{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:BC4HNQJAE7D2XTOCGPT735FYDK","short_pith_number":"pith:BC4HNQJA","canonical_record":{"source":{"id":"2109.01951","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-04T23:08:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"531c1036af05ac5b0e2c1a0fd6f34c4a27966168586154892f1fa3e7b1dbcb6b","abstract_canon_sha256":"0b5e017f3645a7447b5901548c0b80583486eddb71071fd0a9dd36e544541762"},"schema_version":"1.0"},"canonical_sha256":"08b876c12027c7abcdc233e7fdf4b81ab88236b174b266c87595e0f77f649626","source":{"kind":"arxiv","id":"2109.01951","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.01951","created_at":"2026-07-05T03:21:59Z"},{"alias_kind":"arxiv_version","alias_value":"2109.01951v3","created_at":"2026-07-05T03:21:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.01951","created_at":"2026-07-05T03:21:59Z"},{"alias_kind":"pith_short_12","alias_value":"BC4HNQJAE7D2","created_at":"2026-07-05T03:21:59Z"},{"alias_kind":"pith_short_16","alias_value":"BC4HNQJAE7D2XTOC","created_at":"2026-07-05T03:21:59Z"},{"alias_kind":"pith_short_8","alias_value":"BC4HNQJA","created_at":"2026-07-05T03:21:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:BC4HNQJAE7D2XTOCGPT735FYDK","target":"record","payload":{"canonical_record":{"source":{"id":"2109.01951","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-04T23:08:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"531c1036af05ac5b0e2c1a0fd6f34c4a27966168586154892f1fa3e7b1dbcb6b","abstract_canon_sha256":"0b5e017f3645a7447b5901548c0b80583486eddb71071fd0a9dd36e544541762"},"schema_version":"1.0"},"canonical_sha256":"08b876c12027c7abcdc233e7fdf4b81ab88236b174b266c87595e0f77f649626","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:21:59.382541Z","signature_b64":"7JLI3QfhcdBCmkX4Oan4fjhSfTZdEOLn0B0OBU8z3fpPBVuvw1St0sfbp6169va1cRhrfrhYus1MM3twSW9/Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08b876c12027c7abcdc233e7fdf4b81ab88236b174b266c87595e0f77f649626","last_reissued_at":"2026-07-05T03:21:59.382008Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:21:59.382008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.01951","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":"2026-07-05T03:21:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hAuCznWMXZp4CedugWZvOZ0QRYbvY6nS9IUulf43dcUtPPwE9xKO/4sJ73dUgNDuSTGiT8rADthH1lg02cnFBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:19:51.140670Z"},"content_sha256":"b691c352cc35213e1198aef0bfb79dcecc1f84f36834ec6f05c88cf7477867ad","schema_version":"1.0","event_id":"sha256:b691c352cc35213e1198aef0bfb79dcecc1f84f36834ec6f05c88cf7477867ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:BC4HNQJAE7D2XTOCGPT735FYDK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FewshotQA: A simple framework for few-shot learning of question answering tasks using pre-trained text-to-text models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Pradeep Natarajan, Rakesh Chada","submitted_at":"2021-09-04T23:08:57Z","abstract_excerpt":"The task of learning from only a few examples (called a few-shot setting) is of key importance and relevance to a real-world setting. For question answering (QA), the current state-of-the-art pre-trained models typically need fine-tuning on tens of thousands of examples to obtain good results. Their performance degrades significantly in a few-shot setting (< 100 examples). To address this, we propose a simple fine-tuning framework that leverages pre-trained text-to-text models and is directly aligned with their pre-training framework. Specifically, we construct the input as a concatenation