{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:BLVLC3M6WFFLT6FLW52ZV3AHXC","short_pith_number":"pith:BLVLC3M6","canonical_record":{"source":{"id":"1904.03626","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-07T11:36:35Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"15147258978389a5f95951357af474baa4eceaa7fecc0741edd64163175e1a3c","abstract_canon_sha256":"a21b6393fac53ba01887d626cf16108160c0b4852c0c4a77e7310e92edd48288"},"schema_version":"1.0"},"canonical_sha256":"0aeab16d9eb14ab9f8abb7759aec07b8b059bc83a1283764b12f7989a0bf2767","source":{"kind":"arxiv","id":"1904.03626","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.03626","created_at":"2026-07-05T01:56:27Z"},{"alias_kind":"arxiv_version","alias_value":"1904.03626v3","created_at":"2026-07-05T01:56:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03626","created_at":"2026-07-05T01:56:27Z"},{"alias_kind":"pith_short_12","alias_value":"BLVLC3M6WFFL","created_at":"2026-07-05T01:56:27Z"},{"alias_kind":"pith_short_16","alias_value":"BLVLC3M6WFFLT6FL","created_at":"2026-07-05T01:56:27Z"},{"alias_kind":"pith_short_8","alias_value":"BLVLC3M6","created_at":"2026-07-05T01:56:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:BLVLC3M6WFFLT6FLW52ZV3AHXC","target":"record","payload":{"canonical_record":{"source":{"id":"1904.03626","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-07T11:36:35Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"15147258978389a5f95951357af474baa4eceaa7fecc0741edd64163175e1a3c","abstract_canon_sha256":"a21b6393fac53ba01887d626cf16108160c0b4852c0c4a77e7310e92edd48288"},"schema_version":"1.0"},"canonical_sha256":"0aeab16d9eb14ab9f8abb7759aec07b8b059bc83a1283764b12f7989a0bf2767","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:56:27.820405Z","signature_b64":"EZIbA2b9wIdt7gy1gZUrNQAV/7JnQgZSkuAXaYidFZ4PavkSbugeflUWMjwSWH4ieGRP1EO29uE8E5vIroyIBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0aeab16d9eb14ab9f8abb7759aec07b8b059bc83a1283764b12f7989a0bf2767","last_reissued_at":"2026-07-05T01:56:27.819966Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:56:27.819966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.03626","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:56:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4xeOY0Rog7wkx9dw8dxh7Al+w9ySeHZrizIh/lU0NNDi337paif5rQUyvdr9oW54qtwckYSRUBsxUQNVQgZ1Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:27:52.844407Z"},"content_sha256":"4d438af86d1bec0c2c1af0a25deca079f0379814bed30690c0b744f9235beaf6","schema_version":"1.0","event_id":"sha256:4d438af86d1bec0c2c1af0a25deca079f0379814bed30690c0b744f9235beaf6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:BLVLC3M6WFFLT6FLW52ZV3AHXC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On The Power of Curriculum Learning in Training Deep Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Daphna Weinshall, Guy Hacohen","submitted_at":"2019-04-07T11:36:35Z","abstract_excerpt":"Training neural networks is traditionally done by providing a sequence of random mini-batches sampled uniformly from the entire training data. In this work, we analyze the effect of curriculum learning, which involves the non-uniform sampling of mini-batches, on the training of deep networks, and specifically CNNs trained for image recognition. To employ curriculum learning, the training algorithm must resolve 2 problems: (i) sort the training examples by difficulty; (ii) compute a series of mini-batches that exhibit an increasing level of difficulty. We address challenge (i) using two methods"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03626","kind":"arxiv","version":3},"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/1904.03626/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":"2026-07-05T01:56:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"grQiKpIH4iGlE24MIw362aynFC4mXi2CEXOY+OEK7VjBXZZar8UkY6r9LiQi2GM8hALZc+HsZ5ArLOh0Irt1DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:27:52.844948Z"},"content_sha256":"a818a8cd9ceee2082ce4610c027f2665671d54f18f6c6d91ad63478917d60a1e","schema_version":"1.0","event_id":"sha256:a818a8cd9ceee2082ce4610c027f2665671d54f18f6c6d91ad63478917d60a1e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BLVLC3M6WFFLT6FLW52ZV3AHXC/bundle.json","state_url":"https://pith.science/