{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IR5DQQICYTQ2JQDSJA5Z6RYS5T","short_pith_number":"pith:IR5DQQIC","canonical_record":{"source":{"id":"2606.19989","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-06-18T09:29:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9de390a03f8ceb70673c789c28f2c9f2e02a4662f1c7b09809f439664b9b5c1e","abstract_canon_sha256":"630120d64eb6c9b53ca2cf28c4e151941a37d787df17328714b7e2571b0a73ce"},"schema_version":"1.0"},"canonical_sha256":"447a384102c4e1a4c072483b9f4712ecf8ff39114a1f61aac92a59287e88e512","source":{"kind":"arxiv","id":"2606.19989","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19989","created_at":"2026-06-19T16:12:59Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19989v1","created_at":"2026-06-19T16:12:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19989","created_at":"2026-06-19T16:12:59Z"},{"alias_kind":"pith_short_12","alias_value":"IR5DQQICYTQ2","created_at":"2026-06-19T16:12:59Z"},{"alias_kind":"pith_short_16","alias_value":"IR5DQQICYTQ2JQDS","created_at":"2026-06-19T16:12:59Z"},{"alias_kind":"pith_short_8","alias_value":"IR5DQQIC","created_at":"2026-06-19T16:12:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IR5DQQICYTQ2JQDSJA5Z6RYS5T","target":"record","payload":{"canonical_record":{"source":{"id":"2606.19989","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-06-18T09:29:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9de390a03f8ceb70673c789c28f2c9f2e02a4662f1c7b09809f439664b9b5c1e","abstract_canon_sha256":"630120d64eb6c9b53ca2cf28c4e151941a37d787df17328714b7e2571b0a73ce"},"schema_version":"1.0"},"canonical_sha256":"447a384102c4e1a4c072483b9f4712ecf8ff39114a1f61aac92a59287e88e512","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:59.933441Z","signature_b64":"31qYLTtatz9+gs9XPrhxMLfTQaAdQQVU7EJuYg0rqhASGA69FezvLDtwC0DiX9NV/MqS39j2a2bMZiKouKmEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"447a384102c4e1a4c072483b9f4712ecf8ff39114a1f61aac92a59287e88e512","last_reissued_at":"2026-06-19T16:12:59.933082Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:59.933082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.19989","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":"2026-06-19T16:12:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/aIcQ+XayYerj4OBs++vfYqTug7yx7+ARCkDGJwTqc0MWNwS4v6BYVdmKIEkbFQq7ZMECAqpHFWJ/ffdbbbGCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T00:04:45.979903Z"},"content_sha256":"9aeb958923ecb7f84cd86e9cb743ff2b873e61a35324451b80b6f7fe1be92069","schema_version":"1.0","event_id":"sha256:9aeb958923ecb7f84cd86e9cb743ff2b873e61a35324451b80b6f7fe1be92069"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IR5DQQICYTQ2JQDSJA5Z6RYS5T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Online Dynamic Batching with Formal Guarantees for LLM Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Dian Li, Jiahong Yan, Yaoru Wang, Zekun Wang","submitted_at":"2026-06-18T09:29:28Z","abstract_excerpt":"Modern LLM training breaks a core assumption behind offline batch samplers: the true training cost of a sample is only observable after preprocessing, augmentation, templating, tokenization, and multimodal visual-token expansion. Unless one pays for a preprocessing- and augmentation-dependent length cache, batch construction is therefore blind to the quantity that determines padding, memory use, and GPU saturation. We introduce Online Dynamic Batching (ODB), a DataLoader-side drop-in system that moves batch formation to this point of accurate observability while preserving DDP step alignment. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19989","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/2606.19989/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":"2026-06-19T16:12:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"goGkon/tqc0zMgAG1fSp4a519MfmOMgQBX/nVmRlR1hrt6pObrCjogtXu1XOkLJ+/Tex8XPpIjg1DKxXSFVdBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T00:04:45.980274Z"},"content_sha256":"77264d3296d7ac723b16d785d4c3398d2423e0af3a22ea2ebf1672ea85906bb7","schema_version":"1.0","event_id":"sha256:77264d3296d7ac723b16d785d4c3398d2423e0af3a22ea2ebf1672ea85906bb7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IR5DQQICYTQ2JQDSJA5Z6RYS5T/bundle.json","state_url":"https://pith.science