{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UE2SBYHPIXXDOBUZXW7QFK4YLR","short_pith_number":"pith:UE2SBYHP","canonical_record":{"source":{"id":"2411.04330","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-07T00:10:10Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9e5ebe38a1c574b5ae9f91c5e138ef297852af018d59eaa63aeb5144993c4567","abstract_canon_sha256":"cdc6b409fbc87e04ef97235ef0b6c3732f09bfe085c09bae2b7107e4c624503d"},"schema_version":"1.0"},"canonical_sha256":"a13520e0ef45ee370699bdbf02ab985c666779618a48625c99242a90609fb1db","source":{"kind":"arxiv","id":"2411.04330","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.04330","created_at":"2026-07-05T09:42:32Z"},{"alias_kind":"arxiv_version","alias_value":"2411.04330v2","created_at":"2026-07-05T09:42:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04330","created_at":"2026-07-05T09:42:32Z"},{"alias_kind":"pith_short_12","alias_value":"UE2SBYHPIXXD","created_at":"2026-07-05T09:42:32Z"},{"alias_kind":"pith_short_16","alias_value":"UE2SBYHPIXXDOBUZ","created_at":"2026-07-05T09:42:32Z"},{"alias_kind":"pith_short_8","alias_value":"UE2SBYHP","created_at":"2026-07-05T09:42:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UE2SBYHPIXXDOBUZXW7QFK4YLR","target":"record","payload":{"canonical_record":{"source":{"id":"2411.04330","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-07T00:10:10Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9e5ebe38a1c574b5ae9f91c5e138ef297852af018d59eaa63aeb5144993c4567","abstract_canon_sha256":"cdc6b409fbc87e04ef97235ef0b6c3732f09bfe085c09bae2b7107e4c624503d"},"schema_version":"1.0"},"canonical_sha256":"a13520e0ef45ee370699bdbf02ab985c666779618a48625c99242a90609fb1db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:32.043489Z","signature_b64":"8XnjyUJc41pHezhKQf0uABreoAro3cvlTEOKbdffRh/ULwETwUnN/jRPyrVD7gT9FANIU6m8F2RJ3HF0Mrp5Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a13520e0ef45ee370699bdbf02ab985c666779618a48625c99242a90609fb1db","last_reissued_at":"2026-07-05T09:42:32.043010Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:32.043010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.04330","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":"2026-07-05T09:42:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b7Usf9XrB2toebbJYt5ZBv7sVZf3026uGHaqUcaur9Tt4BT7MpVRHAYhf8sAUQpoiykQDNZ+QB97wEtjLI3OAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:49:34.423791Z"},"content_sha256":"86def6273171f9323d3f2953e1728465902eacda1e42fdeab0a73bf363236297","schema_version":"1.0","event_id":"sha256:86def6273171f9323d3f2953e1728465902eacda1e42fdeab0a73bf363236297"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UE2SBYHPIXXDOBUZXW7QFK4YLR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling Laws for Precision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Aditi Raghunathan, Benjamin F. Spector, Blake Bordelon, Cengiz Pehlevan, Christopher R\\'e, Mansheej Paul, Niklas Muennighoff, Tanishq Kumar, Zachary Ankner","submitted_at":"2024-11-07T00:10:10Z","abstract_excerpt":"Low precision training and inference affect both the quality and cost of language models, but current scaling laws do not account for this. In this work, we devise \"precision-aware\" scaling laws for both training and inference. We propose that training in lower precision reduces the model's \"effective parameter count,\" allowing us to predict the additional loss incurred from training in low precision and post-train quantization. For inference, we find that the degradation introduced by post-training quantization increases as models are trained on more data, eventually making additional pretrai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04330","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/2411.04330/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":"2026-07-05T09:42:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xyQb7FDqZh8n4O/PliEksVeNRkrhEzjUx5tNkopjPZCe5coYeIRXAStITDzamoJW2tnkqMxvqviucxWb6vcdCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:49:34.424299Z"},"content_sha256":"c7d4cdd6a67459ddfd77b23d150bd9d1b471e174cedca7685c303c2c64a77a3e","schema_version":"1.0","event_id":"sha256:c7d4cdd6a67459ddfd77b23d150bd9d1b471e174cedca7685c303c2c64a77a3e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UE2SBYHPIXXDOBUZXW7QFK4YLR/bundle.json","state_url":"https://pith.science