{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:47445REGGOU5RD4O4V7ZXLMPFC","short_pith_number":"pith:47445REG","canonical_record":{"source":{"id":"2409.09281","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-14T03:11:00Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"63d8683105d334f512abdd4fad0cacb533e28b4afc4045faf36fc92965ea304c","abstract_canon_sha256":"709f830f1ca829488d262bf3712d9366cc0cd8debfee8412bf9362ccb6fc0c14"},"schema_version":"1.0"},"canonical_sha256":"e7f9cec48633a9d88f8ee57f9bad8f28abf9ef6953f497ed5e41a19b8c982161","source":{"kind":"arxiv","id":"2409.09281","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.09281","created_at":"2026-07-05T10:10:08Z"},{"alias_kind":"arxiv_version","alias_value":"2409.09281v2","created_at":"2026-07-05T10:10:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09281","created_at":"2026-07-05T10:10:08Z"},{"alias_kind":"pith_short_12","alias_value":"47445REGGOU5","created_at":"2026-07-05T10:10:08Z"},{"alias_kind":"pith_short_16","alias_value":"47445REGGOU5RD4O","created_at":"2026-07-05T10:10:08Z"},{"alias_kind":"pith_short_8","alias_value":"47445REG","created_at":"2026-07-05T10:10:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:47445REGGOU5RD4O4V7ZXLMPFC","target":"record","payload":{"canonical_record":{"source":{"id":"2409.09281","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-14T03:11:00Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"63d8683105d334f512abdd4fad0cacb533e28b4afc4045faf36fc92965ea304c","abstract_canon_sha256":"709f830f1ca829488d262bf3712d9366cc0cd8debfee8412bf9362ccb6fc0c14"},"schema_version":"1.0"},"canonical_sha256":"e7f9cec48633a9d88f8ee57f9bad8f28abf9ef6953f497ed5e41a19b8c982161","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:08.941854Z","signature_b64":"D3bPTUs0UuYMxq/lgi0huTnCkAlWUQOeYYccUfYqgqYk+12UXyVS1UwC4v2LOdmEcKC8/UXVThB/1iNLswPdAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7f9cec48633a9d88f8ee57f9bad8f28abf9ef6953f497ed5e41a19b8c982161","last_reissued_at":"2026-07-05T10:10:08.941448Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:08.941448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.09281","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":"2026-07-05T10:10:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VL/Oh0lxqaIxIRmIH9cOayO6Zc4xmH7VjDwXtc8IGne7OaKgU8XQ97f4UA96rOdNEDxWLWpwW0KNIPWEUIEYAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T21:36:46.566939Z"},"content_sha256":"946e88c9dd7b582e74778624c8e4b7e660d33f937d69a07b92ed3273851c7e5b","schema_version":"1.0","event_id":"sha256:946e88c9dd7b582e74778624c8e4b7e660d33f937d69a07b92ed3273851c7e5b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:47445REGGOU5RD4O4V7ZXLMPFC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Language Models \"Grok\" to Copy","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ang Lv, Rui Yan, Ruobing Xie, Xingwu Sun, Zhanhui Kang","submitted_at":"2024-09-14T03:11:00Z","abstract_excerpt":"We examine the pre-training dynamics of language models, focusing on their ability to copy text from preceding context--a fundamental skill for various LLM applications, including in-context learning (ICL) and retrieval-augmented generation (RAG). We propose a novel perspective that Transformer-based language models develop copying abilities similarly to grokking, which refers to sudden generalization on test set long after the model fit to the training set. Our experiments yield three arguments: (1) The pre-training loss decreases rapidly, while the context copying ability of models initially"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09281","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/2409.09281/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":"2026-07-05T10:10:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HprAl83tsXUzbPbSh7cuO8PckMBYCisEGrMU5vExurvvBt/cHFlZg/uDuSsKj70u38z/BsYg/wHMSltIfaAkCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T21:36:46.567442Z"},"content_sha256":"421443a300c3abc0b344f23c96c8a9322721aeb18567674a6eb3785f1597faa4","schema_version":"1.0","event_id":"sha256:421443a300c3abc0b344f23c96c8a9322721aeb18567674a6eb3785f1597faa4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/47445REGGOU5RD4O4V7ZXLMPFC/bundle.json","state_url":"https://