{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BPYBSQVVYGROACWMAV5KBV6R35","short_pith_number":"pith:BPYBSQVV","canonical_record":{"source":{"id":"2405.01582","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-26T18:01:25Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4602e13bec87d13806c4575c06b9f4f80f10353000f4ca88b389018286d0b181","abstract_canon_sha256":"dabe77cd478e3cde015d0653c9dd11a31bbd9772099946f3bb4eefeb88c82fce"},"schema_version":"1.0"},"canonical_sha256":"0bf01942b5c1a2e00acc057aa0d7d1df722957f51b9830250cb336349937ad65","source":{"kind":"arxiv","id":"2405.01582","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.01582","created_at":"2026-07-05T08:18:08Z"},{"alias_kind":"arxiv_version","alias_value":"2405.01582v3","created_at":"2026-07-05T08:18:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.01582","created_at":"2026-07-05T08:18:08Z"},{"alias_kind":"pith_short_12","alias_value":"BPYBSQVVYGRO","created_at":"2026-07-05T08:18:08Z"},{"alias_kind":"pith_short_16","alias_value":"BPYBSQVVYGROACWM","created_at":"2026-07-05T08:18:08Z"},{"alias_kind":"pith_short_8","alias_value":"BPYBSQVV","created_at":"2026-07-05T08:18:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BPYBSQVVYGROACWMAV5KBV6R35","target":"record","payload":{"canonical_record":{"source":{"id":"2405.01582","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-26T18:01:25Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4602e13bec87d13806c4575c06b9f4f80f10353000f4ca88b389018286d0b181","abstract_canon_sha256":"dabe77cd478e3cde015d0653c9dd11a31bbd9772099946f3bb4eefeb88c82fce"},"schema_version":"1.0"},"canonical_sha256":"0bf01942b5c1a2e00acc057aa0d7d1df722957f51b9830250cb336349937ad65","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:18:08.166252Z","signature_b64":"wc2UHDM9179j9S/PIbZgbc80Lva+0VmZ2esdslZ5g/RX53bSpZx2XMh7KnuIbrIAOyOCwXsxs+ACOGlMGhjMCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bf01942b5c1a2e00acc057aa0d7d1df722957f51b9830250cb336349937ad65","last_reissued_at":"2026-07-05T08:18:08.165784Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:18:08.165784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.01582","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":"2026-07-05T08:18:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PEmSkgkpgRgw02J1L4M3970kyw6i+KE0egCOrgkwYMAJcbZiWgtOykbHjjLm9NOqm9OwOQySPp+ZV+Uy6ktBCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:35:37.503370Z"},"content_sha256":"03ea6c6ce5a9c8dd430502759740bea2c25edd27f6047bb14e0b69b0b6fcff5c","schema_version":"1.0","event_id":"sha256:03ea6c6ce5a9c8dd430502759740bea2c25edd27f6047bb14e0b69b0b6fcff5c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BPYBSQVVYGROACWMAV5KBV6R35","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text Quality-Based Pruning for Efficient Training of Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Armen Aghajanyan, Gargi Ghosh, Hu Xu, Karthik Padthe, Kushal Tirumala, Luke Zettlemoyer, Newsha Ardalani, Po-Yao Huang, Russell Howes, Shang-Wen Li, Vasu Sharma","submitted_at":"2024-04-26T18:01:25Z","abstract_excerpt":"In recent times training Language Models (LMs) have relied on computationally heavy training over massive datasets which makes this training process extremely laborious. In this paper we propose a novel method for numerically evaluating text quality in large unlabelled NLP datasets in a model agnostic manner to assign the text instances a \"quality score\".\n  By proposing the text quality metric, the paper establishes a framework to identify and eliminate low-quality text instances, leading to improved training efficiency for LM models. Experimental results over multiple models and datasets demo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.01582","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/2405.01582/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":"2026-07-05T08:18:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7akBPszOK1HrldGzgncacmgfYpUzK1+qK5YrUveF4l1U1RND0rKvW0Sjq2DdZUzJAMGVDW7pqS5TyhTc5ItDCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:35:37.504015Z"},"content_sha256":"bb770cc5b6890d31aa593135e0e0974d9956a6328edc5cee00ccb41cc6f5ee61","schema_version":"1.0","event_id":"sha256:bb770cc5b6890d31aa593135e0e0974d9956a6328edc5cee00ccb41cc6f5ee61"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BPYBSQVVYGROACWMAV5KBV6R35/bundle.json","state_url":"https://