{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SHKLNNLXOQZW6PISFK2QNYXQJ4","short_pith_number":"pith:SHKLNNLX","canonical_record":{"source":{"id":"2309.08520","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-15T16:29:27Z","cross_cats_sorted":[],"title_canon_sha256":"082dbb3249b7f4101c61436618de4b9ef1129908f4b8b3cebf6be265621ec144","abstract_canon_sha256":"cab163c2177c297ebeef7e8817e9021e449ae7c90e821453237fda4e231f18a0"},"schema_version":"1.0"},"canonical_sha256":"91d4b6b57774336f3d122ab506e2f04f3b1ab101e60426d0cde6ab132525aa0e","source":{"kind":"arxiv","id":"2309.08520","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.08520","created_at":"2026-07-05T06:51:07Z"},{"alias_kind":"arxiv_version","alias_value":"2309.08520v1","created_at":"2026-07-05T06:51:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08520","created_at":"2026-07-05T06:51:07Z"},{"alias_kind":"pith_short_12","alias_value":"SHKLNNLXOQZW","created_at":"2026-07-05T06:51:07Z"},{"alias_kind":"pith_short_16","alias_value":"SHKLNNLXOQZW6PIS","created_at":"2026-07-05T06:51:07Z"},{"alias_kind":"pith_short_8","alias_value":"SHKLNNLX","created_at":"2026-07-05T06:51:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SHKLNNLXOQZW6PISFK2QNYXQJ4","target":"record","payload":{"canonical_record":{"source":{"id":"2309.08520","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-15T16:29:27Z","cross_cats_sorted":[],"title_canon_sha256":"082dbb3249b7f4101c61436618de4b9ef1129908f4b8b3cebf6be265621ec144","abstract_canon_sha256":"cab163c2177c297ebeef7e8817e9021e449ae7c90e821453237fda4e231f18a0"},"schema_version":"1.0"},"canonical_sha256":"91d4b6b57774336f3d122ab506e2f04f3b1ab101e60426d0cde6ab132525aa0e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:51:07.437390Z","signature_b64":"3+kg3s07NTrE93VFixQo7q01k2JPAHNjIWtGAMmzJ9IbYX75cOy4no6bjsHwFLRl4r4KYsko0NX2UkpsrM8XBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91d4b6b57774336f3d122ab506e2f04f3b1ab101e60426d0cde6ab132525aa0e","last_reissued_at":"2026-07-05T06:51:07.436901Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:51:07.436901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.08520","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":"2026-07-05T06:51:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ESnzgxUWGQzkRNap6U08Qx154bL1DGG0weP4NShVauxcj4WbJMLa9f1zza1xVcfLloXBH6fMpHqsNZStgBvCDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T17:59:27.773984Z"},"content_sha256":"00dbf1d11138455f25394ef041a6db9978f6b34f813d5ad5a245d2c60abc1628","schema_version":"1.0","event_id":"sha256:00dbf1d11138455f25394ef041a6db9978f6b34f813d5ad5a245d2c60abc1628"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SHKLNNLXOQZW6PISFK2QNYXQJ4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling Laws for Sparsely-Connected Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carlos Riquelme, Dan Alistarh, Elias Frantar, Neil Houlsby, Utku Evci","submitted_at":"2023-09-15T16:29:27Z","abstract_excerpt":"We explore the impact of parameter sparsity on the scaling behavior of Transformers trained on massive datasets (i.e., \"foundation models\"), in both vision and language domains. In this setting, we identify the first scaling law describing the relationship between weight sparsity, number of non-zero parameters, and amount of training data, which we validate empirically across model and data scales; on ViT/JFT-4B and T5/C4. These results allow us to characterize the \"optimal sparsity\", the sparsity level which yields the best performance for a given effective model size and training budget. For"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08520","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/2309.08520/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":"2026-07-05T06:51:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wEomk50JYE36FxlSKivB/5fJehWFt6VZ2/D50e/3O/iNIWdHRSyEkmfMY8oipdWmhrv/kg1Tp+oTtCDwC0j+Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T17:59:27.774477Z"},"content_sha256":"63632dcddd1a6ebcc272a4260135e90dcaa15184c142074b472d641ab9522c18","schema_version":"1.0","event_id":"sha256:63632dcddd1a6ebcc272a4260135e90dcaa15184c142074b472d641ab9522c18"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SHKLNNLXOQZW6PISFK2QNYXQJ4/bundle.json","state_url":"https://pith.science