{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HLUCL2K5G6UOZLOP54IQ2NQ6HU","short_pith_number":"pith:HLUCL2K5","canonical_record":{"source":{"id":"2408.09621","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-19T00:26:53Z","cross_cats_sorted":[],"title_canon_sha256":"966f2f6fee40a96254d2887ff0bcbaa31f5f64a7ab6bbe8e3b04a8f8dc58e5c5","abstract_canon_sha256":"a67c2274ba53b49b633ef1f20b027b601a4dba6a654c3d5bab4c391917b6e1a1"},"schema_version":"1.0"},"canonical_sha256":"3ae825e95d37a8ecadcfef110d361e3d1bda84d3742a8b692e506dbe2151ea5b","source":{"kind":"arxiv","id":"2408.09621","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.09621","created_at":"2026-07-05T08:56:34Z"},{"alias_kind":"arxiv_version","alias_value":"2408.09621v1","created_at":"2026-07-05T08:56:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09621","created_at":"2026-07-05T08:56:34Z"},{"alias_kind":"pith_short_12","alias_value":"HLUCL2K5G6UO","created_at":"2026-07-05T08:56:34Z"},{"alias_kind":"pith_short_16","alias_value":"HLUCL2K5G6UOZLOP","created_at":"2026-07-05T08:56:34Z"},{"alias_kind":"pith_short_8","alias_value":"HLUCL2K5","created_at":"2026-07-05T08:56:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HLUCL2K5G6UOZLOP54IQ2NQ6HU","target":"record","payload":{"canonical_record":{"source":{"id":"2408.09621","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-19T00:26:53Z","cross_cats_sorted":[],"title_canon_sha256":"966f2f6fee40a96254d2887ff0bcbaa31f5f64a7ab6bbe8e3b04a8f8dc58e5c5","abstract_canon_sha256":"a67c2274ba53b49b633ef1f20b027b601a4dba6a654c3d5bab4c391917b6e1a1"},"schema_version":"1.0"},"canonical_sha256":"3ae825e95d37a8ecadcfef110d361e3d1bda84d3742a8b692e506dbe2151ea5b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:34.713515Z","signature_b64":"Ueaxa8FBhSvWVxlTS/3UqAatV86WF1gvxk1hJcRWCB0PfJFSPn6jcZOM5lHYbo1kX/pxPMevImxKrFZNlasHDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ae825e95d37a8ecadcfef110d361e3d1bda84d3742a8b692e506dbe2151ea5b","last_reissued_at":"2026-07-05T08:56:34.713076Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:34.713076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.09621","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":"2026-07-05T08:56:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QsDy1ozxzY5uBjLuHdqjCFnzA8FEfeZcWjhveRaYqeqYRN1IzrLcQ/aVz0+Bi+NurC/SqwYPxxbxAwg3Oh1HCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T12:48:15.893776Z"},"content_sha256":"9a8ab05a3ac177951a5391cf6df83013e5062cc78bb212a0f75835ddaec49090","schema_version":"1.0","event_id":"sha256:9a8ab05a3ac177951a5391cf6df83013e5062cc78bb212a0f75835ddaec49090"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HLUCL2K5G6UOZLOP54IQ2NQ6HU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Refining Packing and Shuffling Strategies for Enhanced Performance in Generative Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eric Karl Oermann, Lavender Yao Jiang, Ruilin Wang, Yanbing Chen, Zihao Yang","submitted_at":"2024-08-19T00:26:53Z","abstract_excerpt":"Packing and shuffling tokens is a common practice in training auto-regressive language models (LMs) to prevent overfitting and improve efficiency. Typically documents are concatenated to chunks of maximum sequence length (MSL) and then shuffled. However setting the atom size, the length for each data chunk accompanied by random shuffling, to MSL may lead to contextual incoherence due to tokens from different documents being packed into the same chunk. An alternative approach is to utilize padding, another common data packing strategy, to avoid contextual incoherence by only including one docum"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09621","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/2408.09621/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":"2026-07-05T08:56:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xsA8XRC3w2hJPdb9ovTMu6dgYjtbFtK86pQZXsVxev6OSLm/+wFKK+kI9EBwL1EwXZ3VWGowX4jFbvOmuXLMBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T12:48:15.894610Z"},"content_sha256":"fee7f705fc1363457d86880b272139b51aacc532cf1fa264ee77151fea7ab3ce","schema_version":"1.0","event_id":"sha256:fee7f705fc1363457d86880b272139b51aacc532cf1fa264ee77151fea7ab3ce"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HLUCL2K5G6UOZLOP54IQ2NQ6HU/bundle.json","state_url":"https://pith.