{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:UZ3JX2HRYKENAYWICGS3I56SOK","short_pith_number":"pith:UZ3JX2HR","canonical_record":{"source":{"id":"2306.02870","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T13:43:50Z","cross_cats_sorted":[],"title_canon_sha256":"99f771bdeb90ebfc265865ff8db0afdf831fe9a133aa7801f62ba0c13380a444","abstract_canon_sha256":"e85132bc5de40ce36444e609efff3556889e160b779811eb776cd61f8357efca"},"schema_version":"1.0"},"canonical_sha256":"a6769be8f1c288d062c811a5b477d272885b339a1d9e51c44e6ab7d3fe3d2bd2","source":{"kind":"arxiv","id":"2306.02870","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.02870","created_at":"2026-07-05T06:17:32Z"},{"alias_kind":"arxiv_version","alias_value":"2306.02870v1","created_at":"2026-07-05T06:17:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02870","created_at":"2026-07-05T06:17:32Z"},{"alias_kind":"pith_short_12","alias_value":"UZ3JX2HRYKEN","created_at":"2026-07-05T06:17:32Z"},{"alias_kind":"pith_short_16","alias_value":"UZ3JX2HRYKENAYWI","created_at":"2026-07-05T06:17:32Z"},{"alias_kind":"pith_short_8","alias_value":"UZ3JX2HR","created_at":"2026-07-05T06:17:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:UZ3JX2HRYKENAYWICGS3I56SOK","target":"record","payload":{"canonical_record":{"source":{"id":"2306.02870","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T13:43:50Z","cross_cats_sorted":[],"title_canon_sha256":"99f771bdeb90ebfc265865ff8db0afdf831fe9a133aa7801f62ba0c13380a444","abstract_canon_sha256":"e85132bc5de40ce36444e609efff3556889e160b779811eb776cd61f8357efca"},"schema_version":"1.0"},"canonical_sha256":"a6769be8f1c288d062c811a5b477d272885b339a1d9e51c44e6ab7d3fe3d2bd2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:32.251157Z","signature_b64":"7gXEKkJzV5Z6ZuyBysVgom2Ucy1b9Jn18wnQdzzinlFRgtULgr0nQsBO53nCNj/6cYk9xD9APOvtRICC7E2cCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6769be8f1c288d062c811a5b477d272885b339a1d9e51c44e6ab7d3fe3d2bd2","last_reissued_at":"2026-07-05T06:17:32.250718Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:32.250718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.02870","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":"2026-07-05T06:17:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RD2FzCiTYMb1+3go3+qXoQgS/La1yJgBA1Tn+y8qYwfu2Fdx967NMvSmk2OgtEYOXlGxUIBGL0SiKg5hl2Y4Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:06:08.932316Z"},"content_sha256":"5c165d84c538c3f4ae28e38e9009c9a1798f811b183efe469cd069418dc7560d","schema_version":"1.0","event_id":"sha256:5c165d84c538c3f4ae28e38e9009c9a1798f811b183efe469cd069418dc7560d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:UZ3JX2HRYKENAYWICGS3I56SOK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On \"Scientific Debt\" in NLP: A Case for More Rigour in Language Model Pre-Training Research","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adhiguna Kuncoro, Alham Fikri Aji, Genta Indra Winata, Haryo Akbarianto Wibowo, Made Nindyatama Nityasya, Phil Blunsom, Radityo Eko Prasojo","submitted_at":"2023-06-05T13:43:50Z","abstract_excerpt":"This evidence-based position paper critiques current research practices within the language model pre-training literature. Despite rapid recent progress afforded by increasingly better pre-trained language models (PLMs), current PLM research practices often conflate different possible sources of model improvement, without conducting proper ablation studies and principled comparisons between different models under comparable conditions. These practices (i) leave us ill-equipped to understand which pre-training approaches should be used under what circumstances; (ii) impede reproducibility and c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02870","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/2306.02870/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":"2026-07-05T06:17:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SYLPN/QVs2H3d2d3XM9S0uuG7mioNv72s3mWFDiomOHS4OP1ZFRZ5KKQptrfJ/kbMhU2HGRyxZ9y9W7mEnOjDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:06:08.933201Z"},"content_sha256":"fc5182b6322241eefb94e9f8363128566d76a084a7d8a33a907602edaa873498","schema_version":"1.0","event_id":"sha256:fc5182b6322241eefb94e9f8363128566d76a084a7d8a33a907602edaa873498"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UZ3JX2HRYKENAYWICGS3I56SOK/bundle.json","state_url":"https://pith.science