{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6L5SWJD4MHOPJPT67DVEZVZ7X2","short_pith_number":"pith:6L5SWJD4","canonical_record":{"source":{"id":"2310.10102","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2023-10-16T06:19:29Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"0b4c19c29fd00a2597be47d7c145835295e0404fbacd8fd309834698622ba10d","abstract_canon_sha256":"c910be54d34a18f36f9187df3a5c5af6f7c8e8c12f97a7bac4213192346487df"},"schema_version":"1.0"},"canonical_sha256":"f2fb2b247c61dcf4be7ef8ea4cd73fbe88e60da9cc20e488c94273fbf2b14231","source":{"kind":"arxiv","id":"2310.10102","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.10102","created_at":"2026-07-05T07:01:15Z"},{"alias_kind":"arxiv_version","alias_value":"2310.10102v1","created_at":"2026-07-05T07:01:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10102","created_at":"2026-07-05T07:01:15Z"},{"alias_kind":"pith_short_12","alias_value":"6L5SWJD4MHOP","created_at":"2026-07-05T07:01:15Z"},{"alias_kind":"pith_short_16","alias_value":"6L5SWJD4MHOPJPT6","created_at":"2026-07-05T07:01:15Z"},{"alias_kind":"pith_short_8","alias_value":"6L5SWJD4","created_at":"2026-07-05T07:01:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6L5SWJD4MHOPJPT67DVEZVZ7X2","target":"record","payload":{"canonical_record":{"source":{"id":"2310.10102","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2023-10-16T06:19:29Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"0b4c19c29fd00a2597be47d7c145835295e0404fbacd8fd309834698622ba10d","abstract_canon_sha256":"c910be54d34a18f36f9187df3a5c5af6f7c8e8c12f97a7bac4213192346487df"},"schema_version":"1.0"},"canonical_sha256":"f2fb2b247c61dcf4be7ef8ea4cd73fbe88e60da9cc20e488c94273fbf2b14231","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:01:15.328793Z","signature_b64":"U2QzWmdr7tI850B5k2SOGz2uTjts58Btjb4Yx1t+LLMTw1icQika3BeUdrGjIXgKMKoQ2aOVWUedgzQTZ/R/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2fb2b247c61dcf4be7ef8ea4cd73fbe88e60da9cc20e488c94273fbf2b14231","last_reissued_at":"2026-07-05T07:01:15.328305Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:01:15.328305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.10102","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":"2026-07-05T07:01:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R+XIUj1K5DxKTkK9gji6RUZG7SAA9Agu/scILWIMsskQQuFfNgJVIYyT8mAiulSTHFZAKb4F9KX3Ol8RRxK4AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T01:59:44.392637Z"},"content_sha256":"0f4883575b682094218c44b043c6ae4ac08e1f0a40b3777f32b129dda175e49a","schema_version":"1.0","event_id":"sha256:0f4883575b682094218c44b043c6ae4ac08e1f0a40b3777f32b129dda175e49a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6L5SWJD4MHOPJPT67DVEZVZ7X2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"KAKURENBO: Adaptively Hiding Samples in Deep Neural Network Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.DC","authors_text":"Balazs Gerofi, Edgar Josafat Martinez-Noriega, Fran\\c{c}ois Trahay, Mohamed Wahib, Truong Thao Nguyen","submitted_at":"2023-10-16T06:19:29Z","abstract_excerpt":"This paper proposes a method for hiding the least-important samples during the training of deep neural networks to increase efficiency, i.e., to reduce the cost of training. Using information about the loss and prediction confidence during training, we adaptively find samples to exclude in a given epoch based on their contribution to the overall learning process, without significantly degrading accuracy. We explore the converge properties when accounting for the reduction in the number of SGD updates. Empirical results on various large-scale datasets and models used directly in image classific"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10102","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/2310.10102/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":"2026-07-05T07:01:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f1SAsppkjkwuxoWYOdxa/HEZr51O2Zov0XeDaZhu6w3VqhhNzcHj0a03JjqrJlnOELNM+Z/zO02RSYzIg3FICA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T01:59:44.393339Z"},"content_sha256":"67b9dd6841a5748a82368e71f6915ef717fe6e3646516375caf3cd5937a7bf08","schema_version":"1.0","event_id":"sha256:67b9dd6841a5748a82368e71f6915ef717fe6e3646516375caf3cd5937a7bf08"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6L5SWJD4MHOPJPT67DVEZVZ7X2/bundle.json","state_url":