science/pith/HLUCL2K5G6UOZLOP54IQ2NQ6HU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HLUCL2K5G6UOZLOP54IQ2NQ6HU/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":"2026-08-19T12:48:15Z","links":{"resolver":"https://pith.science/pith/HLUCL2K5G6UOZLOP54IQ2NQ6HU","bundle":"https://pith.science/pith/HLUCL2K5G6UOZLOP54IQ2NQ6HU/bundle.json","state":"https://pith.science/pith/HLUCL2K5G6UOZLOP54IQ2NQ6HU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HLUCL2K5G6UOZLOP54IQ2NQ6HU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HLUCL2K5G6UOZLOP54IQ2NQ6HU","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":"a67c2274ba53b49b633ef1f20b027b601a4dba6a654c3d5bab4c391917b6e1a1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-19T00:26:53Z","title_canon_sha256":"966f2f6fee40a96254d2887ff0bcbaa31f5f64a7ab6bbe8e3b04a8f8dc58e5c5"},"schema_version":"1.0","source":{"id":"2408.09621","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.09621","created_at":"2026-07-05T08:56:34Z"},{"alias_kind":"arxiv_version","alias_value":"2408.09621v1","created_at":"2026-07-05T08:56:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09621","created_at":"2026-07-05T08:56:34Z"},{"alias_kind":"pith_short_12","alias_value":"HLUCL2K5G6UO","created_at":"2026-07-05T08:56:34Z"},{"alias_kind":"pith_short_16","alias_value":"HLUCL2K5G6UOZLOP","created_at":"2026-07-05T08:56:34Z"},{"alias_kind":"pith_short_8","alias_value":"HLUCL2K5","created_at":"2026-07-05T08:56:34Z"}],"graph_snapshots":[{"event_id":"sha256:fee7f705fc1363457d86880b272139b51aacc532cf1fa264ee77151fea7ab3ce","target":"graph","created_at":"2026-07-05T08:56:34Z","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/2408.09621/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Packing and shuffling tokens is a common practice in training auto-regressive language models (LMs) to prevent overfitting and improve efficiency. Typically documents are concatenated to chunks of maximum sequence length (MSL) and then shuffled. However setting the atom size, the length for each data chunk accompanied by random shuffling, to MSL may lead to contextual incoherence due to tokens from different documents being packed into the same chunk. An alternative approach is to utilize padding, another common data packing strategy, to avoid contextual incoherence by only including one docum","authors_text":"Eric Karl Oermann, Lavender Yao Jiang, Ruilin Wang, Yanbing Chen, Zihao Yang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-19T00:26:53Z","title":"Refining Packing and Shuffling Strategies for Enhanced Performance in Generative Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09621","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":"sha256:9a8ab05a3ac177951a5391cf6df83013e5062cc78bb212a0f75835ddaec49090","target":"record","created_at":"2026-07-05T08:56:34Z","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":"a67c2274ba53b49b633ef1f20b027b601a4dba6a654c3d5bab4c391917b6e1a1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-19T00:26:53Z","title_canon_sha256":"966f2f6fee40a96254d2887ff0bcbaa31f5f64a7ab6bbe8e3b04a8f8dc58e5c5"},"schema_version":"1.0","source":{"id":"2408.09621","kind":"arxiv","version":1}},"canonical_sha256":"3ae825e95d37a8ecadcfef110d361e3d1bda84d3742a8b692e506dbe2151ea5b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ae825e95d37a8ecadcfef110d361e3d1bda84d3742a8b692e506dbe2151ea5b","first_computed_at":"2026-07-05T08:56:34.713076Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:56:34.713076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ueaxa8FBhSvWVxlTS/3UqAatV86WF1gvxk1hJcRWCB0PfJFSPn6jcZOM5lHYbo1kX/pxPMevImxKrFZNlasHDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:56:34.713515Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.09621","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a8ab05a3ac177951a5391cf6df83013e5062cc78bb212a0f75835ddaec49090","sha256:fee7f705fc1363457d86880b272139b51aacc532cf1fa264ee77151fea7ab3ce"],"state_sha256":"ccc534cc598f051a6dcf30f486848aa7c83d932ffe5b11611882ccc525db6c95"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DlA15mrafzj4pMHrObTV5ZmdpEQNCr2Z0x4STs0V+1bcx4daKj6eEGUsHinMn7cxo/hWl1i++5aeiNXmYIX4BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T12:48:15.899771Z","bundle_sha256":"7cd6ac0d29a414c6746b2393ac0c95200ba44c7a3b58d139b968e3d0562d2d6b"}}