/pith/IR5DQQICYTQ2JQDSJA5Z6RYS5T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IR5DQQICYTQ2JQDSJA5Z6RYS5T/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":"2026-06-28T00:04:45Z","links":{"resolver":"https://pith.science/pith/IR5DQQICYTQ2JQDSJA5Z6RYS5T","bundle":"https://pith.science/pith/IR5DQQICYTQ2JQDSJA5Z6RYS5T/bundle.json","state":"https://pith.science/pith/IR5DQQICYTQ2JQDSJA5Z6RYS5T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IR5DQQICYTQ2JQDSJA5Z6RYS5T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IR5DQQICYTQ2JQDSJA5Z6RYS5T","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":"630120d64eb6c9b53ca2cf28c4e151941a37d787df17328714b7e2571b0a73ce","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-06-18T09:29:28Z","title_canon_sha256":"9de390a03f8ceb70673c789c28f2c9f2e02a4662f1c7b09809f439664b9b5c1e"},"schema_version":"1.0","source":{"id":"2606.19989","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19989","created_at":"2026-06-19T16:12:59Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19989v1","created_at":"2026-06-19T16:12:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19989","created_at":"2026-06-19T16:12:59Z"},{"alias_kind":"pith_short_12","alias_value":"IR5DQQICYTQ2","created_at":"2026-06-19T16:12:59Z"},{"alias_kind":"pith_short_16","alias_value":"IR5DQQICYTQ2JQDS","created_at":"2026-06-19T16:12:59Z"},{"alias_kind":"pith_short_8","alias_value":"IR5DQQIC","created_at":"2026-06-19T16:12:59Z"}],"graph_snapshots":[{"event_id":"sha256:77264d3296d7ac723b16d785d4c3398d2423e0af3a22ea2ebf1672ea85906bb7","target":"graph","created_at":"2026-06-19T16:12:59Z","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/2606.19989/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern LLM training breaks a core assumption behind offline batch samplers: the true training cost of a sample is only observable after preprocessing, augmentation, templating, tokenization, and multimodal visual-token expansion. Unless one pays for a preprocessing- and augmentation-dependent length cache, batch construction is therefore blind to the quantity that determines padding, memory use, and GPU saturation. We introduce Online Dynamic Batching (ODB), a DataLoader-side drop-in system that moves batch formation to this point of accurate observability while preserving DDP step alignment. ","authors_text":"Dian Li, Jiahong Yan, Yaoru Wang, Zekun Wang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-06-18T09:29:28Z","title":"Online Dynamic Batching with Formal Guarantees for LLM Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19989","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":"sha256:9aeb958923ecb7f84cd86e9cb743ff2b873e61a35324451b80b6f7fe1be92069","target":"record","created_at":"2026-06-19T16:12:59Z","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":"630120d64eb6c9b53ca2cf28c4e151941a37d787df17328714b7e2571b0a73ce","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-06-18T09:29:28Z","title_canon_sha256":"9de390a03f8ceb70673c789c28f2c9f2e02a4662f1c7b09809f439664b9b5c1e"},"schema_version":"1.0","source":{"id":"2606.19989","kind":"arxiv","version":1}},"canonical_sha256":"447a384102c4e1a4c072483b9f4712ecf8ff39114a1f61aac92a59287e88e512","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"447a384102c4e1a4c072483b9f4712ecf8ff39114a1f61aac92a59287e88e512","first_computed_at":"2026-06-19T16:12:59.933082Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:59.933082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"31qYLTtatz9+gs9XPrhxMLfTQaAdQQVU7EJuYg0rqhASGA69FezvLDtwC0DiX9NV/MqS39j2a2bMZiKouKmEDQ==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:59.933441Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.19989","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9aeb958923ecb7f84cd86e9cb743ff2b873e61a35324451b80b6f7fe1be92069","sha256:77264d3296d7ac723b16d785d4c3398d2423e0af3a22ea2ebf1672ea85906bb7"],"state_sha256":"b0f01850ffe4e2c3e3490f4fbce1512d258d99b1b768480527b6c5c5c4e11446"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g69I9XpAp40oTBpwydJcjJOl+Xxz4ka7YU8Tj/9Pev/PowGDf69tIL4ODftmZQpn/ITRDN1/Nb6iFFQj9aMgAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T00:04:45.982255Z","bundle_sha256":"ad9174c95265b3ef9d92817bb402c5c8d1965f92c6791e512278226b87cc44d8"}}