{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XHXDT54HGMTMD3AWS7F2BF6UOG","short_pith_number":"pith:XHXDT54H","canonical_record":{"source":{"id":"2308.15419","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-29T16:24:09Z","cross_cats_sorted":[],"title_canon_sha256":"a144f1184dfd5d63fc4b5e57c85838747cd1c592e17357402cf2362a4dab7b6b","abstract_canon_sha256":"d5645bbfde70c6dd810e3647360470353c1bb0d05704af1a51d43cdbbe559377"},"schema_version":"1.0"},"canonical_sha256":"b9ee39f7873326c1ec1697cba097d47195acac6725685084dd8d08711704604f","source":{"kind":"arxiv","id":"2308.15419","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.15419","created_at":"2026-07-05T08:50:24Z"},{"alias_kind":"arxiv_version","alias_value":"2308.15419v2","created_at":"2026-07-05T08:50:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.15419","created_at":"2026-07-05T08:50:24Z"},{"alias_kind":"pith_short_12","alias_value":"XHXDT54HGMTM","created_at":"2026-07-05T08:50:24Z"},{"alias_kind":"pith_short_16","alias_value":"XHXDT54HGMTMD3AW","created_at":"2026-07-05T08:50:24Z"},{"alias_kind":"pith_short_8","alias_value":"XHXDT54H","created_at":"2026-07-05T08:50:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XHXDT54HGMTMD3AWS7F2BF6UOG","target":"record","payload":{"canonical_record":{"source":{"id":"2308.15419","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-29T16:24:09Z","cross_cats_sorted":[],"title_canon_sha256":"a144f1184dfd5d63fc4b5e57c85838747cd1c592e17357402cf2362a4dab7b6b","abstract_canon_sha256":"d5645bbfde70c6dd810e3647360470353c1bb0d05704af1a51d43cdbbe559377"},"schema_version":"1.0"},"canonical_sha256":"b9ee39f7873326c1ec1697cba097d47195acac6725685084dd8d08711704604f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:24.382515Z","signature_b64":"fmnBD+Mp8E55fSbOrRd2dvebvSMRUMm+n9h3nDxMqoVAB8/yrr6kP/5+YQnbUbTzT7g/JtR4W5B6HdHVEaNQAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9ee39f7873326c1ec1697cba097d47195acac6725685084dd8d08711704604f","last_reissued_at":"2026-07-05T08:50:24.382084Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:24.382084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.15419","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":"2026-07-05T08:50:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9DWY4EE59sOF6kPKrMXVguS4roWkDlIv7pPmwJAzsZL7d/Otl9h4znFhfZboW7p+Z6Z91gQzHK21BxJhY5NlAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:27:23.100144Z"},"content_sha256":"c80479a1e83873aa70dc31a14851f41c622fd328744249f04f5eea255d673c87","schema_version":"1.0","event_id":"sha256:c80479a1e83873aa70dc31a14851f41c622fd328744249f04f5eea255d673c87"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XHXDT54HGMTMD3AWS7F2BF6UOG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Characterizing Learning Curves During Language Model Pre-Training: Learning, Forgetting, and Stability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin K. Bergen, Tyler A. Chang, Zhuowen Tu","submitted_at":"2023-08-29T16:24:09Z","abstract_excerpt":"How do language models learn to make predictions during pre-training? To study this, we extract learning curves from five autoregressive English language model pre-training runs, for 1M unseen tokens in context. We observe that the language models generate short repetitive phrases before learning to generate longer and more coherent text. We also find that individual tokens often exhibit sudden increases or decreases in loss that are surprisingly consistent across pre-training runs. To better understand these fluctuations, we quantify the final surprisal, within-run variability, age of acquisi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.15419","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/2308.15419/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":"2026-07-05T08:50:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7h4pt6ZgCnXYz+5sT40pKqGf3H1G7yClSCUomZsX78vJBh3YG4wh3fPfsU3pG6eO075Z5NoXQYWLpSMdooJlDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:27:23.100629Z"},"content_sha256":"d9c0a9e6a18f414e863f87ec096ba793996d5c0c4de9a2baece3f21ed4b55839","schema_version":"1.0","event_id":"sha256:d9c0a9e6a18f414e863f87ec096ba793996d5c0c4de9a2baece3f21ed4b55839"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XHXDT54HGMTMD3AWS7F2BF6UOG/bundle.json","state_url":"https://pith.science