{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CPVIRAVNFWN4USPUBPMGEVGPMH","short_pith_number":"pith:CPVIRAVN","canonical_record":{"source":{"id":"2507.03648","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-04T15:25:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b099c30feebf31e394f5fac0d9c76845851d13982e9e725657f1079010244709","abstract_canon_sha256":"b0ba0f4958deb9915a799d129ef693db3c32d1221c721696f15754239d07a642"},"schema_version":"1.0"},"canonical_sha256":"13ea8882ad2d9bca49f40bd86254cf61d88b4a9f73bf80bedc39abbf973deac2","source":{"kind":"arxiv","id":"2507.03648","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.03648","created_at":"2026-07-05T11:32:03Z"},{"alias_kind":"arxiv_version","alias_value":"2507.03648v1","created_at":"2026-07-05T11:32:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03648","created_at":"2026-07-05T11:32:03Z"},{"alias_kind":"pith_short_12","alias_value":"CPVIRAVNFWN4","created_at":"2026-07-05T11:32:03Z"},{"alias_kind":"pith_short_16","alias_value":"CPVIRAVNFWN4USPU","created_at":"2026-07-05T11:32:03Z"},{"alias_kind":"pith_short_8","alias_value":"CPVIRAVN","created_at":"2026-07-05T11:32:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CPVIRAVNFWN4USPUBPMGEVGPMH","target":"record","payload":{"canonical_record":{"source":{"id":"2507.03648","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-04T15:25:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b099c30feebf31e394f5fac0d9c76845851d13982e9e725657f1079010244709","abstract_canon_sha256":"b0ba0f4958deb9915a799d129ef693db3c32d1221c721696f15754239d07a642"},"schema_version":"1.0"},"canonical_sha256":"13ea8882ad2d9bca49f40bd86254cf61d88b4a9f73bf80bedc39abbf973deac2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:03.186253Z","signature_b64":"rhqRS9oS8N6huFa76RC5Sw87YRLot2XpTq9oagP3OMepUHgmbRxMJMHbSVVSB3EPm2cQKgpJEswcpCIfHd9ODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13ea8882ad2d9bca49f40bd86254cf61d88b4a9f73bf80bedc39abbf973deac2","last_reissued_at":"2026-07-05T11:32:03.185755Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:03.185755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.03648","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":"2026-07-05T11:32:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JbSyvtKs+BMxOGyPuh1WMDKZR9In2rp4DkbZVJN7z3CxH2oX9kIzZ13v4Hmqz5attIvScVjCD3mT3/hI0iY1Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:02:48.967326Z"},"content_sha256":"4aa4e698dc8f6d0bf97d992203afcb5726f52574485d9cf2ded4a79bb4bcd195","schema_version":"1.0","event_id":"sha256:4aa4e698dc8f6d0bf97d992203afcb5726f52574485d9cf2ded4a79bb4bcd195"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CPVIRAVNFWN4USPUBPMGEVGPMH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Disentangling the Roles of Representation and Selection in Data Pruning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Albert Gatt, Daniil Ignatev, Dong Nguyen, Hugh Mee Wong, Yingjin Song, Yupei Du","submitted_at":"2025-07-04T15:25:04Z","abstract_excerpt":"Data pruning, selecting small but impactful subsets, offers a promising way to efficiently scale NLP model training. However, existing methods often involve many different design choices, which have not been systematically studied. This limits future developments. In this work, we decompose data pruning into two key components: the data representation and the selection algorithm, and we systematically analyze their influence on the selection of instances. Our theoretical and empirical results highlight the crucial role of representations: better representations, e.g., training gradients, gener"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03648","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/2507.03648/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":"2026-07-05T11:32:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NRnOZJxv7mKk03IvORclU/BQxcz4K+uy8hOxwK2U6vFIO7yN7LNQ0GD2Eo8Dz47k9kysAKJ285LiRf78dQ+YBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:02:48.967709Z"},"content_sha256":"e3fcbd79f599959b7775602bdc61e1d45aeb6ea7e1ec9d558f2150bcbe6b380d","schema_version":"1.0","event_id":"sha256:e3fcbd79f599959b7775602bdc61e1d45aeb6ea7e1ec9d558f2150bcbe6b380d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CPVIRAVNFWN4USPUBPMGEVGPMH/bundle.json","state_url":"https://pith.science