{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EKDZ6J2OCQMZHELY62LJ6Q75WS","short_pith_number":"pith:EKDZ6J2O","canonical_record":{"source":{"id":"2311.05754","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-09T21:43:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b1e6a9c70029f88d72a6f72e123946d259e22293952a81bed0da317e96c6853d","abstract_canon_sha256":"3358459d719f2eae450977a67fe67a61f4aa9f1a1a61ff88b9f2ebac406b11f4"},"schema_version":"1.0"},"canonical_sha256":"22879f274e1419939178f6969f43fdb4bbced64b433438e0f17f0ab7cae4bdbf","source":{"kind":"arxiv","id":"2311.05754","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.05754","created_at":"2026-07-05T07:40:03Z"},{"alias_kind":"arxiv_version","alias_value":"2311.05754v1","created_at":"2026-07-05T07:40:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05754","created_at":"2026-07-05T07:40:03Z"},{"alias_kind":"pith_short_12","alias_value":"EKDZ6J2OCQMZ","created_at":"2026-07-05T07:40:03Z"},{"alias_kind":"pith_short_16","alias_value":"EKDZ6J2OCQMZHELY","created_at":"2026-07-05T07:40:03Z"},{"alias_kind":"pith_short_8","alias_value":"EKDZ6J2O","created_at":"2026-07-05T07:40:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EKDZ6J2OCQMZHELY62LJ6Q75WS","target":"record","payload":{"canonical_record":{"source":{"id":"2311.05754","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-09T21:43:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b1e6a9c70029f88d72a6f72e123946d259e22293952a81bed0da317e96c6853d","abstract_canon_sha256":"3358459d719f2eae450977a67fe67a61f4aa9f1a1a61ff88b9f2ebac406b11f4"},"schema_version":"1.0"},"canonical_sha256":"22879f274e1419939178f6969f43fdb4bbced64b433438e0f17f0ab7cae4bdbf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:03.552596Z","signature_b64":"KAhdSHZxhr/8c8wHkvcS8rknq5S1+mM2FhXnhhsqp2Si6+CGV2EVERkZ/TVV0KxN7UPZRTxYxAgzxAAeOf4gAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22879f274e1419939178f6969f43fdb4bbced64b433438e0f17f0ab7cae4bdbf","last_reissued_at":"2026-07-05T07:40:03.552192Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:03.552192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.05754","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":"2026-07-05T07:40:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"blhml3hAztU8FBvUg1X+lBkDonXZGMN9qdXS+0oC5lAeMaCX3v4CvWvuoGBtK30aaJYAPeFVXZwcHRaKLkAIBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:33:42.670908Z"},"content_sha256":"d38d8d7a2625f4cc0fb3b6800817edb5fd16508d0deee739524c4ef3ee8c9633","schema_version":"1.0","event_id":"sha256:d38d8d7a2625f4cc0fb3b6800817edb5fd16508d0deee739524c4ef3ee8c9633"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EKDZ6J2OCQMZHELY62LJ6Q75WS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Natural Language Feature Learning for Interpretable Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Cristian Buc, Felipe Urrutia, Valentin Barriere","submitted_at":"2023-11-09T21:43:27Z","abstract_excerpt":"We propose a general method to break down a main complex task into a set of intermediary easier sub-tasks, which are formulated in natural language as binary questions related to the final target task. Our method allows for representing each example by a vector consisting of the answers to these questions. We call this representation Natural Language Learned Features (NLLF). NLLF is generated by a small transformer language model (e.g., BERT) that has been trained in a Natural Language Inference (NLI) fashion, using weak labels automatically obtained from a Large Language Model (LLM). We show "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05754","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/2311.05754/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":"2026-07-05T07:40:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VbSjkHEgjpseXEGBeNRousvUophzZVNR3oSdWiaNYbE8bQ4RxemX3OKbeGFggKE/tY2IBYespd/6GqGXOEK6AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:33:42.672226Z"},"content_sha256":"8e41f2e4b48e652949bdf686640b38a58fce3b082716017c1746bda7bcea8604","schema_version":"1.0","event_id":"sha256:8e41f2e4b48e652949bdf686640b38a58fce3b082716017c1746bda7bcea8604"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EKDZ6J2OCQMZHELY62LJ6Q75WS/bundle.json","state_url":"https://pith.