{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:EPP4LLBFT6RGO4DI7OMD63QD34","short_pith_number":"pith:EPP4LLBF","canonical_record":{"source":{"id":"2109.04660","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-10T04:41:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c433a8107d709c9df10faeabd1a1106e8f6c2842275b08773f3c16af4f1ff751","abstract_canon_sha256":"8a69d406912ee4e2458ea0959d024f6e7d6813684cf400f5d40d37af44b6e5b8"},"schema_version":"1.0"},"canonical_sha256":"23dfc5ac259fa2677068fb983f6e03df1df23f1346361c56ba2b8ceac663d605","source":{"kind":"arxiv","id":"2109.04660","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.04660","created_at":"2026-07-05T06:36:09Z"},{"alias_kind":"arxiv_version","alias_value":"2109.04660v2","created_at":"2026-07-05T06:36:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.04660","created_at":"2026-07-05T06:36:09Z"},{"alias_kind":"pith_short_12","alias_value":"EPP4LLBFT6RG","created_at":"2026-07-05T06:36:09Z"},{"alias_kind":"pith_short_16","alias_value":"EPP4LLBFT6RGO4DI","created_at":"2026-07-05T06:36:09Z"},{"alias_kind":"pith_short_8","alias_value":"EPP4LLBF","created_at":"2026-07-05T06:36:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:EPP4LLBFT6RGO4DI7OMD63QD34","target":"record","payload":{"canonical_record":{"source":{"id":"2109.04660","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-10T04:41:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c433a8107d709c9df10faeabd1a1106e8f6c2842275b08773f3c16af4f1ff751","abstract_canon_sha256":"8a69d406912ee4e2458ea0959d024f6e7d6813684cf400f5d40d37af44b6e5b8"},"schema_version":"1.0"},"canonical_sha256":"23dfc5ac259fa2677068fb983f6e03df1df23f1346361c56ba2b8ceac663d605","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:36:09.963703Z","signature_b64":"AGeQWHOVdywSI+AdBVvEAv6t2T7HRo0HmVWv1noA/mQWoEYQksiEywDYfmjDVdd+HX37NjF28VYcAEklYOqNBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23dfc5ac259fa2677068fb983f6e03df1df23f1346361c56ba2b8ceac663d605","last_reissued_at":"2026-07-05T06:36:09.963273Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:36:09.963273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.04660","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":"2026-07-05T06:36:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"muRGMlkax4w7Vcri6ZCFjgFYpFogI/qppFzcQuYMYhsr5JbytbqUDusaeFJNZ/xOgQEo+njhzSDDDCCnqbAJAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:40:53.057018Z"},"content_sha256":"fad09ebcdebb455447b7a4d0e4ba93c4a54ad325d1d649a6284141dea73bcee3","schema_version":"1.0","event_id":"sha256:fad09ebcdebb455447b7a4d0e4ba93c4a54ad325d1d649a6284141dea73bcee3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:EPP4LLBFT6RGO4DI7OMD63QD34","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamic Collective Intelligence Learning: Finding Efficient Sparse Model via Refined Gradients for Pruned Weights","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jangho Kim, Jayeon Yoo, KiYoon Yoo, Nojun Kwak, Yeji Song","submitted_at":"2021-09-10T04:41:17Z","abstract_excerpt":"With the growth of deep neural networks (DNN), the number of DNN parameters has drastically increased. This makes DNN models hard to be deployed on resource-limited embedded systems. To alleviate this problem, dynamic pruning methods have emerged, which try to find diverse sparsity patterns during training by utilizing Straight-Through-Estimator (STE) to approximate gradients of pruned weights. STE can help the pruned weights revive in the process of finding dynamic sparsity patterns. However, using these coarse gradients causes training instability and performance degradation owing to the unr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.04660","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/2109.04660/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":"2026-07-05T06:36:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OiU6OBKXw0NML28+QRFhNB747B4kDw0jHp8n4wXyMbgmnWZILyxwlLiK3U8n6WFADaY5/vVv1plrgF0mrbXZDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:40:53.057522Z"},"content_sha256":"4b2eac082ac99e9ffd2864dcc9888566c1e723ec9d289938577024a059614b89","schema_version":"1.0","event_id":"sha256:4b2eac082ac99e9ffd2864dcc9888566c1e723ec9d289938577024a059614b89"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EPP4LLBFT6RGO4DI7OMD63QD34/bundle.json","state_url":"https