{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3GC5GGOFA6L5XND2XMTVG4PXRP","short_pith_number":"pith:3GC5GGOF","canonical_record":{"source":{"id":"2310.14633","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-23T07:13:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"adc7bed7265de4aa8e200a7274d8dc6b0ddd58ce81c720f55a382a24df987c4d","abstract_canon_sha256":"73b9c7b11561b46d63640d16dec6d48b5b43a3aa161b9d3ab821a0fef3c54aba"},"schema_version":"1.0"},"canonical_sha256":"d985d319c50797dbb47abb275371f78bc3b26c9fcf4094e02908918db4dc6ae4","source":{"kind":"arxiv","id":"2310.14633","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.14633","created_at":"2026-07-05T08:34:07Z"},{"alias_kind":"arxiv_version","alias_value":"2310.14633v3","created_at":"2026-07-05T08:34:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14633","created_at":"2026-07-05T08:34:07Z"},{"alias_kind":"pith_short_12","alias_value":"3GC5GGOFA6L5","created_at":"2026-07-05T08:34:07Z"},{"alias_kind":"pith_short_16","alias_value":"3GC5GGOFA6L5XND2","created_at":"2026-07-05T08:34:07Z"},{"alias_kind":"pith_short_8","alias_value":"3GC5GGOF","created_at":"2026-07-05T08:34:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3GC5GGOFA6L5XND2XMTVG4PXRP","target":"record","payload":{"canonical_record":{"source":{"id":"2310.14633","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-23T07:13:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"adc7bed7265de4aa8e200a7274d8dc6b0ddd58ce81c720f55a382a24df987c4d","abstract_canon_sha256":"73b9c7b11561b46d63640d16dec6d48b5b43a3aa161b9d3ab821a0fef3c54aba"},"schema_version":"1.0"},"canonical_sha256":"d985d319c50797dbb47abb275371f78bc3b26c9fcf4094e02908918db4dc6ae4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:07.025606Z","signature_b64":"icx7oniqJioqzfrrsZNuLRE8dzgsPpvtQWA5U7CdnjlOutdwxeOLZ5k+yywJ0CzGnfSX+sXmkHs4l2yQ5AVQAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d985d319c50797dbb47abb275371f78bc3b26c9fcf4094e02908918db4dc6ae4","last_reissued_at":"2026-07-05T08:34:07.025105Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:07.025105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.14633","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:34:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6EwXAKM+wGqPdxUupAvvFoIid3V7uU6ds67A+cfkuKtlt/3Sqz+bPkAYqTH9FlFIE0S+tO1812Rpa8sl9TSqAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T14:58:35.551283Z"},"content_sha256":"0afe2bd671ccd41b5fd18ef05348e20ad80b157244a14ab7cb26c1edf67297d1","schema_version":"1.0","event_id":"sha256:0afe2bd671ccd41b5fd18ef05348e20ad80b157244a14ab7cb26c1edf67297d1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3GC5GGOFA6L5XND2XMTVG4PXRP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Extending Input Contexts of Language Models through Training on Segmented Sequences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"George Karypis, Julian McAuley, Petros Karypis","submitted_at":"2023-10-23T07:13:31Z","abstract_excerpt":"Effectively training language models on long inputs poses many technical challenges. As a cost consideration, languages models are pretrained on a fixed sequence length before being adapted to longer sequences. We explore various methods for adapting models to longer inputs by training on segmented sequences and an interpolation-based method for extending absolute positional embeddings. We develop a training procedure to extend the input context size of pretrained models with no architectural changes and no additional memory costs than training on the original input lengths. By sub-sampling se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14633","kind":"arxiv","version":3},"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/2310.14633/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":"2026-07-05T08:34:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iSxuwXxVJXJ0wMm5qk28ce2YS3wxgqIvwvrnk6zPROjvbnJstg+crlBwHxGGh8feqBk0iBUngpJUNNfAOFCMCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T14:58:35.551786Z"},"content_sha256":"0b347e06f457214a3b2e224c8673390c984972b9a270a4ed85bb8fc70995ee4c","schema_version":"1.0","event_id":"sha256:0b347e06f457214a3b2e224c8673390c984972b9a270a4ed85bb8fc70995ee4c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3GC5GGOFA6L5XND2XMTVG4PXRP/bundle.json","state_url":"https://pith.science/pith