{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:FMRLLYBNMRTPFPAPGHBF7QKILB","short_pith_number":"pith:FMRLLYBN","canonical_record":{"source":{"id":"2111.08284","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-16T08:21:40Z","cross_cats_sorted":[],"title_canon_sha256":"1d2fef7d4d37354f5f91c9ae00c75ac1004f77a835cf5574a69f699867013c7d","abstract_canon_sha256":"ecb3a7f073a9c1bb7358393cf7d72a8b085aeb170d344cbf0ee2abf40e835c9f"},"schema_version":"1.0"},"canonical_sha256":"2b22b5e02d6466f2bc0f31c25fc148584fda8e5fd32ae3e585187a57cba01add","source":{"kind":"arxiv","id":"2111.08284","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.08284","created_at":"2026-07-05T04:17:37Z"},{"alias_kind":"arxiv_version","alias_value":"2111.08284v2","created_at":"2026-07-05T04:17:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.08284","created_at":"2026-07-05T04:17:37Z"},{"alias_kind":"pith_short_12","alias_value":"FMRLLYBNMRTP","created_at":"2026-07-05T04:17:37Z"},{"alias_kind":"pith_short_16","alias_value":"FMRLLYBNMRTPFPAP","created_at":"2026-07-05T04:17:37Z"},{"alias_kind":"pith_short_8","alias_value":"FMRLLYBN","created_at":"2026-07-05T04:17:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:FMRLLYBNMRTPFPAPGHBF7QKILB","target":"record","payload":{"canonical_record":{"source":{"id":"2111.08284","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-16T08:21:40Z","cross_cats_sorted":[],"title_canon_sha256":"1d2fef7d4d37354f5f91c9ae00c75ac1004f77a835cf5574a69f699867013c7d","abstract_canon_sha256":"ecb3a7f073a9c1bb7358393cf7d72a8b085aeb170d344cbf0ee2abf40e835c9f"},"schema_version":"1.0"},"canonical_sha256":"2b22b5e02d6466f2bc0f31c25fc148584fda8e5fd32ae3e585187a57cba01add","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:17:37.409339Z","signature_b64":"E2DsfM4gcmz53IWT/62KOqchiykQRE31ehgmr2D9WdaT7amf8UHiWRjR4pAdxnnLcHevnLIE6SahexmUiNz8DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b22b5e02d6466f2bc0f31c25fc148584fda8e5fd32ae3e585187a57cba01add","last_reissued_at":"2026-07-05T04:17:37.408814Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:17:37.408814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.08284","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:17:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q6BfEz0ofJdKCVz3lkhboXBIE+45w9IUclDMA/iP6K+l4J6sjZiesTjiAJoi/inUWe8Uh6m6UE4MHPF8pQQODw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:37:55.109023Z"},"content_sha256":"4140d010085c929887558e9d42fe4d631bfac9bd119f378ce00227c6e86ce2a2","schema_version":"1.0","event_id":"sha256:4140d010085c929887558e9d42fe4d631bfac9bd119f378ce00227c6e86ce2a2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:FMRLLYBNMRTPFPAPGHBF7QKILB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Few-Shot Self-Rationalization with Natural Language Prompts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ana Marasovi\\'c, Doug Downey, Iz Beltagy, Matthew E. Peters","submitted_at":"2021-11-16T08:21:40Z","abstract_excerpt":"Self-rationalization models that predict task labels and generate free-text elaborations for their predictions could enable more intuitive interaction with NLP systems. These models are, however, currently trained with a large amount of human-written free-text explanations for each task which hinders their broader usage. We propose to study a more realistic setting of self-rationalization using few training examples. We present FEB -- a standardized collection of four existing English-language datasets and associated metrics. We identify the right prompting approach by extensively exploring na"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.08284","kind":"arxiv","version":2},"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/2111.08284/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":"2026-07-05T04:17:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PPGeHXmeHyH5h1BAgdUpRTwy959xbaIOJQlSPMyzsyWW2pC+fTSmnN3xSKTAllQ1B2azUh+/tCCNbIkb3ky3Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T09:37:55.109403Z"},"content_sha256":"c3dfc73f2dd771a4b6b243aa28b693598cced40afdf6143e6b6fa511e7d67836","schema_version":"1.0","event_id":"sha256:c3dfc73f2dd771a4b6b243aa28b693598cced40afdf6143e6b6fa511e7d67836"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FMRLLYBNMRTPFPAPGHBF7QKILB/bundle.json","state_url":"https://pith.science