/pith/CPVIRAVNFWN4USPUBPMGEVGPMH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CPVIRAVNFWN4USPUBPMGEVGPMH/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":"2026-08-07T12:02:48Z","links":{"resolver":"https://pith.science/pith/CPVIRAVNFWN4USPUBPMGEVGPMH","bundle":"https://pith.science/pith/CPVIRAVNFWN4USPUBPMGEVGPMH/bundle.json","state":"https://pith.science/pith/CPVIRAVNFWN4USPUBPMGEVGPMH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CPVIRAVNFWN4USPUBPMGEVGPMH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CPVIRAVNFWN4USPUBPMGEVGPMH","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":"b0ba0f4958deb9915a799d129ef693db3c32d1221c721696f15754239d07a642","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-04T15:25:04Z","title_canon_sha256":"b099c30feebf31e394f5fac0d9c76845851d13982e9e725657f1079010244709"},"schema_version":"1.0","source":{"id":"2507.03648","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.03648","created_at":"2026-07-05T11:32:03Z"},{"alias_kind":"arxiv_version","alias_value":"2507.03648v1","created_at":"2026-07-05T11:32:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03648","created_at":"2026-07-05T11:32:03Z"},{"alias_kind":"pith_short_12","alias_value":"CPVIRAVNFWN4","created_at":"2026-07-05T11:32:03Z"},{"alias_kind":"pith_short_16","alias_value":"CPVIRAVNFWN4USPU","created_at":"2026-07-05T11:32:03Z"},{"alias_kind":"pith_short_8","alias_value":"CPVIRAVN","created_at":"2026-07-05T11:32:03Z"}],"graph_snapshots":[{"event_id":"sha256:e3fcbd79f599959b7775602bdc61e1d45aeb6ea7e1ec9d558f2150bcbe6b380d","target":"graph","created_at":"2026-07-05T11:32:03Z","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/2507.03648/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data pruning, selecting small but impactful subsets, offers a promising way to efficiently scale NLP model training. However, existing methods often involve many different design choices, which have not been systematically studied. This limits future developments. In this work, we decompose data pruning into two key components: the data representation and the selection algorithm, and we systematically analyze their influence on the selection of instances. Our theoretical and empirical results highlight the crucial role of representations: better representations, e.g., training gradients, gener","authors_text":"Albert Gatt, Daniil Ignatev, Dong Nguyen, Hugh Mee Wong, Yingjin Song, Yupei Du","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-04T15:25:04Z","title":"Disentangling the Roles of Representation and Selection in Data Pruning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03648","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":"sha256:4aa4e698dc8f6d0bf97d992203afcb5726f52574485d9cf2ded4a79bb4bcd195","target":"record","created_at":"2026-07-05T11:32:03Z","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":"b0ba0f4958deb9915a799d129ef693db3c32d1221c721696f15754239d07a642","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-04T15:25:04Z","title_canon_sha256":"b099c30feebf31e394f5fac0d9c76845851d13982e9e725657f1079010244709"},"schema_version":"1.0","source":{"id":"2507.03648","kind":"arxiv","version":1}},"canonical_sha256":"13ea8882ad2d9bca49f40bd86254cf61d88b4a9f73bf80bedc39abbf973deac2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13ea8882ad2d9bca49f40bd86254cf61d88b4a9f73bf80bedc39abbf973deac2","first_computed_at":"2026-07-05T11:32:03.185755Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:32:03.185755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rhqRS9oS8N6huFa76RC5Sw87YRLot2XpTq9oagP3OMepUHgmbRxMJMHbSVVSB3EPm2cQKgpJEswcpCIfHd9ODA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:32:03.186253Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.03648","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4aa4e698dc8f6d0bf97d992203afcb5726f52574485d9cf2ded4a79bb4bcd195","sha256:e3fcbd79f599959b7775602bdc61e1d45aeb6ea7e1ec9d558f2150bcbe6b380d"],"state_sha256":"884e28426d31ab8d53d73235db66daeffe6af950efbb4356688d59dcd14f7185"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WJTDR/oiAbts4UuajPkzoRpUr9WAsaqn1H5ElAfRTaIhALlYHAERHNr1mQJHqYsApTAiP/qqFOsSMpphdMx+DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T12:02:48.970283Z","bundle_sha256":"4a75d28b291184210e468ef1f9cc8df8dfb23860186f97563100197490ef79d0"}}