science/pith/EKDZ6J2OCQMZHELY62LJ6Q75WS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EKDZ6J2OCQMZHELY62LJ6Q75WS/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":"2026-08-14T08:33:42Z","links":{"resolver":"https://pith.science/pith/EKDZ6J2OCQMZHELY62LJ6Q75WS","bundle":"https://pith.science/pith/EKDZ6J2OCQMZHELY62LJ6Q75WS/bundle.json","state":"https://pith.science/pith/EKDZ6J2OCQMZHELY62LJ6Q75WS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EKDZ6J2OCQMZHELY62LJ6Q75WS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EKDZ6J2OCQMZHELY62LJ6Q75WS","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":"3358459d719f2eae450977a67fe67a61f4aa9f1a1a61ff88b9f2ebac406b11f4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-09T21:43:27Z","title_canon_sha256":"b1e6a9c70029f88d72a6f72e123946d259e22293952a81bed0da317e96c6853d"},"schema_version":"1.0","source":{"id":"2311.05754","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.05754","created_at":"2026-07-05T07:40:03Z"},{"alias_kind":"arxiv_version","alias_value":"2311.05754v1","created_at":"2026-07-05T07:40:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05754","created_at":"2026-07-05T07:40:03Z"},{"alias_kind":"pith_short_12","alias_value":"EKDZ6J2OCQMZ","created_at":"2026-07-05T07:40:03Z"},{"alias_kind":"pith_short_16","alias_value":"EKDZ6J2OCQMZHELY","created_at":"2026-07-05T07:40:03Z"},{"alias_kind":"pith_short_8","alias_value":"EKDZ6J2O","created_at":"2026-07-05T07:40:03Z"}],"graph_snapshots":[{"event_id":"sha256:8e41f2e4b48e652949bdf686640b38a58fce3b082716017c1746bda7bcea8604","target":"graph","created_at":"2026-07-05T07:40:03Z","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/2311.05754/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a general method to break down a main complex task into a set of intermediary easier sub-tasks, which are formulated in natural language as binary questions related to the final target task. Our method allows for representing each example by a vector consisting of the answers to these questions. We call this representation Natural Language Learned Features (NLLF). NLLF is generated by a small transformer language model (e.g., BERT) that has been trained in a Natural Language Inference (NLI) fashion, using weak labels automatically obtained from a Large Language Model (LLM). We show ","authors_text":"Cristian Buc, Felipe Urrutia, Valentin Barriere","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-09T21:43:27Z","title":"Deep Natural Language Feature Learning for Interpretable Prediction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05754","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:d38d8d7a2625f4cc0fb3b6800817edb5fd16508d0deee739524c4ef3ee8c9633","target":"record","created_at":"2026-07-05T07:40:03Z","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":"3358459d719f2eae450977a67fe67a61f4aa9f1a1a61ff88b9f2ebac406b11f4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-09T21:43:27Z","title_canon_sha256":"b1e6a9c70029f88d72a6f72e123946d259e22293952a81bed0da317e96c6853d"},"schema_version":"1.0","source":{"id":"2311.05754","kind":"arxiv","version":1}},"canonical_sha256":"22879f274e1419939178f6969f43fdb4bbced64b433438e0f17f0ab7cae4bdbf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"22879f274e1419939178f6969f43fdb4bbced64b433438e0f17f0ab7cae4bdbf","first_computed_at":"2026-07-05T07:40:03.552192Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:40:03.552192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KAhdSHZxhr/8c8wHkvcS8rknq5S1+mM2FhXnhhsqp2Si6+CGV2EVERkZ/TVV0KxN7UPZRTxYxAgzxAAeOf4gAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:40:03.552596Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.05754","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d38d8d7a2625f4cc0fb3b6800817edb5fd16508d0deee739524c4ef3ee8c9633","sha256:8e41f2e4b48e652949bdf686640b38a58fce3b082716017c1746bda7bcea8604"],"state_sha256":"02e1b95131a1ae3c53ab25b679aae341ba3c559ec177c32df350a537586076ff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MFN4S7GJt+Ipb4lWWOF4K2N2bpqB0aQWLWYGfYGURGFK84bQ+XGWY7BAzG764euYcf2EyD8uut2NeIRy8+9/Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T08:33:42.679971Z","bundle_sha256":"0fdbf74d668febb4563cc83255fadd21423622e6a6767f7535d5f139086daa95"}}