pith.science/pith/BPYBSQVVYGROACWMAV5KBV6R35/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BPYBSQVVYGROACWMAV5KBV6R35/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":"2026-07-07T07:35:37Z","links":{"resolver":"https://pith.science/pith/BPYBSQVVYGROACWMAV5KBV6R35","bundle":"https://pith.science/pith/BPYBSQVVYGROACWMAV5KBV6R35/bundle.json","state":"https://pith.science/pith/BPYBSQVVYGROACWMAV5KBV6R35/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BPYBSQVVYGROACWMAV5KBV6R35/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BPYBSQVVYGROACWMAV5KBV6R35","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":"dabe77cd478e3cde015d0653c9dd11a31bbd9772099946f3bb4eefeb88c82fce","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-26T18:01:25Z","title_canon_sha256":"4602e13bec87d13806c4575c06b9f4f80f10353000f4ca88b389018286d0b181"},"schema_version":"1.0","source":{"id":"2405.01582","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.01582","created_at":"2026-07-05T08:18:08Z"},{"alias_kind":"arxiv_version","alias_value":"2405.01582v3","created_at":"2026-07-05T08:18:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.01582","created_at":"2026-07-05T08:18:08Z"},{"alias_kind":"pith_short_12","alias_value":"BPYBSQVVYGRO","created_at":"2026-07-05T08:18:08Z"},{"alias_kind":"pith_short_16","alias_value":"BPYBSQVVYGROACWM","created_at":"2026-07-05T08:18:08Z"},{"alias_kind":"pith_short_8","alias_value":"BPYBSQVV","created_at":"2026-07-05T08:18:08Z"}],"graph_snapshots":[{"event_id":"sha256:bb770cc5b6890d31aa593135e0e0974d9956a6328edc5cee00ccb41cc6f5ee61","target":"graph","created_at":"2026-07-05T08:18:08Z","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/2405.01582/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent times training Language Models (LMs) have relied on computationally heavy training over massive datasets which makes this training process extremely laborious. In this paper we propose a novel method for numerically evaluating text quality in large unlabelled NLP datasets in a model agnostic manner to assign the text instances a \"quality score\".\n  By proposing the text quality metric, the paper establishes a framework to identify and eliminate low-quality text instances, leading to improved training efficiency for LM models. Experimental results over multiple models and datasets demo","authors_text":"Armen Aghajanyan, Gargi Ghosh, Hu Xu, Karthik Padthe, Kushal Tirumala, Luke Zettlemoyer, Newsha Ardalani, Po-Yao Huang, Russell Howes, Shang-Wen Li, Vasu Sharma","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-26T18:01:25Z","title":"Text Quality-Based Pruning for Efficient Training of Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.01582","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":"sha256:03ea6c6ce5a9c8dd430502759740bea2c25edd27f6047bb14e0b69b0b6fcff5c","target":"record","created_at":"2026-07-05T08:18:08Z","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":"dabe77cd478e3cde015d0653c9dd11a31bbd9772099946f3bb4eefeb88c82fce","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-26T18:01:25Z","title_canon_sha256":"4602e13bec87d13806c4575c06b9f4f80f10353000f4ca88b389018286d0b181"},"schema_version":"1.0","source":{"id":"2405.01582","kind":"arxiv","version":3}},"canonical_sha256":"0bf01942b5c1a2e00acc057aa0d7d1df722957f51b9830250cb336349937ad65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0bf01942b5c1a2e00acc057aa0d7d1df722957f51b9830250cb336349937ad65","first_computed_at":"2026-07-05T08:18:08.165784Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:18:08.165784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wc2UHDM9179j9S/PIbZgbc80Lva+0VmZ2esdslZ5g/RX53bSpZx2XMh7KnuIbrIAOyOCwXsxs+ACOGlMGhjMCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:18:08.166252Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.01582","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03ea6c6ce5a9c8dd430502759740bea2c25edd27f6047bb14e0b69b0b6fcff5c","sha256:bb770cc5b6890d31aa593135e0e0974d9956a6328edc5cee00ccb41cc6f5ee61"],"state_sha256":"a0f876b76a724b4145260c5e5071ab05d1ecf87ec60db5f35d3f78e286f8eea5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CwkHd9QgPMC8CvzszjOTvfCPnVf6LuxmOjoqGMI9JtTFvdrz5EvtR/As9XzpspqKJ10llx4upJWrO/a8StGJCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:35:37.509661Z","bundle_sha256":"a354c8f9b32d9e0add6fc5a0176e0a1f7a37af0e7ff29c3c0696def3c9648657"}}