/3GC5GGOFA6L5XND2XMTVG4PXRP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3GC5GGOFA6L5XND2XMTVG4PXRP/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":"2026-08-12T14:58:35Z","links":{"resolver":"https://pith.science/pith/3GC5GGOFA6L5XND2XMTVG4PXRP","bundle":"https://pith.science/pith/3GC5GGOFA6L5XND2XMTVG4PXRP/bundle.json","state":"https://pith.science/pith/3GC5GGOFA6L5XND2XMTVG4PXRP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3GC5GGOFA6L5XND2XMTVG4PXRP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3GC5GGOFA6L5XND2XMTVG4PXRP","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":"73b9c7b11561b46d63640d16dec6d48b5b43a3aa161b9d3ab821a0fef3c54aba","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-23T07:13:31Z","title_canon_sha256":"adc7bed7265de4aa8e200a7274d8dc6b0ddd58ce81c720f55a382a24df987c4d"},"schema_version":"1.0","source":{"id":"2310.14633","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.14633","created_at":"2026-07-05T08:34:07Z"},{"alias_kind":"arxiv_version","alias_value":"2310.14633v3","created_at":"2026-07-05T08:34:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14633","created_at":"2026-07-05T08:34:07Z"},{"alias_kind":"pith_short_12","alias_value":"3GC5GGOFA6L5","created_at":"2026-07-05T08:34:07Z"},{"alias_kind":"pith_short_16","alias_value":"3GC5GGOFA6L5XND2","created_at":"2026-07-05T08:34:07Z"},{"alias_kind":"pith_short_8","alias_value":"3GC5GGOF","created_at":"2026-07-05T08:34:07Z"}],"graph_snapshots":[{"event_id":"sha256:0b347e06f457214a3b2e224c8673390c984972b9a270a4ed85bb8fc70995ee4c","target":"graph","created_at":"2026-07-05T08:34:07Z","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/2310.14633/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Effectively training language models on long inputs poses many technical challenges. As a cost consideration, languages models are pretrained on a fixed sequence length before being adapted to longer sequences. We explore various methods for adapting models to longer inputs by training on segmented sequences and an interpolation-based method for extending absolute positional embeddings. We develop a training procedure to extend the input context size of pretrained models with no architectural changes and no additional memory costs than training on the original input lengths. By sub-sampling se","authors_text":"George Karypis, Julian McAuley, Petros Karypis","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-23T07:13:31Z","title":"Extending Input Contexts of Language Models through Training on Segmented Sequences"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14633","kind":"arxiv","version":3},"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":"sha256:0afe2bd671ccd41b5fd18ef05348e20ad80b157244a14ab7cb26c1edf67297d1","target":"record","created_at":"2026-07-05T08:34:07Z","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":"73b9c7b11561b46d63640d16dec6d48b5b43a3aa161b9d3ab821a0fef3c54aba","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-23T07:13:31Z","title_canon_sha256":"adc7bed7265de4aa8e200a7274d8dc6b0ddd58ce81c720f55a382a24df987c4d"},"schema_version":"1.0","source":{"id":"2310.14633","kind":"arxiv","version":3}},"canonical_sha256":"d985d319c50797dbb47abb275371f78bc3b26c9fcf4094e02908918db4dc6ae4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d985d319c50797dbb47abb275371f78bc3b26c9fcf4094e02908918db4dc6ae4","first_computed_at":"2026-07-05T08:34:07.025105Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:34:07.025105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"icx7oniqJioqzfrrsZNuLRE8dzgsPpvtQWA5U7CdnjlOutdwxeOLZ5k+yywJ0CzGnfSX+sXmkHs4l2yQ5AVQAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:34:07.025606Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.14633","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0afe2bd671ccd41b5fd18ef05348e20ad80b157244a14ab7cb26c1edf67297d1","sha256:0b347e06f457214a3b2e224c8673390c984972b9a270a4ed85bb8fc70995ee4c"],"state_sha256":"a00dfa3111006ec0b078f083930704bb367664e2aad8d0bdaa19373a394cf4c2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YRCLZm6Mv5EY70dop0Q2EUP1oSmHZYcdeDHE33LfTFCfivCHnM2lMNqpmv1CubBLaxfm1RZEvF+/yYVvyWN9Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T14:58:35.555490Z","bundle_sha256":"577da7ae6a8995cf8912512c954602ee75a5ffb9a2803d3078a93f9cb806d1dd"}}