{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:BKJDLOJG4OQNO4N7CWOJGJ2MGL","short_pith_number":"pith:BKJDLOJG","canonical_record":{"source":{"id":"2005.07683","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-15T17:54:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c7af006da9dd9b9914940a98450fa41d519f6b6c9f233bd21fde8e74c7a34bda","abstract_canon_sha256":"d1cdda3490c5e8d01c1327cab14833e1fda78f7977ab18417fca0a7ac7e1289f"},"schema_version":"1.0"},"canonical_sha256":"0a9235b926e3a0d771bf159c93274c32e07a3a1c7b3bbe5fef25388f171608d7","source":{"kind":"arxiv","id":"2005.07683","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.07683","created_at":"2026-07-05T01:45:26Z"},{"alias_kind":"arxiv_version","alias_value":"2005.07683v2","created_at":"2026-07-05T01:45:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.07683","created_at":"2026-07-05T01:45:26Z"},{"alias_kind":"pith_short_12","alias_value":"BKJDLOJG4OQN","created_at":"2026-07-05T01:45:26Z"},{"alias_kind":"pith_short_16","alias_value":"BKJDLOJG4OQNO4N7","created_at":"2026-07-05T01:45:26Z"},{"alias_kind":"pith_short_8","alias_value":"BKJDLOJG","created_at":"2026-07-05T01:45:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:BKJDLOJG4OQNO4N7CWOJGJ2MGL","target":"record","payload":{"canonical_record":{"source":{"id":"2005.07683","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-15T17:54:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c7af006da9dd9b9914940a98450fa41d519f6b6c9f233bd21fde8e74c7a34bda","abstract_canon_sha256":"d1cdda3490c5e8d01c1327cab14833e1fda78f7977ab18417fca0a7ac7e1289f"},"schema_version":"1.0"},"canonical_sha256":"0a9235b926e3a0d771bf159c93274c32e07a3a1c7b3bbe5fef25388f171608d7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:26.952568Z","signature_b64":"EKkYkKdpzJ7SYm/xOtOD4H6mJEvgBmhMlSIH3MqIUStUORDhxAUKtCzeji3U/M+EJD8fhIwTTWSFaNiZAgiYCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a9235b926e3a0d771bf159c93274c32e07a3a1c7b3bbe5fef25388f171608d7","last_reissued_at":"2026-07-05T01:45:26.952153Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:26.952153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.07683","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":"2026-07-05T01:45:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tEutoDn3vREePyeY2kbU+BVRHxK0qu67VAV0v1oh27Y9LVlUNI4YUaZ08/4/iir4L1A3FBd73Afr3fD5MUovAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:31:50.654993Z"},"content_sha256":"596ec50db1751a02dc51a09c7d62d392cca8cb9c5f55100d62d8594c11f123e4","schema_version":"1.0","event_id":"sha256:596ec50db1751a02dc51a09c7d62d392cca8cb9c5f55100d62d8594c11f123e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:BKJDLOJG4OQNO4N7CWOJGJ2MGL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Movement Pruning: Adaptive Sparsity by Fine-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alexander M. Rush, Thomas Wolf, Victor Sanh","submitted_at":"2020-05-15T17:54:15Z","abstract_excerpt":"Magnitude pruning is a widely used strategy for reducing model size in pure supervised learning; however, it is less effective in the transfer learning regime that has become standard for state-of-the-art natural language processing applications. We propose the use of movement pruning, a simple, deterministic first-order weight pruning method that is more adaptive to pretrained model fine-tuning. We give mathematical foundations to the method and compare it to existing zeroth- and first-order pruning methods. Experiments show that when pruning large pretrained language models, movement pruning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.07683","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/2005.07683/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":"2026-07-05T01:45:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GvIb5mNgkwOqDHXNLSufdEQACe+V53U4hoJH+XVzli3sCYtk9lkefo40/bLVdkGAcT9fMYhFrhauXnEws4ogCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T06:31:50.656342Z"},"content_sha256":"cbe654ce9275f842da66d1f2e46c9c0806f9441d578ca4833038ba0626497bb8","schema_version":"1.0","event_id":"sha256:cbe654ce9275f842da66d1f2e46c9c0806f9441d578ca4833038ba0626497bb8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BKJDLOJG4OQNO4N7CWOJGJ2MGL/bundle.json","state_url":"https://pith