://pith.science/pith/EPP4LLBFT6RGO4DI7OMD63QD34/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EPP4LLBFT6RGO4DI7OMD63QD34/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":"2026-08-10T06:40:53Z","links":{"resolver":"https://pith.science/pith/EPP4LLBFT6RGO4DI7OMD63QD34","bundle":"https://pith.science/pith/EPP4LLBFT6RGO4DI7OMD63QD34/bundle.json","state":"https://pith.science/pith/EPP4LLBFT6RGO4DI7OMD63QD34/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EPP4LLBFT6RGO4DI7OMD63QD34/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:EPP4LLBFT6RGO4DI7OMD63QD34","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":"8a69d406912ee4e2458ea0959d024f6e7d6813684cf400f5d40d37af44b6e5b8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-10T04:41:17Z","title_canon_sha256":"c433a8107d709c9df10faeabd1a1106e8f6c2842275b08773f3c16af4f1ff751"},"schema_version":"1.0","source":{"id":"2109.04660","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.04660","created_at":"2026-07-05T06:36:09Z"},{"alias_kind":"arxiv_version","alias_value":"2109.04660v2","created_at":"2026-07-05T06:36:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.04660","created_at":"2026-07-05T06:36:09Z"},{"alias_kind":"pith_short_12","alias_value":"EPP4LLBFT6RG","created_at":"2026-07-05T06:36:09Z"},{"alias_kind":"pith_short_16","alias_value":"EPP4LLBFT6RGO4DI","created_at":"2026-07-05T06:36:09Z"},{"alias_kind":"pith_short_8","alias_value":"EPP4LLBF","created_at":"2026-07-05T06:36:09Z"}],"graph_snapshots":[{"event_id":"sha256:4b2eac082ac99e9ffd2864dcc9888566c1e723ec9d289938577024a059614b89","target":"graph","created_at":"2026-07-05T06:36:09Z","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/2109.04660/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the growth of deep neural networks (DNN), the number of DNN parameters has drastically increased. This makes DNN models hard to be deployed on resource-limited embedded systems. To alleviate this problem, dynamic pruning methods have emerged, which try to find diverse sparsity patterns during training by utilizing Straight-Through-Estimator (STE) to approximate gradients of pruned weights. STE can help the pruned weights revive in the process of finding dynamic sparsity patterns. However, using these coarse gradients causes training instability and performance degradation owing to the unr","authors_text":"Jangho Kim, Jayeon Yoo, KiYoon Yoo, Nojun Kwak, Yeji Song","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-10T04:41:17Z","title":"Dynamic Collective Intelligence Learning: Finding Efficient Sparse Model via Refined Gradients for Pruned Weights"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.04660","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:fad09ebcdebb455447b7a4d0e4ba93c4a54ad325d1d649a6284141dea73bcee3","target":"record","created_at":"2026-07-05T06:36:09Z","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":"8a69d406912ee4e2458ea0959d024f6e7d6813684cf400f5d40d37af44b6e5b8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-10T04:41:17Z","title_canon_sha256":"c433a8107d709c9df10faeabd1a1106e8f6c2842275b08773f3c16af4f1ff751"},"schema_version":"1.0","source":{"id":"2109.04660","kind":"arxiv","version":2}},"canonical_sha256":"23dfc5ac259fa2677068fb983f6e03df1df23f1346361c56ba2b8ceac663d605","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23dfc5ac259fa2677068fb983f6e03df1df23f1346361c56ba2b8ceac663d605","first_computed_at":"2026-07-05T06:36:09.963273Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:36:09.963273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AGeQWHOVdywSI+AdBVvEAv6t2T7HRo0HmVWv1noA/mQWoEYQksiEywDYfmjDVdd+HX37NjF28VYcAEklYOqNBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:36:09.963703Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.04660","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fad09ebcdebb455447b7a4d0e4ba93c4a54ad325d1d649a6284141dea73bcee3","sha256:4b2eac082ac99e9ffd2864dcc9888566c1e723ec9d289938577024a059614b89"],"state_sha256":"8ba5a1155173101b49cd34e7ab158fd10c4273fddee597da95a2aa0f9d2a7f6c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O+HgSI2EyeEpYlVnBx3n5nH/cA4xzb8y5D+f9WqYqe1FoFVZVSZZGuA/TY0BRH94P+RO0Rq0PVcuAGWtkebXBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T06:40:53.061362Z","bundle_sha256":"e58d9f9e1b55f15600d8f7e07a37a15350a280f39adb03a3e6b4f38d1503c863"}}