{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:L43AP57CSFMO23UEX7XVWA6NOP","short_pith_number":"pith:L43AP57C","canonical_record":{"source":{"id":"1809.04403","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-12T13:14:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8d7a9162a0135aa199544a615856b75bbe5253d8a010c08328a6a09692a1c991","abstract_canon_sha256":"c09f90a45cfbac3e80f10c311470248eea74fbc2104370dab9d8df1cf275a4ea"},"schema_version":"1.0"},"canonical_sha256":"5f3607f7e29158ed6e84bfef5b03cd73ccd6787c405c71b3dd93f4d7ec3e9b4c","source":{"kind":"arxiv","id":"1809.04403","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.04403","created_at":"2026-05-17T23:56:14Z"},{"alias_kind":"arxiv_version","alias_value":"1809.04403v2","created_at":"2026-05-17T23:56:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04403","created_at":"2026-05-17T23:56:14Z"},{"alias_kind":"pith_short_12","alias_value":"L43AP57CSFMO","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"L43AP57CSFMO23UE","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"L43AP57C","created_at":"2026-05-18T12:32:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:L43AP57CSFMO23UEX7XVWA6NOP","target":"record","payload":{"canonical_record":{"source":{"id":"1809.04403","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-12T13:14:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8d7a9162a0135aa199544a615856b75bbe5253d8a010c08328a6a09692a1c991","abstract_canon_sha256":"c09f90a45cfbac3e80f10c311470248eea74fbc2104370dab9d8df1cf275a4ea"},"schema_version":"1.0"},"canonical_sha256":"5f3607f7e29158ed6e84bfef5b03cd73ccd6787c405c71b3dd93f4d7ec3e9b4c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:14.689778Z","signature_b64":"/whU/j2nZX8iCD/PIiOCR6MUdbuG24ubzqYkMvqccmMbbxy6+l/1sXjV+Jy+pal+xQG2LZ24m/ALYL7RRtBfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f3607f7e29158ed6e84bfef5b03cd73ccd6787c405c71b3dd93f4d7ec3e9b4c","last_reissued_at":"2026-05-17T23:56:14.689133Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:14.689133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.04403","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:56:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4dz8M70IqzGBq0B7XVgD7RoAiZjXgPhWM5EKN/ylgqRPCO7hG62DLjwH8Vopqoy802sTwGNGslpklxeV6FKCCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T06:04:08.806875Z"},"content_sha256":"80d3c54910a2d0ef92512ac6e92b32a5a502c514feedbc0dd567eb4916a273d5","schema_version":"1.0","event_id":"sha256:80d3c54910a2d0ef92512ac6e92b32a5a502c514feedbc0dd567eb4916a273d5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:L43AP57CSFMO23UEX7XVWA6NOP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Label Denoising with Large Ensembles of Heterogeneous Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Elizaveta Logacheva, Gleb Sterkin, Oleg Khomenko, Pavel Ostyakov, Roman Suvorov, Sergey I. Nikolenko, Vladimir Aliev","submitted_at":"2018-09-12T13:14:59Z","abstract_excerpt":"Despite recent advances in computer vision based on various convolutional architectures, video understanding remains an important challenge. In this work, we present and discuss a top solution for the large-scale video classification (labeling) problem introduced as a Kaggle competition based on the YouTube-8M dataset. We show and compare different approaches to preprocessing, data augmentation, model architectures, and model combination. Our final model is based on a large ensemble of video- and frame-level models but fits into rather limiting hardware constraints. We apply an approach based "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04403","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":""},"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":"2026-05-17T23:56:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"98zQ5pOaB+oatxh8RePucX+cT0C51fn3K8S7aGPtFWtsQnNaXuJGPQ44gzuYoPefufVQn2oYRYFN5/wqxLjSBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-25T06:04:08.807221Z"},"content_sha256":"7822f5273d91b9882c4c509c999dc0a66ccabf1ea4f0058c1bfd6f9ca6d971df","schema_version":"1.0","event_id":"sha256:7822f5273d91b9882c4c509c999dc0a66ccabf1ea4f0058c1bfd6f9ca6d971df"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L43AP57CSFMO23UEX7XVWA6NOP/bundle.json","state_url":"https://pith.science/pith/L43AP57CSFMO23UEX7XVWA6NOP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L43AP57CSFMO23UEX7XVWA6NOP/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":"2026-06-25T06:04:08Z","links":{"resolver":"https://pith.science/pith/L43AP57CSFMO23UEX7XVWA6NOP","bundle":"https://pith.science/pith/L43AP57CSFMO23UEX7XVWA6NOP/bundle.json","state":"https://pith.science/pith/L43AP57CSFMO23UEX7XVWA6NOP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L43AP57CSFMO23UEX7XVWA6NOP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:L43AP57CSFMO23UEX7XVWA6NOP","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":"c09f90a45cfbac3e80f10c311470248eea74fbc2104370dab9d8df1cf275a4ea","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-12T13:14:59Z","title_canon_sha256":"8d7a9162a0135aa199544a615856b75bbe5253d8a010c08328a6a09692a1c991"},"schema_version":"1.0","source":{"id":"1809.04403","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.04403","created_at":"2026-05-17T23:56:14Z"},{"alias_kind":"arxiv_version","alias_value":"1809.04403v2","created_at":"2026-05-17T23:56:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04403","created_at":"2026-05-17T23:56:14Z"},{"alias_kind":"pith_short_12","alias_value":"L43AP57CSFMO","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_16","alias_value":"L43AP57CSFMO23UE","created_at":"2026-05-18T12:32:33Z"},{"alias_kind":"pith_short_8","alias_value":"L43AP57C","created_at":"2026-05-18T12:32:33Z"}],"graph_snapshots":[{"event_id":"sha256:7822f5273d91b9882c4c509c999dc0a66ccabf1ea4f0058c1bfd6f9ca6d971df","target":"graph","created_at":"2026-05-17T23:56:14Z","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"},"paper":{"abstract_excerpt":"Despite recent advances in computer vision based on various convolutional architectures, video understanding remains an important challenge. In this work, we present and discuss a top solution for the large-scale video classification (labeling) problem introduced as a Kaggle competition based on the YouTube-8M dataset. We show and compare different approaches to preprocessing, data augmentation, model architectures, and model combination. Our final model is based on a large ensemble of video- and frame-level models but fits into rather limiting hardware constraints. We apply an approach based ","authors_text":"Elizaveta Logacheva, Gleb Sterkin, Oleg Khomenko, Pavel Ostyakov, Roman Suvorov, Sergey I. Nikolenko, Vladimir Aliev","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-12T13:14:59Z","title":"Label Denoising with Large Ensembles of Heterogeneous Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04403","kind":"arxiv","version":2},"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":"sha256:80d3c54910a2d0ef92512ac6e92b32a5a502c514feedbc0dd567eb4916a273d5","target":"record","created_at":"2026-05-17T23:56:14Z","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":"c09f90a45cfbac3e80f10c311470248eea74fbc2104370dab9d8df1cf275a4ea","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-09-12T13:14:59Z","title_canon_sha256":"8d7a9162a0135aa199544a615856b75bbe5253d8a010c08328a6a09692a1c991"},"schema_version":"1.0","source":{"id":"1809.04403","kind":"arxiv","version":2}},"canonical_sha256":"5f3607f7e29158ed6e84bfef5b03cd73ccd6787c405c71b3dd93f4d7ec3e9b4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f3607f7e29158ed6e84bfef5b03cd73ccd6787c405c71b3dd93f4d7ec3e9b4c","first_computed_at":"2026-05-17T23:56:14.689133Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:56:14.689133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/whU/j2nZX8iCD/PIiOCR6MUdbuG24ubzqYkMvqccmMbbxy6+l/1sXjV+Jy+pal+xQG2LZ24m/ALYL7RRtBfDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:56:14.689778Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.04403","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80d3c54910a2d0ef92512ac6e92b32a5a502c514feedbc0dd567eb4916a273d5","sha256:7822f5273d91b9882c4c509c999dc0a66ccabf1ea4f0058c1bfd6f9ca6d971df"],"state_sha256":"d68a95f43e38f08fd6dcc1d187da33e9d8ecf45befc72e47a142fd1fbc2b3619"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j+0Mwm+YPhoJYKOaBJvVR9eJ7H8fDHDmF4Sy4QyblxL7a+JbrP0cEEWU+P9GAGpGe3ihUI4hUlTj7W5tKX11Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-25T06:04:08.809175Z","bundle_sha256":"1a7139efc0e04960cf435f86475dad3bb21441370ac96a2c603bd1c6e190ab03"}}