{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KSUY6JYSS2LEG6CJHZRLAUX2NT","short_pith_number":"pith:KSUY6JYS","canonical_record":{"source":{"id":"2401.06898","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-12T21:32:04Z","cross_cats_sorted":[],"title_canon_sha256":"487d976a8d4f3d79c6ccc8a44e16ffb5dc55933c553469553ad559054358574d","abstract_canon_sha256":"52c3b4bdf147981b84925bc93bc29d77801b9f2373138a57800dbfd84f18509b"},"schema_version":"1.0"},"canonical_sha256":"54a98f271296964378493e62b052fa6cd2d11b86f9cce94edae77bf0ede25fa4","source":{"kind":"arxiv","id":"2401.06898","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.06898","created_at":"2026-07-05T10:56:04Z"},{"alias_kind":"arxiv_version","alias_value":"2401.06898v2","created_at":"2026-07-05T10:56:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06898","created_at":"2026-07-05T10:56:04Z"},{"alias_kind":"pith_short_12","alias_value":"KSUY6JYSS2LE","created_at":"2026-07-05T10:56:04Z"},{"alias_kind":"pith_short_16","alias_value":"KSUY6JYSS2LEG6CJ","created_at":"2026-07-05T10:56:04Z"},{"alias_kind":"pith_short_8","alias_value":"KSUY6JYS","created_at":"2026-07-05T10:56:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KSUY6JYSS2LEG6CJHZRLAUX2NT","target":"record","payload":{"canonical_record":{"source":{"id":"2401.06898","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-12T21:32:04Z","cross_cats_sorted":[],"title_canon_sha256":"487d976a8d4f3d79c6ccc8a44e16ffb5dc55933c553469553ad559054358574d","abstract_canon_sha256":"52c3b4bdf147981b84925bc93bc29d77801b9f2373138a57800dbfd84f18509b"},"schema_version":"1.0"},"canonical_sha256":"54a98f271296964378493e62b052fa6cd2d11b86f9cce94edae77bf0ede25fa4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:04.895409Z","signature_b64":"swOa0aFxVwKJd6Pydkxs8d3Jk55X6m+/H95be/SGZ8dQxzrBJDuaWlckf166Ze3sunz9qXdq3DI5lnH/YbdYCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54a98f271296964378493e62b052fa6cd2d11b86f9cce94edae77bf0ede25fa4","last_reissued_at":"2026-07-05T10:56:04.894978Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:04.894978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.06898","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":"2026-07-05T10:56:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yfq911FyFYqPXwb/OKS+mLClOEeKbO3PxY8XLzJHHJz/OQS4U/q0MtAj8TXWyPn7COBDh+fsaup/eMe2p6D2BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T12:15:49.608600Z"},"content_sha256":"3199f60ea29be703be8e8dc5b7c59f62de01d0d6b86adcc6b37c6438d0b03610","schema_version":"1.0","event_id":"sha256:3199f60ea29be703be8e8dc5b7c59f62de01d0d6b86adcc6b37c6438d0b03610"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KSUY6JYSS2LEG6CJHZRLAUX2NT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Always-Sparse Training by Growing Connections with Guided Stochastic Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexandru Nicolau, Mike Heddes, Narayan Srinivasa, Tony Givargis","submitted_at":"2024-01-12T21:32:04Z","abstract_excerpt":"The excessive computational requirements of modern artificial neural networks (ANNs) are posing limitations on the machines that can run them. Sparsification of ANNs is often motivated by time, memory and energy savings only during model inference, yielding no benefits during training. A growing body of work is now focusing on providing the benefits of model sparsification also during training. While these methods greatly improve the training efficiency, the training algorithms yielding the most accurate models still materialize the dense weights, or compute dense gradients during training. We"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06898","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/2401.06898/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":"2026-07-05T10:56:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UjfG3F5sJQk4dkqvNfejzwRE9+6Ep5csA8ix6WXhkaGqoBA2beh5X0Wi1okf1Z/hwfBq7l1yEG+OJP1BOU8JBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T12:15:49.609165Z"},"content_sha256":"2d03c7e2d176fa91bb65f5940a723a7b235a1c05dd52c40f8fb0349e35803bfd","schema_version":"1.0","event_id":"sha256:2d03c7e2d176fa91bb65f5940a723a7b235a1c05dd52c40f8fb0349e35803bfd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KSUY6JYSS2LEG6CJHZRLAUX2NT/bundle.json","state_url":"https://pith.science