pith/BLVLC3M6WFFLT6FLW52ZV3AHXC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BLVLC3M6WFFLT6FLW52ZV3AHXC/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":"2026-08-10T09:27:52Z","links":{"resolver":"https://pith.science/pith/BLVLC3M6WFFLT6FLW52ZV3AHXC","bundle":"https://pith.science/pith/BLVLC3M6WFFLT6FLW52ZV3AHXC/bundle.json","state":"https://pith.science/pith/BLVLC3M6WFFLT6FLW52ZV3AHXC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BLVLC3M6WFFLT6FLW52ZV3AHXC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:BLVLC3M6WFFLT6FLW52ZV3AHXC","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":"a21b6393fac53ba01887d626cf16108160c0b4852c0c4a77e7310e92edd48288","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-07T11:36:35Z","title_canon_sha256":"15147258978389a5f95951357af474baa4eceaa7fecc0741edd64163175e1a3c"},"schema_version":"1.0","source":{"id":"1904.03626","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.03626","created_at":"2026-07-05T01:56:27Z"},{"alias_kind":"arxiv_version","alias_value":"1904.03626v3","created_at":"2026-07-05T01:56:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03626","created_at":"2026-07-05T01:56:27Z"},{"alias_kind":"pith_short_12","alias_value":"BLVLC3M6WFFL","created_at":"2026-07-05T01:56:27Z"},{"alias_kind":"pith_short_16","alias_value":"BLVLC3M6WFFLT6FL","created_at":"2026-07-05T01:56:27Z"},{"alias_kind":"pith_short_8","alias_value":"BLVLC3M6","created_at":"2026-07-05T01:56:27Z"}],"graph_snapshots":[{"event_id":"sha256:a818a8cd9ceee2082ce4610c027f2665671d54f18f6c6d91ad63478917d60a1e","target":"graph","created_at":"2026-07-05T01:56:27Z","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/1904.03626/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training neural networks is traditionally done by providing a sequence of random mini-batches sampled uniformly from the entire training data. In this work, we analyze the effect of curriculum learning, which involves the non-uniform sampling of mini-batches, on the training of deep networks, and specifically CNNs trained for image recognition. To employ curriculum learning, the training algorithm must resolve 2 problems: (i) sort the training examples by difficulty; (ii) compute a series of mini-batches that exhibit an increasing level of difficulty. We address challenge (i) using two methods","authors_text":"Daphna Weinshall, Guy Hacohen","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-07T11:36:35Z","title":"On The Power of Curriculum Learning in Training Deep Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03626","kind":"arxiv","version":3},"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":"sha256:4d438af86d1bec0c2c1af0a25deca079f0379814bed30690c0b744f9235beaf6","target":"record","created_at":"2026-07-05T01:56:27Z","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":"a21b6393fac53ba01887d626cf16108160c0b4852c0c4a77e7310e92edd48288","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-07T11:36:35Z","title_canon_sha256":"15147258978389a5f95951357af474baa4eceaa7fecc0741edd64163175e1a3c"},"schema_version":"1.0","source":{"id":"1904.03626","kind":"arxiv","version":3}},"canonical_sha256":"0aeab16d9eb14ab9f8abb7759aec07b8b059bc83a1283764b12f7989a0bf2767","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0aeab16d9eb14ab9f8abb7759aec07b8b059bc83a1283764b12f7989a0bf2767","first_computed_at":"2026-07-05T01:56:27.819966Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:56:27.819966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EZIbA2b9wIdt7gy1gZUrNQAV/7JnQgZSkuAXaYidFZ4PavkSbugeflUWMjwSWH4ieGRP1EO29uE8E5vIroyIBA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:56:27.820405Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.03626","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4d438af86d1bec0c2c1af0a25deca079f0379814bed30690c0b744f9235beaf6","sha256:a818a8cd9ceee2082ce4610c027f2665671d54f18f6c6d91ad63478917d60a1e"],"state_sha256":"5f802d8f3e8753d22db3d7435c6a681380cf0e9421035b808ba2d7dac797dc3a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IrpLIwC/cp4MOD2PZ3MEwxgAbtTVXyAaNpjUNlmszAiLVmbEVLFyEIV3vCVq9ozHJ+OB89IvW+MY7I0b68hhDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T09:27:52.851228Z","bundle_sha256":"0c2dc1a95edda5133732d9b2b90d9410f042bd53669bfacff960a9c7b80963ef"}}