/pith/XHXDT54HGMTMD3AWS7F2BF6UOG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XHXDT54HGMTMD3AWS7F2BF6UOG/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":"2026-08-08T12:27:23Z","links":{"resolver":"https://pith.science/pith/XHXDT54HGMTMD3AWS7F2BF6UOG","bundle":"https://pith.science/pith/XHXDT54HGMTMD3AWS7F2BF6UOG/bundle.json","state":"https://pith.science/pith/XHXDT54HGMTMD3AWS7F2BF6UOG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XHXDT54HGMTMD3AWS7F2BF6UOG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XHXDT54HGMTMD3AWS7F2BF6UOG","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":"d5645bbfde70c6dd810e3647360470353c1bb0d05704af1a51d43cdbbe559377","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-29T16:24:09Z","title_canon_sha256":"a144f1184dfd5d63fc4b5e57c85838747cd1c592e17357402cf2362a4dab7b6b"},"schema_version":"1.0","source":{"id":"2308.15419","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.15419","created_at":"2026-07-05T08:50:24Z"},{"alias_kind":"arxiv_version","alias_value":"2308.15419v2","created_at":"2026-07-05T08:50:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.15419","created_at":"2026-07-05T08:50:24Z"},{"alias_kind":"pith_short_12","alias_value":"XHXDT54HGMTM","created_at":"2026-07-05T08:50:24Z"},{"alias_kind":"pith_short_16","alias_value":"XHXDT54HGMTMD3AW","created_at":"2026-07-05T08:50:24Z"},{"alias_kind":"pith_short_8","alias_value":"XHXDT54H","created_at":"2026-07-05T08:50:24Z"}],"graph_snapshots":[{"event_id":"sha256:d9c0a9e6a18f414e863f87ec096ba793996d5c0c4de9a2baece3f21ed4b55839","target":"graph","created_at":"2026-07-05T08:50:24Z","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/2308.15419/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"How do language models learn to make predictions during pre-training? To study this, we extract learning curves from five autoregressive English language model pre-training runs, for 1M unseen tokens in context. We observe that the language models generate short repetitive phrases before learning to generate longer and more coherent text. We also find that individual tokens often exhibit sudden increases or decreases in loss that are surprisingly consistent across pre-training runs. To better understand these fluctuations, we quantify the final surprisal, within-run variability, age of acquisi","authors_text":"Benjamin K. Bergen, Tyler A. Chang, Zhuowen Tu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-29T16:24:09Z","title":"Characterizing Learning Curves During Language Model Pre-Training: Learning, Forgetting, and Stability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.15419","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:c80479a1e83873aa70dc31a14851f41c622fd328744249f04f5eea255d673c87","target":"record","created_at":"2026-07-05T08:50:24Z","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":"d5645bbfde70c6dd810e3647360470353c1bb0d05704af1a51d43cdbbe559377","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-29T16:24:09Z","title_canon_sha256":"a144f1184dfd5d63fc4b5e57c85838747cd1c592e17357402cf2362a4dab7b6b"},"schema_version":"1.0","source":{"id":"2308.15419","kind":"arxiv","version":2}},"canonical_sha256":"b9ee39f7873326c1ec1697cba097d47195acac6725685084dd8d08711704604f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b9ee39f7873326c1ec1697cba097d47195acac6725685084dd8d08711704604f","first_computed_at":"2026-07-05T08:50:24.382084Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:50:24.382084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fmnBD+Mp8E55fSbOrRd2dvebvSMRUMm+n9h3nDxMqoVAB8/yrr6kP/5+YQnbUbTzT7g/JtR4W5B6HdHVEaNQAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:50:24.382515Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.15419","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c80479a1e83873aa70dc31a14851f41c622fd328744249f04f5eea255d673c87","sha256:d9c0a9e6a18f414e863f87ec096ba793996d5c0c4de9a2baece3f21ed4b55839"],"state_sha256":"f887b26555f4773e8aead6d21c28d3d8f4a69dd73199f7cfbd49a22f6a541cb2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lVrpX6EGHy8p3yP26ofg88hroUJFhxff/t9KVdtffmHRXanhcaf9yTiyFpGoEsF20+pcED7luMByxvuA3xtRCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:27:23.104974Z","bundle_sha256":"6da6a1c703b58e6680689986614f5808446f2ccc19f7e96549fdc286b2fba60e"}}