/pith/KSUY6JYSS2LEG6CJHZRLAUX2NT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KSUY6JYSS2LEG6CJHZRLAUX2NT/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":"2026-08-18T12:15:49Z","links":{"resolver":"https://pith.science/pith/KSUY6JYSS2LEG6CJHZRLAUX2NT","bundle":"https://pith.science/pith/KSUY6JYSS2LEG6CJHZRLAUX2NT/bundle.json","state":"https://pith.science/pith/KSUY6JYSS2LEG6CJHZRLAUX2NT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KSUY6JYSS2LEG6CJHZRLAUX2NT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KSUY6JYSS2LEG6CJHZRLAUX2NT","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":"52c3b4bdf147981b84925bc93bc29d77801b9f2373138a57800dbfd84f18509b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-12T21:32:04Z","title_canon_sha256":"487d976a8d4f3d79c6ccc8a44e16ffb5dc55933c553469553ad559054358574d"},"schema_version":"1.0","source":{"id":"2401.06898","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.06898","created_at":"2026-07-05T10:56:04Z"},{"alias_kind":"arxiv_version","alias_value":"2401.06898v2","created_at":"2026-07-05T10:56:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06898","created_at":"2026-07-05T10:56:04Z"},{"alias_kind":"pith_short_12","alias_value":"KSUY6JYSS2LE","created_at":"2026-07-05T10:56:04Z"},{"alias_kind":"pith_short_16","alias_value":"KSUY6JYSS2LEG6CJ","created_at":"2026-07-05T10:56:04Z"},{"alias_kind":"pith_short_8","alias_value":"KSUY6JYS","created_at":"2026-07-05T10:56:04Z"}],"graph_snapshots":[{"event_id":"sha256:2d03c7e2d176fa91bb65f5940a723a7b235a1c05dd52c40f8fb0349e35803bfd","target":"graph","created_at":"2026-07-05T10:56:04Z","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/2401.06898/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The excessive computational requirements of modern artificial neural networks (ANNs) are posing limitations on the machines that can run them. Sparsification of ANNs is often motivated by time, memory and energy savings only during model inference, yielding no benefits during training. A growing body of work is now focusing on providing the benefits of model sparsification also during training. While these methods greatly improve the training efficiency, the training algorithms yielding the most accurate models still materialize the dense weights, or compute dense gradients during training. We","authors_text":"Alexandru Nicolau, Mike Heddes, Narayan Srinivasa, Tony Givargis","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-12T21:32:04Z","title":"Always-Sparse Training by Growing Connections with Guided Stochastic Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06898","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":"sha256:3199f60ea29be703be8e8dc5b7c59f62de01d0d6b86adcc6b37c6438d0b03610","target":"record","created_at":"2026-07-05T10:56:04Z","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":"52c3b4bdf147981b84925bc93bc29d77801b9f2373138a57800dbfd84f18509b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-12T21:32:04Z","title_canon_sha256":"487d976a8d4f3d79c6ccc8a44e16ffb5dc55933c553469553ad559054358574d"},"schema_version":"1.0","source":{"id":"2401.06898","kind":"arxiv","version":2}},"canonical_sha256":"54a98f271296964378493e62b052fa6cd2d11b86f9cce94edae77bf0ede25fa4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54a98f271296964378493e62b052fa6cd2d11b86f9cce94edae77bf0ede25fa4","first_computed_at":"2026-07-05T10:56:04.894978Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:56:04.894978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"swOa0aFxVwKJd6Pydkxs8d3Jk55X6m+/H95be/SGZ8dQxzrBJDuaWlckf166Ze3sunz9qXdq3DI5lnH/YbdYCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:56:04.895409Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.06898","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3199f60ea29be703be8e8dc5b7c59f62de01d0d6b86adcc6b37c6438d0b03610","sha256:2d03c7e2d176fa91bb65f5940a723a7b235a1c05dd52c40f8fb0349e35803bfd"],"state_sha256":"9246c6fbeed8d7d87dc08b63885257f6917f51bff3a622a4f513e341f5c49e3c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pPPYJ+q4jWQkuhYO4tqJGVYihGTbUsuFsGRSybS9UUsJbIuFBq+tyffrUvIetlsZSo94VlwVjjAgymDNZM34DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T12:15:49.615165Z","bundle_sha256":"1062357c17b31d647797a65276ed108d5a1eefb2f507f2d0e158589f9f5a46d9"}}