"https://pith.science/pith/6L5SWJD4MHOPJPT67DVEZVZ7X2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6L5SWJD4MHOPJPT67DVEZVZ7X2/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":"2026-07-07T01:59:44Z","links":{"resolver":"https://pith.science/pith/6L5SWJD4MHOPJPT67DVEZVZ7X2","bundle":"https://pith.science/pith/6L5SWJD4MHOPJPT67DVEZVZ7X2/bundle.json","state":"https://pith.science/pith/6L5SWJD4MHOPJPT67DVEZVZ7X2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6L5SWJD4MHOPJPT67DVEZVZ7X2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6L5SWJD4MHOPJPT67DVEZVZ7X2","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":"c910be54d34a18f36f9187df3a5c5af6f7c8e8c12f97a7bac4213192346487df","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2023-10-16T06:19:29Z","title_canon_sha256":"0b4c19c29fd00a2597be47d7c145835295e0404fbacd8fd309834698622ba10d"},"schema_version":"1.0","source":{"id":"2310.10102","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.10102","created_at":"2026-07-05T07:01:15Z"},{"alias_kind":"arxiv_version","alias_value":"2310.10102v1","created_at":"2026-07-05T07:01:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10102","created_at":"2026-07-05T07:01:15Z"},{"alias_kind":"pith_short_12","alias_value":"6L5SWJD4MHOP","created_at":"2026-07-05T07:01:15Z"},{"alias_kind":"pith_short_16","alias_value":"6L5SWJD4MHOPJPT6","created_at":"2026-07-05T07:01:15Z"},{"alias_kind":"pith_short_8","alias_value":"6L5SWJD4","created_at":"2026-07-05T07:01:15Z"}],"graph_snapshots":[{"event_id":"sha256:67b9dd6841a5748a82368e71f6915ef717fe6e3646516375caf3cd5937a7bf08","target":"graph","created_at":"2026-07-05T07:01:15Z","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/2310.10102/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper proposes a method for hiding the least-important samples during the training of deep neural networks to increase efficiency, i.e., to reduce the cost of training. Using information about the loss and prediction confidence during training, we adaptively find samples to exclude in a given epoch based on their contribution to the overall learning process, without significantly degrading accuracy. We explore the converge properties when accounting for the reduction in the number of SGD updates. Empirical results on various large-scale datasets and models used directly in image classific","authors_text":"Balazs Gerofi, Edgar Josafat Martinez-Noriega, Fran\\c{c}ois Trahay, Mohamed Wahib, Truong Thao Nguyen","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2023-10-16T06:19:29Z","title":"KAKURENBO: Adaptively Hiding Samples in Deep Neural Network Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10102","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":"sha256:0f4883575b682094218c44b043c6ae4ac08e1f0a40b3777f32b129dda175e49a","target":"record","created_at":"2026-07-05T07:01:15Z","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":"c910be54d34a18f36f9187df3a5c5af6f7c8e8c12f97a7bac4213192346487df","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2023-10-16T06:19:29Z","title_canon_sha256":"0b4c19c29fd00a2597be47d7c145835295e0404fbacd8fd309834698622ba10d"},"schema_version":"1.0","source":{"id":"2310.10102","kind":"arxiv","version":1}},"canonical_sha256":"f2fb2b247c61dcf4be7ef8ea4cd73fbe88e60da9cc20e488c94273fbf2b14231","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2fb2b247c61dcf4be7ef8ea4cd73fbe88e60da9cc20e488c94273fbf2b14231","first_computed_at":"2026-07-05T07:01:15.328305Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:01:15.328305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U2QzWmdr7tI850B5k2SOGz2uTjts58Btjb4Yx1t+LLMTw1icQika3BeUdrGjIXgKMKoQ2aOVWUedgzQTZ/R/Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:01:15.328793Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.10102","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f4883575b682094218c44b043c6ae4ac08e1f0a40b3777f32b129dda175e49a","sha256:67b9dd6841a5748a82368e71f6915ef717fe6e3646516375caf3cd5937a7bf08"],"state_sha256":"39c8cb1ca88206d82f5c083d17fc284ce94b808aa9653207589e1099f59c88cd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T4sc8YOnqZgxToX791s+GJKlBAjPVe6njP5MWG9kycdfS+wgZ/8LfLSZfuft4NzHfqKFvEWQGoio8uyXFTmxDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T01:59:44.397035Z","bundle_sha256":"147cafe7792a19e5d964e17e6b6950077c8b4158f24c4307ec4f2b26d8ae4fa1"}}