/pith/UZ3JX2HRYKENAYWICGS3I56SOK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UZ3JX2HRYKENAYWICGS3I56SOK/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":"2026-08-05T03:06:08Z","links":{"resolver":"https://pith.science/pith/UZ3JX2HRYKENAYWICGS3I56SOK","bundle":"https://pith.science/pith/UZ3JX2HRYKENAYWICGS3I56SOK/bundle.json","state":"https://pith.science/pith/UZ3JX2HRYKENAYWICGS3I56SOK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UZ3JX2HRYKENAYWICGS3I56SOK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UZ3JX2HRYKENAYWICGS3I56SOK","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":"e85132bc5de40ce36444e609efff3556889e160b779811eb776cd61f8357efca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T13:43:50Z","title_canon_sha256":"99f771bdeb90ebfc265865ff8db0afdf831fe9a133aa7801f62ba0c13380a444"},"schema_version":"1.0","source":{"id":"2306.02870","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.02870","created_at":"2026-07-05T06:17:32Z"},{"alias_kind":"arxiv_version","alias_value":"2306.02870v1","created_at":"2026-07-05T06:17:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02870","created_at":"2026-07-05T06:17:32Z"},{"alias_kind":"pith_short_12","alias_value":"UZ3JX2HRYKEN","created_at":"2026-07-05T06:17:32Z"},{"alias_kind":"pith_short_16","alias_value":"UZ3JX2HRYKENAYWI","created_at":"2026-07-05T06:17:32Z"},{"alias_kind":"pith_short_8","alias_value":"UZ3JX2HR","created_at":"2026-07-05T06:17:32Z"}],"graph_snapshots":[{"event_id":"sha256:fc5182b6322241eefb94e9f8363128566d76a084a7d8a33a907602edaa873498","target":"graph","created_at":"2026-07-05T06:17:32Z","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/2306.02870/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This evidence-based position paper critiques current research practices within the language model pre-training literature. Despite rapid recent progress afforded by increasingly better pre-trained language models (PLMs), current PLM research practices often conflate different possible sources of model improvement, without conducting proper ablation studies and principled comparisons between different models under comparable conditions. These practices (i) leave us ill-equipped to understand which pre-training approaches should be used under what circumstances; (ii) impede reproducibility and c","authors_text":"Adhiguna Kuncoro, Alham Fikri Aji, Genta Indra Winata, Haryo Akbarianto Wibowo, Made Nindyatama Nityasya, Phil Blunsom, Radityo Eko Prasojo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T13:43:50Z","title":"On \"Scientific Debt\" in NLP: A Case for More Rigour in Language Model Pre-Training Research"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02870","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":"sha256:5c165d84c538c3f4ae28e38e9009c9a1798f811b183efe469cd069418dc7560d","target":"record","created_at":"2026-07-05T06:17:32Z","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":"e85132bc5de40ce36444e609efff3556889e160b779811eb776cd61f8357efca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-05T13:43:50Z","title_canon_sha256":"99f771bdeb90ebfc265865ff8db0afdf831fe9a133aa7801f62ba0c13380a444"},"schema_version":"1.0","source":{"id":"2306.02870","kind":"arxiv","version":1}},"canonical_sha256":"a6769be8f1c288d062c811a5b477d272885b339a1d9e51c44e6ab7d3fe3d2bd2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a6769be8f1c288d062c811a5b477d272885b339a1d9e51c44e6ab7d3fe3d2bd2","first_computed_at":"2026-07-05T06:17:32.250718Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:17:32.250718Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7gXEKkJzV5Z6ZuyBysVgom2Ucy1b9Jn18wnQdzzinlFRgtULgr0nQsBO53nCNj/6cYk9xD9APOvtRICC7E2cCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:17:32.251157Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.02870","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5c165d84c538c3f4ae28e38e9009c9a1798f811b183efe469cd069418dc7560d","sha256:fc5182b6322241eefb94e9f8363128566d76a084a7d8a33a907602edaa873498"],"state_sha256":"094b81032a92c3f2ee8f83fe6134c1827494305b52950a534cefc518ac9d4281"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lkwyFmr0pFwtfPavp5FBURdzx4VNsMsFoIW/inx0FIAsqJeHKgmobCipPpRUxoPy1Qvo1tAhvxl4ymIEOStaCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T03:06:08.938094Z","bundle_sha256":"7780c3e41047a056c74ae4028f7c37b8d89826afdb5e57d6a5212c26b2318fcb"}}