{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:Q3COCSAI2UY3PWJKNJ2R7NEBE2","short_pith_number":"pith:Q3COCSAI","canonical_record":{"source":{"id":"2006.12279","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-22T14:08:51Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"554d74a76ddcd57cd5981f379c5af3f8617896b54de2fa861d29117206b8f3e5","abstract_canon_sha256":"03595ece8ca0497a15aa08ecd45c442eccedcaf3bfd58770c8080b91cba9d977"},"schema_version":"1.0"},"canonical_sha256":"86c4e14808d531b7d92a6a751fb48126b6e075a6b57963c58c05b72bc6e9f558","source":{"kind":"arxiv","id":"2006.12279","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.12279","created_at":"2026-07-05T01:11:59Z"},{"alias_kind":"arxiv_version","alias_value":"2006.12279v1","created_at":"2026-07-05T01:11:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.12279","created_at":"2026-07-05T01:11:59Z"},{"alias_kind":"pith_short_12","alias_value":"Q3COCSAI2UY3","created_at":"2026-07-05T01:11:59Z"},{"alias_kind":"pith_short_16","alias_value":"Q3COCSAI2UY3PWJK","created_at":"2026-07-05T01:11:59Z"},{"alias_kind":"pith_short_8","alias_value":"Q3COCSAI","created_at":"2026-07-05T01:11:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:Q3COCSAI2UY3PWJKNJ2R7NEBE2","target":"record","payload":{"canonical_record":{"source":{"id":"2006.12279","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-22T14:08:51Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"554d74a76ddcd57cd5981f379c5af3f8617896b54de2fa861d29117206b8f3e5","abstract_canon_sha256":"03595ece8ca0497a15aa08ecd45c442eccedcaf3bfd58770c8080b91cba9d977"},"schema_version":"1.0"},"canonical_sha256":"86c4e14808d531b7d92a6a751fb48126b6e075a6b57963c58c05b72bc6e9f558","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:11:59.123060Z","signature_b64":"xGYjCXiirHjezDGlWX1+28hsvXBtiMaTij/vRCsJZUgdX4J11g7ECFCqt2blY1VS4nPDJLP8wR1d5k15DLjKDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86c4e14808d531b7d92a6a751fb48126b6e075a6b57963c58c05b72bc6e9f558","last_reissued_at":"2026-07-05T01:11:59.122553Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:11:59.122553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.12279","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":"2026-07-05T01:11:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yW95FbtoiG0cgQ0ut2ejRuN3nOeYqK89rbhSpQn58L39ger2c6ajGsOrItO6OxVIkzbueTpZm89uTeCrZFV5Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T21:14:15.846773Z"},"content_sha256":"85dfca2ffd10e96d87bc7627f139941d2e028f007c559ee5900cbd151a738b96","schema_version":"1.0","event_id":"sha256:85dfca2ffd10e96d87bc7627f139941d2e028f007c559ee5900cbd151a738b96"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:Q3COCSAI2UY3PWJKNJ2R7NEBE2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Revisiting Loss Modelling for Unstructured Pruning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Camille Ballas, C\\'esar Laurent, Nicolas Ballas, Pascal Vincent, Thomas George","submitted_at":"2020-06-22T14:08:51Z","abstract_excerpt":"By removing parameters from deep neural networks, unstructured pruning methods aim at cutting down memory footprint and computational cost, while maintaining prediction accuracy. In order to tackle this otherwise intractable problem, many of these methods model the loss landscape using first or second order Taylor expansions to identify which parameters can be discarded. We revisit loss modelling for unstructured pruning: we show the importance of ensuring locality of the pruning steps. We systematically compare first and second order Taylor expansions and empirically show that both can reach "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.12279","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/2006.12279/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":"2026-07-05T01:11:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lFlzaCxA+gjT638ifug7rxLi7qDjsbiO2ZSNvI162yUpaj/TVzTZD0z2+1qK0MD1m3M6GajtuEWVt74kuWu/BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T21:14:15.847263Z"},"content_sha256":"aa3c705c176ce0d2f4f4499d360663fc7f3cef6d89f58c9c62b34b6e33a26701","schema_version":"1.0","event_id":"sha256:aa3c705c176ce0d2f4f4499d360663fc7f3cef6d89f58c9c62b34b6e33a26701"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q3COCSAI2UY3PWJKNJ2R7NEBE2/bundle.json","state_url":"https://pith