pith.science/pith/47445REGGOU5RD4O4V7ZXLMPFC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/47445REGGOU5RD4O4V7ZXLMPFC/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":"2026-08-13T21:36:46Z","links":{"resolver":"https://pith.science/pith/47445REGGOU5RD4O4V7ZXLMPFC","bundle":"https://pith.science/pith/47445REGGOU5RD4O4V7ZXLMPFC/bundle.json","state":"https://pith.science/pith/47445REGGOU5RD4O4V7ZXLMPFC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/47445REGGOU5RD4O4V7ZXLMPFC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:47445REGGOU5RD4O4V7ZXLMPFC","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":"709f830f1ca829488d262bf3712d9366cc0cd8debfee8412bf9362ccb6fc0c14","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-14T03:11:00Z","title_canon_sha256":"63d8683105d334f512abdd4fad0cacb533e28b4afc4045faf36fc92965ea304c"},"schema_version":"1.0","source":{"id":"2409.09281","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.09281","created_at":"2026-07-05T10:10:08Z"},{"alias_kind":"arxiv_version","alias_value":"2409.09281v2","created_at":"2026-07-05T10:10:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09281","created_at":"2026-07-05T10:10:08Z"},{"alias_kind":"pith_short_12","alias_value":"47445REGGOU5","created_at":"2026-07-05T10:10:08Z"},{"alias_kind":"pith_short_16","alias_value":"47445REGGOU5RD4O","created_at":"2026-07-05T10:10:08Z"},{"alias_kind":"pith_short_8","alias_value":"47445REG","created_at":"2026-07-05T10:10:08Z"}],"graph_snapshots":[{"event_id":"sha256:421443a300c3abc0b344f23c96c8a9322721aeb18567674a6eb3785f1597faa4","target":"graph","created_at":"2026-07-05T10:10:08Z","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/2409.09281/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We examine the pre-training dynamics of language models, focusing on their ability to copy text from preceding context--a fundamental skill for various LLM applications, including in-context learning (ICL) and retrieval-augmented generation (RAG). We propose a novel perspective that Transformer-based language models develop copying abilities similarly to grokking, which refers to sudden generalization on test set long after the model fit to the training set. Our experiments yield three arguments: (1) The pre-training loss decreases rapidly, while the context copying ability of models initially","authors_text":"Ang Lv, Rui Yan, Ruobing Xie, Xingwu Sun, Zhanhui Kang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-14T03:11:00Z","title":"Language Models \"Grok\" to Copy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09281","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":"sha256:946e88c9dd7b582e74778624c8e4b7e660d33f937d69a07b92ed3273851c7e5b","target":"record","created_at":"2026-07-05T10:10:08Z","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":"709f830f1ca829488d262bf3712d9366cc0cd8debfee8412bf9362ccb6fc0c14","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-14T03:11:00Z","title_canon_sha256":"63d8683105d334f512abdd4fad0cacb533e28b4afc4045faf36fc92965ea304c"},"schema_version":"1.0","source":{"id":"2409.09281","kind":"arxiv","version":2}},"canonical_sha256":"e7f9cec48633a9d88f8ee57f9bad8f28abf9ef6953f497ed5e41a19b8c982161","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7f9cec48633a9d88f8ee57f9bad8f28abf9ef6953f497ed5e41a19b8c982161","first_computed_at":"2026-07-05T10:10:08.941448Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:08.941448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D3bPTUs0UuYMxq/lgi0huTnCkAlWUQOeYYccUfYqgqYk+12UXyVS1UwC4v2LOdmEcKC8/UXVThB/1iNLswPdAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:08.941854Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.09281","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:946e88c9dd7b582e74778624c8e4b7e660d33f937d69a07b92ed3273851c7e5b","sha256:421443a300c3abc0b344f23c96c8a9322721aeb18567674a6eb3785f1597faa4"],"state_sha256":"798be2fe67d160737341b895af8733b30231b660374e3110b25557c7d8f3abe4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eAUXj3GwMI/dQkn5nuD98M5UuxlgQ11XgZhPyKJ98v1Jvwx8iopoebQJIqGHRaFP59r78hoyQs5LGxsDbXwvCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T21:36:46.585602Z","bundle_sha256":"f1ac7e6cdb0a5054a1f0a518590643b7ccd3ccfc4252490321ff789701f6f7a7"}}