{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:N5IPFUTS7FMRJ4AXXUE27IPLFA","short_pith_number":"pith:N5IPFUTS","canonical_record":{"source":{"id":"2005.00175","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-05-01T02:01:18Z","cross_cats_sorted":[],"title_canon_sha256":"fd41aac96594acf374c3d3a23f087cfe8bdbb01c1d2341a13d241597cf6272c7","abstract_canon_sha256":"b88e437fde1ad4b3622811484e669d5253116fd5f01b13c70833afda53834b00"},"schema_version":"1.0"},"canonical_sha256":"6f50f2d272f95914f017bd09afa1eb280c18a479b14247c5008191c904f9cc91","source":{"kind":"arxiv","id":"2005.00175","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.00175","created_at":"2026-07-05T04:24:53Z"},{"alias_kind":"arxiv_version","alias_value":"2005.00175v3","created_at":"2026-07-05T04:24:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00175","created_at":"2026-07-05T04:24:53Z"},{"alias_kind":"pith_short_12","alias_value":"N5IPFUTS7FMR","created_at":"2026-07-05T04:24:53Z"},{"alias_kind":"pith_short_16","alias_value":"N5IPFUTS7FMRJ4AX","created_at":"2026-07-05T04:24:53Z"},{"alias_kind":"pith_short_8","alias_value":"N5IPFUTS","created_at":"2026-07-05T04:24:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:N5IPFUTS7FMRJ4AXXUE27IPLFA","target":"record","payload":{"canonical_record":{"source":{"id":"2005.00175","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-05-01T02:01:18Z","cross_cats_sorted":[],"title_canon_sha256":"fd41aac96594acf374c3d3a23f087cfe8bdbb01c1d2341a13d241597cf6272c7","abstract_canon_sha256":"b88e437fde1ad4b3622811484e669d5253116fd5f01b13c70833afda53834b00"},"schema_version":"1.0"},"canonical_sha256":"6f50f2d272f95914f017bd09afa1eb280c18a479b14247c5008191c904f9cc91","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:24:53.786614Z","signature_b64":"3ABrW0C5p8GJ9UYwHBUD9w5dsnTlVAo9HjyKoDxNfk5rcZU9frAL+mze52glyyiOHyZKfwC3yn18389XF8lQDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f50f2d272f95914f017bd09afa1eb280c18a479b14247c5008191c904f9cc91","last_reissued_at":"2026-07-05T04:24:53.785996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:24:53.785996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.00175","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":"2026-07-05T04:24:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C6kq4uOz7rgOzUwXQslIBajA4wA4CKrEnp7p4cn3h8ywdUu3tKJP6Owcwnj17H/FkgueATP7LbcpygPttjnJAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:04:01.657977Z"},"content_sha256":"02f39e070466f163d0cab07d41b824be2929a2c8155ca5628973a70e71b42565","schema_version":"1.0","event_id":"sha256:02f39e070466f163d0cab07d41b824be2929a2c8155ca5628973a70e71b42565"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:N5IPFUTS7FMRJ4AXXUE27IPLFA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Selecting Informative Contexts Improves Language Model Finetuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Huth, Javier Turek, Nicole Beckage, Richard Antonello","submitted_at":"2020-05-01T02:01:18Z","abstract_excerpt":"Language model fine-tuning is essential for modern natural language processing, but is computationally expensive and time-consuming. Further, the effectiveness of fine-tuning is limited by the inclusion of training examples that negatively affect performance. Here we present a general fine-tuning method that we call information gain filtration for improving the overall training efficiency and final performance of language model fine-tuning. We define the information gain of an example as the improvement on a test metric after training on that example. A secondary learner is then trained to app"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00175","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/2005.00175/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":"2026-07-05T04:24:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zKKUeqBj2KYgMqN+dZngZmGprKYcuK6pNxB+LFHSVGhv/oKdM3D9Y97cGyHdabBMYqkNXaEncPv5ntrjwDSGDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:04:01.658480Z"},"content_sha256":"5bd4cb4e19a501f3e188407a83586ab2f513aa7dac35be134b0d2b9825a2ed15","schema_version":"1.0","event_id":"sha256:5bd4cb4e19a501f3e188407a83586ab2f513aa7dac35be134b0d2b9825a2ed15"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/N5IPFUTS7FMRJ4AXXUE27IPLFA/bundle.json","state_url":"https://pith.science/pith