/pith/FMRLLYBNMRTPFPAPGHBF7QKILB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FMRLLYBNMRTPFPAPGHBF7QKILB/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":"2026-07-07T09:37:55Z","links":{"resolver":"https://pith.science/pith/FMRLLYBNMRTPFPAPGHBF7QKILB","bundle":"https://pith.science/pith/FMRLLYBNMRTPFPAPGHBF7QKILB/bundle.json","state":"https://pith.science/pith/FMRLLYBNMRTPFPAPGHBF7QKILB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FMRLLYBNMRTPFPAPGHBF7QKILB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FMRLLYBNMRTPFPAPGHBF7QKILB","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":"ecb3a7f073a9c1bb7358393cf7d72a8b085aeb170d344cbf0ee2abf40e835c9f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-16T08:21:40Z","title_canon_sha256":"1d2fef7d4d37354f5f91c9ae00c75ac1004f77a835cf5574a69f699867013c7d"},"schema_version":"1.0","source":{"id":"2111.08284","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.08284","created_at":"2026-07-05T04:17:37Z"},{"alias_kind":"arxiv_version","alias_value":"2111.08284v2","created_at":"2026-07-05T04:17:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.08284","created_at":"2026-07-05T04:17:37Z"},{"alias_kind":"pith_short_12","alias_value":"FMRLLYBNMRTP","created_at":"2026-07-05T04:17:37Z"},{"alias_kind":"pith_short_16","alias_value":"FMRLLYBNMRTPFPAP","created_at":"2026-07-05T04:17:37Z"},{"alias_kind":"pith_short_8","alias_value":"FMRLLYBN","created_at":"2026-07-05T04:17:37Z"}],"graph_snapshots":[{"event_id":"sha256:c3dfc73f2dd771a4b6b243aa28b693598cced40afdf6143e6b6fa511e7d67836","target":"graph","created_at":"2026-07-05T04:17:37Z","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/2111.08284/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-rationalization models that predict task labels and generate free-text elaborations for their predictions could enable more intuitive interaction with NLP systems. These models are, however, currently trained with a large amount of human-written free-text explanations for each task which hinders their broader usage. We propose to study a more realistic setting of self-rationalization using few training examples. We present FEB -- a standardized collection of four existing English-language datasets and associated metrics. We identify the right prompting approach by extensively exploring na","authors_text":"Ana Marasovi\\'c, Doug Downey, Iz Beltagy, Matthew E. Peters","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-16T08:21:40Z","title":"Few-Shot Self-Rationalization with Natural Language Prompts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.08284","kind":"arxiv","version":2},"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":"sha256:4140d010085c929887558e9d42fe4d631bfac9bd119f378ce00227c6e86ce2a2","target":"record","created_at":"2026-07-05T04:17:37Z","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":"ecb3a7f073a9c1bb7358393cf7d72a8b085aeb170d344cbf0ee2abf40e835c9f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-11-16T08:21:40Z","title_canon_sha256":"1d2fef7d4d37354f5f91c9ae00c75ac1004f77a835cf5574a69f699867013c7d"},"schema_version":"1.0","source":{"id":"2111.08284","kind":"arxiv","version":2}},"canonical_sha256":"2b22b5e02d6466f2bc0f31c25fc148584fda8e5fd32ae3e585187a57cba01add","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b22b5e02d6466f2bc0f31c25fc148584fda8e5fd32ae3e585187a57cba01add","first_computed_at":"2026-07-05T04:17:37.408814Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:17:37.408814Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E2DsfM4gcmz53IWT/62KOqchiykQRE31ehgmr2D9WdaT7amf8UHiWRjR4pAdxnnLcHevnLIE6SahexmUiNz8DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:17:37.409339Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.08284","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4140d010085c929887558e9d42fe4d631bfac9bd119f378ce00227c6e86ce2a2","sha256:c3dfc73f2dd771a4b6b243aa28b693598cced40afdf6143e6b6fa511e7d67836"],"state_sha256":"5193fd0083fabcb7833574764f7123d7db3b172e7899259505c4a32d4d32cea8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M4vLB6gR0X9CijrvI+mHtkBSgRxAI7D0DDcJ0PFyNufA83zXr5R1vL699i9yC2MkOGDcYCWotJHgrKidzEFqDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T09:37:55.111282Z","bundle_sha256":"74d2a34dce435a72ddee1495d8d86f0d1d2ec23b341c288fb8e3fcb9a1264ff8"}}