/pith/UE2SBYHPIXXDOBUZXW7QFK4YLR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UE2SBYHPIXXDOBUZXW7QFK4YLR/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":"2026-08-04T16:49:34Z","links":{"resolver":"https://pith.science/pith/UE2SBYHPIXXDOBUZXW7QFK4YLR","bundle":"https://pith.science/pith/UE2SBYHPIXXDOBUZXW7QFK4YLR/bundle.json","state":"https://pith.science/pith/UE2SBYHPIXXDOBUZXW7QFK4YLR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UE2SBYHPIXXDOBUZXW7QFK4YLR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UE2SBYHPIXXDOBUZXW7QFK4YLR","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":"cdc6b409fbc87e04ef97235ef0b6c3732f09bfe085c09bae2b7107e4c624503d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-07T00:10:10Z","title_canon_sha256":"9e5ebe38a1c574b5ae9f91c5e138ef297852af018d59eaa63aeb5144993c4567"},"schema_version":"1.0","source":{"id":"2411.04330","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.04330","created_at":"2026-07-05T09:42:32Z"},{"alias_kind":"arxiv_version","alias_value":"2411.04330v2","created_at":"2026-07-05T09:42:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04330","created_at":"2026-07-05T09:42:32Z"},{"alias_kind":"pith_short_12","alias_value":"UE2SBYHPIXXD","created_at":"2026-07-05T09:42:32Z"},{"alias_kind":"pith_short_16","alias_value":"UE2SBYHPIXXDOBUZ","created_at":"2026-07-05T09:42:32Z"},{"alias_kind":"pith_short_8","alias_value":"UE2SBYHP","created_at":"2026-07-05T09:42:32Z"}],"graph_snapshots":[{"event_id":"sha256:c7d4cdd6a67459ddfd77b23d150bd9d1b471e174cedca7685c303c2c64a77a3e","target":"graph","created_at":"2026-07-05T09:42:32Z","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/2411.04330/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Low precision training and inference affect both the quality and cost of language models, but current scaling laws do not account for this. In this work, we devise \"precision-aware\" scaling laws for both training and inference. We propose that training in lower precision reduces the model's \"effective parameter count,\" allowing us to predict the additional loss incurred from training in low precision and post-train quantization. For inference, we find that the degradation introduced by post-training quantization increases as models are trained on more data, eventually making additional pretrai","authors_text":"Aditi Raghunathan, Benjamin F. Spector, Blake Bordelon, Cengiz Pehlevan, Christopher R\\'e, Mansheej Paul, Niklas Muennighoff, Tanishq Kumar, Zachary Ankner","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-07T00:10:10Z","title":"Scaling Laws for Precision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04330","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":"sha256:86def6273171f9323d3f2953e1728465902eacda1e42fdeab0a73bf363236297","target":"record","created_at":"2026-07-05T09:42:32Z","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":"cdc6b409fbc87e04ef97235ef0b6c3732f09bfe085c09bae2b7107e4c624503d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-07T00:10:10Z","title_canon_sha256":"9e5ebe38a1c574b5ae9f91c5e138ef297852af018d59eaa63aeb5144993c4567"},"schema_version":"1.0","source":{"id":"2411.04330","kind":"arxiv","version":2}},"canonical_sha256":"a13520e0ef45ee370699bdbf02ab985c666779618a48625c99242a90609fb1db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a13520e0ef45ee370699bdbf02ab985c666779618a48625c99242a90609fb1db","first_computed_at":"2026-07-05T09:42:32.043010Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:32.043010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8XnjyUJc41pHezhKQf0uABreoAro3cvlTEOKbdffRh/ULwETwUnN/jRPyrVD7gT9FANIU6m8F2RJ3HF0Mrp5Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:32.043489Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.04330","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86def6273171f9323d3f2953e1728465902eacda1e42fdeab0a73bf363236297","sha256:c7d4cdd6a67459ddfd77b23d150bd9d1b471e174cedca7685c303c2c64a77a3e"],"state_sha256":"31e153f689c30c008d710fa2c0b9c71c8fe1dbc26a085ffadb10d1a884262797"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"367hWVkN/yZztHmoa1UhcCbZsiVOw8gnEBZsSUVtUkKbVs5I34k/j3d0gm1rPyPMlNkqXIXENgcoF/s+fuIxBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T16:49:34.427759Z","bundle_sha256":"10c3594df27040db3ec5de5d8e7db1d33c6c1b5ab99fa699bd3dc6de3cc893b2"}}