/N5IPFUTS7FMRJ4AXXUE27IPLFA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/N5IPFUTS7FMRJ4AXXUE27IPLFA/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":"2026-08-08T08:04:01Z","links":{"resolver":"https://pith.science/pith/N5IPFUTS7FMRJ4AXXUE27IPLFA","bundle":"https://pith.science/pith/N5IPFUTS7FMRJ4AXXUE27IPLFA/bundle.json","state":"https://pith.science/pith/N5IPFUTS7FMRJ4AXXUE27IPLFA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/N5IPFUTS7FMRJ4AXXUE27IPLFA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:N5IPFUTS7FMRJ4AXXUE27IPLFA","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":"b88e437fde1ad4b3622811484e669d5253116fd5f01b13c70833afda53834b00","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-05-01T02:01:18Z","title_canon_sha256":"fd41aac96594acf374c3d3a23f087cfe8bdbb01c1d2341a13d241597cf6272c7"},"schema_version":"1.0","source":{"id":"2005.00175","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.00175","created_at":"2026-07-05T04:24:53Z"},{"alias_kind":"arxiv_version","alias_value":"2005.00175v3","created_at":"2026-07-05T04:24:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00175","created_at":"2026-07-05T04:24:53Z"},{"alias_kind":"pith_short_12","alias_value":"N5IPFUTS7FMR","created_at":"2026-07-05T04:24:53Z"},{"alias_kind":"pith_short_16","alias_value":"N5IPFUTS7FMRJ4AX","created_at":"2026-07-05T04:24:53Z"},{"alias_kind":"pith_short_8","alias_value":"N5IPFUTS","created_at":"2026-07-05T04:24:53Z"}],"graph_snapshots":[{"event_id":"sha256:5bd4cb4e19a501f3e188407a83586ab2f513aa7dac35be134b0d2b9825a2ed15","target":"graph","created_at":"2026-07-05T04:24:53Z","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/2005.00175/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language model fine-tuning is essential for modern natural language processing, but is computationally expensive and time-consuming. Further, the effectiveness of fine-tuning is limited by the inclusion of training examples that negatively affect performance. Here we present a general fine-tuning method that we call information gain filtration for improving the overall training efficiency and final performance of language model fine-tuning. We define the information gain of an example as the improvement on a test metric after training on that example. A secondary learner is then trained to app","authors_text":"Alexander Huth, Javier Turek, Nicole Beckage, Richard Antonello","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-05-01T02:01:18Z","title":"Selecting Informative Contexts Improves Language Model Finetuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00175","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":"sha256:02f39e070466f163d0cab07d41b824be2929a2c8155ca5628973a70e71b42565","target":"record","created_at":"2026-07-05T04:24:53Z","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":"b88e437fde1ad4b3622811484e669d5253116fd5f01b13c70833afda53834b00","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-05-01T02:01:18Z","title_canon_sha256":"fd41aac96594acf374c3d3a23f087cfe8bdbb01c1d2341a13d241597cf6272c7"},"schema_version":"1.0","source":{"id":"2005.00175","kind":"arxiv","version":3}},"canonical_sha256":"6f50f2d272f95914f017bd09afa1eb280c18a479b14247c5008191c904f9cc91","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f50f2d272f95914f017bd09afa1eb280c18a479b14247c5008191c904f9cc91","first_computed_at":"2026-07-05T04:24:53.785996Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:24:53.785996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3ABrW0C5p8GJ9UYwHBUD9w5dsnTlVAo9HjyKoDxNfk5rcZU9frAL+mze52glyyiOHyZKfwC3yn18389XF8lQDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:24:53.786614Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.00175","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02f39e070466f163d0cab07d41b824be2929a2c8155ca5628973a70e71b42565","sha256:5bd4cb4e19a501f3e188407a83586ab2f513aa7dac35be134b0d2b9825a2ed15"],"state_sha256":"a2daa5103d3e00c316073bc744f5d4dae496ed807c355018319f23967bae4072"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tBVySOTH8j13qbo+MT3Z7qgqPhAbGJ41qqgLdGP+S0YCgFWXKGw0Y423A1C69akoBEyvqr0jZgqKAbDfgui7AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T08:04:01.662662Z","bundle_sha256":"091259d4249201cbea2e76843580b99d09bd5e652e3c1a8a5a30665d669adb11"}}