.science/pith/Q3COCSAI2UY3PWJKNJ2R7NEBE2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q3COCSAI2UY3PWJKNJ2R7NEBE2/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":"2026-08-05T21:14:15Z","links":{"resolver":"https://pith.science/pith/Q3COCSAI2UY3PWJKNJ2R7NEBE2","bundle":"https://pith.science/pith/Q3COCSAI2UY3PWJKNJ2R7NEBE2/bundle.json","state":"https://pith.science/pith/Q3COCSAI2UY3PWJKNJ2R7NEBE2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q3COCSAI2UY3PWJKNJ2R7NEBE2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:Q3COCSAI2UY3PWJKNJ2R7NEBE2","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":"03595ece8ca0497a15aa08ecd45c442eccedcaf3bfd58770c8080b91cba9d977","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-22T14:08:51Z","title_canon_sha256":"554d74a76ddcd57cd5981f379c5af3f8617896b54de2fa861d29117206b8f3e5"},"schema_version":"1.0","source":{"id":"2006.12279","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.12279","created_at":"2026-07-05T01:11:59Z"},{"alias_kind":"arxiv_version","alias_value":"2006.12279v1","created_at":"2026-07-05T01:11:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.12279","created_at":"2026-07-05T01:11:59Z"},{"alias_kind":"pith_short_12","alias_value":"Q3COCSAI2UY3","created_at":"2026-07-05T01:11:59Z"},{"alias_kind":"pith_short_16","alias_value":"Q3COCSAI2UY3PWJK","created_at":"2026-07-05T01:11:59Z"},{"alias_kind":"pith_short_8","alias_value":"Q3COCSAI","created_at":"2026-07-05T01:11:59Z"}],"graph_snapshots":[{"event_id":"sha256:aa3c705c176ce0d2f4f4499d360663fc7f3cef6d89f58c9c62b34b6e33a26701","target":"graph","created_at":"2026-07-05T01:11:59Z","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/2006.12279/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"By removing parameters from deep neural networks, unstructured pruning methods aim at cutting down memory footprint and computational cost, while maintaining prediction accuracy. In order to tackle this otherwise intractable problem, many of these methods model the loss landscape using first or second order Taylor expansions to identify which parameters can be discarded. We revisit loss modelling for unstructured pruning: we show the importance of ensuring locality of the pruning steps. We systematically compare first and second order Taylor expansions and empirically show that both can reach ","authors_text":"Camille Ballas, C\\'esar Laurent, Nicolas Ballas, Pascal Vincent, Thomas George","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-22T14:08:51Z","title":"Revisiting Loss Modelling for Unstructured Pruning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.12279","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":"sha256:85dfca2ffd10e96d87bc7627f139941d2e028f007c559ee5900cbd151a738b96","target":"record","created_at":"2026-07-05T01:11:59Z","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":"03595ece8ca0497a15aa08ecd45c442eccedcaf3bfd58770c8080b91cba9d977","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-22T14:08:51Z","title_canon_sha256":"554d74a76ddcd57cd5981f379c5af3f8617896b54de2fa861d29117206b8f3e5"},"schema_version":"1.0","source":{"id":"2006.12279","kind":"arxiv","version":1}},"canonical_sha256":"86c4e14808d531b7d92a6a751fb48126b6e075a6b57963c58c05b72bc6e9f558","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86c4e14808d531b7d92a6a751fb48126b6e075a6b57963c58c05b72bc6e9f558","first_computed_at":"2026-07-05T01:11:59.122553Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:11:59.122553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xGYjCXiirHjezDGlWX1+28hsvXBtiMaTij/vRCsJZUgdX4J11g7ECFCqt2blY1VS4nPDJLP8wR1d5k15DLjKDA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:11:59.123060Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.12279","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85dfca2ffd10e96d87bc7627f139941d2e028f007c559ee5900cbd151a738b96","sha256:aa3c705c176ce0d2f4f4499d360663fc7f3cef6d89f58c9c62b34b6e33a26701"],"state_sha256":"988d65e929747010091169142259ad6018b7e25401d0b6d378f993fba0ccfa55"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MT5EIgpa4uXXP4HqoOwNVSj3eksXsMk/xMOdayNWHEp8RYhXtBTD8fxctfIrzvleOKBYIcEcSwiO7lY53QBDCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T21:14:15.851145Z","bundle_sha256":"b73ba93738e35b4a5d5dca40b4c06792401121ccba5545b4740af750e608d424"}}