/pith/SHKLNNLXOQZW6PISFK2QNYXQJ4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SHKLNNLXOQZW6PISFK2QNYXQJ4/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":"2026-08-10T17:59:27Z","links":{"resolver":"https://pith.science/pith/SHKLNNLXOQZW6PISFK2QNYXQJ4","bundle":"https://pith.science/pith/SHKLNNLXOQZW6PISFK2QNYXQJ4/bundle.json","state":"https://pith.science/pith/SHKLNNLXOQZW6PISFK2QNYXQJ4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SHKLNNLXOQZW6PISFK2QNYXQJ4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SHKLNNLXOQZW6PISFK2QNYXQJ4","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":"cab163c2177c297ebeef7e8817e9021e449ae7c90e821453237fda4e231f18a0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-15T16:29:27Z","title_canon_sha256":"082dbb3249b7f4101c61436618de4b9ef1129908f4b8b3cebf6be265621ec144"},"schema_version":"1.0","source":{"id":"2309.08520","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.08520","created_at":"2026-07-05T06:51:07Z"},{"alias_kind":"arxiv_version","alias_value":"2309.08520v1","created_at":"2026-07-05T06:51:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08520","created_at":"2026-07-05T06:51:07Z"},{"alias_kind":"pith_short_12","alias_value":"SHKLNNLXOQZW","created_at":"2026-07-05T06:51:07Z"},{"alias_kind":"pith_short_16","alias_value":"SHKLNNLXOQZW6PIS","created_at":"2026-07-05T06:51:07Z"},{"alias_kind":"pith_short_8","alias_value":"SHKLNNLX","created_at":"2026-07-05T06:51:07Z"}],"graph_snapshots":[{"event_id":"sha256:63632dcddd1a6ebcc272a4260135e90dcaa15184c142074b472d641ab9522c18","target":"graph","created_at":"2026-07-05T06:51:07Z","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/2309.08520/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We explore the impact of parameter sparsity on the scaling behavior of Transformers trained on massive datasets (i.e., \"foundation models\"), in both vision and language domains. In this setting, we identify the first scaling law describing the relationship between weight sparsity, number of non-zero parameters, and amount of training data, which we validate empirically across model and data scales; on ViT/JFT-4B and T5/C4. These results allow us to characterize the \"optimal sparsity\", the sparsity level which yields the best performance for a given effective model size and training budget. For","authors_text":"Carlos Riquelme, Dan Alistarh, Elias Frantar, Neil Houlsby, Utku Evci","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-15T16:29:27Z","title":"Scaling Laws for Sparsely-Connected Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08520","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":"sha256:00dbf1d11138455f25394ef041a6db9978f6b34f813d5ad5a245d2c60abc1628","target":"record","created_at":"2026-07-05T06:51:07Z","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":"cab163c2177c297ebeef7e8817e9021e449ae7c90e821453237fda4e231f18a0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-15T16:29:27Z","title_canon_sha256":"082dbb3249b7f4101c61436618de4b9ef1129908f4b8b3cebf6be265621ec144"},"schema_version":"1.0","source":{"id":"2309.08520","kind":"arxiv","version":1}},"canonical_sha256":"91d4b6b57774336f3d122ab506e2f04f3b1ab101e60426d0cde6ab132525aa0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91d4b6b57774336f3d122ab506e2f04f3b1ab101e60426d0cde6ab132525aa0e","first_computed_at":"2026-07-05T06:51:07.436901Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:51:07.436901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3+kg3s07NTrE93VFixQo7q01k2JPAHNjIWtGAMmzJ9IbYX75cOy4no6bjsHwFLRl4r4KYsko0NX2UkpsrM8XBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:51:07.437390Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.08520","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:00dbf1d11138455f25394ef041a6db9978f6b34f813d5ad5a245d2c60abc1628","sha256:63632dcddd1a6ebcc272a4260135e90dcaa15184c142074b472d641ab9522c18"],"state_sha256":"cbff45749035d83212db5e78b7b038c78432e8d4ff04eaa2787c80166c2a16f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LII0h7sHR8r36iPXTIF6+pFf/EvYmUBaI5Y4aJDJM45oqOJZbQkj5wQGEFAtnYK6JcQgjKM283+vyV1XSBQ6DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T17:59:27.778663Z","bundle_sha256":"f27280850d3d9bc2da60d98e22159b23eb756e89f941d334e3a2d229270d6de4"}}