.science/pith/BKJDLOJG4OQNO4N7CWOJGJ2MGL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BKJDLOJG4OQNO4N7CWOJGJ2MGL/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":"2026-08-10T06:31:50Z","links":{"resolver":"https://pith.science/pith/BKJDLOJG4OQNO4N7CWOJGJ2MGL","bundle":"https://pith.science/pith/BKJDLOJG4OQNO4N7CWOJGJ2MGL/bundle.json","state":"https://pith.science/pith/BKJDLOJG4OQNO4N7CWOJGJ2MGL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BKJDLOJG4OQNO4N7CWOJGJ2MGL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:BKJDLOJG4OQNO4N7CWOJGJ2MGL","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":"d1cdda3490c5e8d01c1327cab14833e1fda78f7977ab18417fca0a7ac7e1289f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-15T17:54:15Z","title_canon_sha256":"c7af006da9dd9b9914940a98450fa41d519f6b6c9f233bd21fde8e74c7a34bda"},"schema_version":"1.0","source":{"id":"2005.07683","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.07683","created_at":"2026-07-05T01:45:26Z"},{"alias_kind":"arxiv_version","alias_value":"2005.07683v2","created_at":"2026-07-05T01:45:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.07683","created_at":"2026-07-05T01:45:26Z"},{"alias_kind":"pith_short_12","alias_value":"BKJDLOJG4OQN","created_at":"2026-07-05T01:45:26Z"},{"alias_kind":"pith_short_16","alias_value":"BKJDLOJG4OQNO4N7","created_at":"2026-07-05T01:45:26Z"},{"alias_kind":"pith_short_8","alias_value":"BKJDLOJG","created_at":"2026-07-05T01:45:26Z"}],"graph_snapshots":[{"event_id":"sha256:cbe654ce9275f842da66d1f2e46c9c0806f9441d578ca4833038ba0626497bb8","target":"graph","created_at":"2026-07-05T01:45:26Z","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/2005.07683/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Magnitude pruning is a widely used strategy for reducing model size in pure supervised learning; however, it is less effective in the transfer learning regime that has become standard for state-of-the-art natural language processing applications. We propose the use of movement pruning, a simple, deterministic first-order weight pruning method that is more adaptive to pretrained model fine-tuning. We give mathematical foundations to the method and compare it to existing zeroth- and first-order pruning methods. Experiments show that when pruning large pretrained language models, movement pruning","authors_text":"Alexander M. Rush, Thomas Wolf, Victor Sanh","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-15T17:54:15Z","title":"Movement Pruning: Adaptive Sparsity by Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.07683","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":"sha256:596ec50db1751a02dc51a09c7d62d392cca8cb9c5f55100d62d8594c11f123e4","target":"record","created_at":"2026-07-05T01:45:26Z","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":"d1cdda3490c5e8d01c1327cab14833e1fda78f7977ab18417fca0a7ac7e1289f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-15T17:54:15Z","title_canon_sha256":"c7af006da9dd9b9914940a98450fa41d519f6b6c9f233bd21fde8e74c7a34bda"},"schema_version":"1.0","source":{"id":"2005.07683","kind":"arxiv","version":2}},"canonical_sha256":"0a9235b926e3a0d771bf159c93274c32e07a3a1c7b3bbe5fef25388f171608d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a9235b926e3a0d771bf159c93274c32e07a3a1c7b3bbe5fef25388f171608d7","first_computed_at":"2026-07-05T01:45:26.952153Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:45:26.952153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EKkYkKdpzJ7SYm/xOtOD4H6mJEvgBmhMlSIH3MqIUStUORDhxAUKtCzeji3U/M+EJD8fhIwTTWSFaNiZAgiYCA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:45:26.952568Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.07683","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:596ec50db1751a02dc51a09c7d62d392cca8cb9c5f55100d62d8594c11f123e4","sha256:cbe654ce9275f842da66d1f2e46c9c0806f9441d578ca4833038ba0626497bb8"],"state_sha256":"6cb44776f5b40e882cec0eb4c5819d8e1dd4c4fabf4e10df90e3ec072b616e22"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GvWDXSgEhc9U4SoJWrerpmTvWbkTGxflfuGeOFJ1mNggou7cDhXqJEj4hD1E2BXNewm0YL/dfI5zUSBio8g/BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T06:31:50.672432Z","bundle_sha256":"0d73e695277d0403fac124454ac7dac4e2e9ea6d3c5340624cdc9aaad189a538"}}