb2daccc818b367c385450cc39d6111f426","last_reissued_at":"2026-07-05T11:29:35.789842Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:35.789842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.00049","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":"2026-07-05T11:29:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LWbk0diOVsv/qs/nfXlDYLFjA7IXRUarkxE0OxOXuQ3g52swiAmUd+olnulNmAHx/yV3QQ639ktHhsiKpJ/1Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:19:59.780833Z"},"content_sha256":"5a00c127d8dc127226f2acd7f02f92d76c584f54d7f91e982618ed2f4d479e65","schema_version":"1.0","event_id":"sha256:5a00c127d8dc127226f2acd7f02f92d76c584f54d7f91e982618ed2f4d479e65"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TLKD7UN6L5AZZDTIBYBIPFZ6WL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AdaDeDup: Adaptive Hybrid Data Pruning for Efficient Large-Scale Object Detection Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Feiyang Kang, Jose M. Alvarez, Marc T. Law, Maying Shen, Nadine Chang, Rafid Mahmood, Ruoxi Jia","submitted_at":"2025-06-24T22:35:51Z","abstract_excerpt":"The computational burden and inherent redundancy of large-scale datasets challenge the training of contemporary machine learning models. Data pruning offers a solution by selecting smaller, informative subsets, yet existing methods struggle: density-based approaches can be task-agnostic, while model-based techniques may introduce redundancy or prove computationally prohibitive. We introduce Adaptive De-Duplication (AdaDeDup), a novel hybrid framework that synergistically integrates density-based pruning with model-informed feedback in a cluster-adaptive manner. AdaDeDup first partitions data a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00049","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/2507.00049/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":"2026-07-05T11:29:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qlpG7BvN6f9udTE+Sv0//anY0dWaPiUdXHlnVfe02QNGvn4C0Mb44mr2XtkRHZFYWPbTeNZIfLnBmyYNa0o8Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T11:19:59.781403Z"},"content_sha256":"421f1bc84ccca3d99a4eac3a74a8be52d2371f0106fad3f4ce41678ffa7a717c","schema_version":"1.0","event_id":"sha256:421f1bc84ccca3d99a4eac3a74a8be52d2371f0106fad3f4ce41678ffa7a717c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TLKD7UN6L5AZZDTIBYBIPFZ6WL/bundle.json","state_url":"https://pith.science/pith/TLKD7UN6L5AZZDTIBYBIPFZ6WL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TLKD7UN6L5AZZDTIBYBIPFZ6WL/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":"2026-08-04T11:19:59Z","links":{"resolver":"https://pith.science/pith/TLKD7UN6L5AZZDTIBYBIPFZ6WL","bundle":"https://pith.science/pith/TLKD7UN6L5AZZDTIBYBIPFZ6WL/bundle.json","state":"https://pith.science/pith/TLKD7UN6L5AZZDTIBYBIPFZ6WL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TLKD7UN6L5AZZDTIBYBIPFZ6WL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TLKD7UN6L5AZZDTIBYBIPFZ6WL","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":"3268c42061342e5c68626e0517bbe8714c033b40451cb646973a475c1aa7cb1c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T22:35:51Z","title_canon_sha256":"55c827288e3817883c075effe6bfa7898700e2aea3ea0deaa103b964200571c3"},"schema_version":"1.0","source":{"id":"2507.00049","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00049","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00049v1","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00049","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_12","alias_value":"TLKD7UN6L5AZ","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_16","alias_value":"TLKD7UN6L5AZZDTI","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_8","alias_value":"TLKD7UN6","created_at":"2026-07-05T11:29:35Z"}],"graph_snapshots":[{"event_id":"sha256:421f1bc84ccca3d99a4eac3a74a8be52d2371f0106fad3f4ce41678ffa7a717c","target":"graph","created_at":"2026-07-05T11:29:35Z","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/2507.00049/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The computational burden and inherent redundancy of large-scale datasets challenge the training of contemporary machine learning models. Data pruning offers a solution by selecting smaller, informative subsets, yet existing methods struggle: density-based approaches can be task-agnostic, while model-based techniques may introduce redundancy or prove computationally prohibitive. We introduce Adaptive De-Duplication (AdaDeDup), a novel hybrid framework that synergistically integrates density-based pruning with model-informed feedback in a cluster-adaptive manner. AdaDeDup first partitions data a","authors_text":"Feiyang Kang, Jose M. Alvarez, Marc T. Law, Maying Shen, Nadine Chang, Rafid Mahmood, Ruoxi Jia","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T22:35:51Z","title":"AdaDeDup: Adaptive Hybrid Data Pruning for Efficient Large-Scale Object Detection Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00049","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":"sha256:5a00c127d8dc127226f2acd7f02f92d76c584f54d7f91e982618ed2f4d479e65","target":"record","created_at":"2026-07-05T11:29:35Z","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":"3268c42061342e5c68626e0517bbe8714c033b40451cb646973a475c1aa7cb1c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-24T22:35:51Z","title_canon_sha256":"55c827288e3817883c075effe6bfa7898700e2aea3ea0deaa103b964200571c3"},"schema_version":"1.0","source":{"id":"2507.00049","kind":"arxiv","version":1}},"canonical_sha256":"9ad43fd1be5f419c8e680e0287973eb2daccc818b367c385450cc39d6111f426","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ad43fd1be5f419c8e680e0287973eb2daccc818b367c385450cc39d6111f426","first_computed_at":"2026-07-05T11:29:35.789842Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:35.789842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mzXjQzaxHHQbvQynBNR3TF6ajPQpLvq6NhD02v+4LOj2sD804H22M5A3bosKEUgtMcCNYlKdOCkHep+oOiyEBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:35.790504Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.00049","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a00c127d8dc127226f2acd7f02f92d76c584f54d7f91e982618ed2f4d479e65","sha256:421f1bc84ccca3d99a4eac3a74a8be52d2371f0106fad3f4ce41678ffa7a717c"],"state_sha256":"143f92907a74e5003a9b53c9a364eb7a33b890714db243435178884778491594"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rd97eIDRPB3PxtHzY0wNgdjjqe4gcSIcof2v+gB6h62a5Fr97wNCt3XIIlPWJQkkbgPdgjyc9bA56Jo44RcDCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T11:19:59.816110Z","bundle_sha256":"c20fbf0cf6492ef0d3fb7452d31f2913d0af923279c70be8bba80f1257c63a6d"}}