of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.01951","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/2109.01951/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":"2026-07-05T03:21:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ddq9CjXxyNJG+Hu8AX8r25sgnmhjX3m806DKXa9TN7b9/sU09INGrohb3dHpKOhFKCJGWKP6j/i88kzaS1ZaCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:19:51.141057Z"},"content_sha256":"c61eecdae589c67b79f3224551529c9d6fd3a073b7177d8ba9d65f6a63f844f9","schema_version":"1.0","event_id":"sha256:c61eecdae589c67b79f3224551529c9d6fd3a073b7177d8ba9d65f6a63f844f9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BC4HNQJAE7D2XTOCGPT735FYDK/bundle.json","state_url":"https://pith.science/pith/BC4HNQJAE7D2XTOCGPT735FYDK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BC4HNQJAE7D2XTOCGPT735FYDK/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":"2026-07-06T23:19:51Z","links":{"resolver":"https://pith.science/pith/BC4HNQJAE7D2XTOCGPT735FYDK","bundle":"https://pith.science/pith/BC4HNQJAE7D2XTOCGPT735FYDK/bundle.json","state":"https://pith.science/pith/BC4HNQJAE7D2XTOCGPT735FYDK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BC4HNQJAE7D2XTOCGPT735FYDK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:BC4HNQJAE7D2XTOCGPT735FYDK","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":"0b5e017f3645a7447b5901548c0b80583486eddb71071fd0a9dd36e544541762","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-04T23:08:57Z","title_canon_sha256":"531c1036af05ac5b0e2c1a0fd6f34c4a27966168586154892f1fa3e7b1dbcb6b"},"schema_version":"1.0","source":{"id":"2109.01951","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.01951","created_at":"2026-07-05T03:21:59Z"},{"alias_kind":"arxiv_version","alias_value":"2109.01951v3","created_at":"2026-07-05T03:21:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.01951","created_at":"2026-07-05T03:21:59Z"},{"alias_kind":"pith_short_12","alias_value":"BC4HNQJAE7D2","created_at":"2026-07-05T03:21:59Z"},{"alias_kind":"pith_short_16","alias_value":"BC4HNQJAE7D2XTOC","created_at":"2026-07-05T03:21:59Z"},{"alias_kind":"pith_short_8","alias_value":"BC4HNQJA","created_at":"2026-07-05T03:21:59Z"}],"graph_snapshots":[{"event_id":"sha256:c61eecdae589c67b79f3224551529c9d6fd3a073b7177d8ba9d65f6a63f844f9","target":"graph","created_at":"2026-07-05T03:21:59Z","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/2109.01951/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The task of learning from only a few examples (called a few-shot setting) is of key importance and relevance to a real-world setting. For question answering (QA), the current state-of-the-art pre-trained models typically need fine-tuning on tens of thousands of examples to obtain good results. Their performance degrades significantly in a few-shot setting (< 100 examples). To address this, we propose a simple fine-tuning framework that leverages pre-trained text-to-text models and is directly aligned with their pre-training framework. Specifically, we construct the input as a concatenation of ","authors_text":"Pradeep Natarajan, Rakesh Chada","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-04T23:08:57Z","title":"FewshotQA: A simple framework for few-shot learning of question answering tasks using pre-trained text-to-text models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.01951","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:b691c352cc35213e1198aef0bfb79dcecc1f84f36834ec6f05c88cf7477867ad","target":"record","created_at":"2026-07-05T03:21:59Z","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":"0b5e017f3645a7447b5901548c0b80583486eddb71071fd0a9dd36e544541762","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-04T23:08:57Z","title_canon_sha256":"531c1036af05ac5b0e2c1a0fd6f34c4a27966168586154892f1fa3e7b1dbcb6b"},"schema_version":"1.0","source":{"id":"2109.01951","kind":"arxiv","version":3}},"canonical_sha256":"08b876c12027c7abcdc233e7fdf4b81ab88236b174b266c87595e0f77f649626","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08b876c12027c7abcdc233e7fdf4b81ab88236b174b266c87595e0f77f649626","first_computed_at":"2026-07-05T03:21:59.382008Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:21:59.382008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7JLI3QfhcdBCmkX4Oan4fjhSfTZdEOLn0B0OBU8z3fpPBVuvw1St0sfbp6169va1cRhrfrhYus1MM3twSW9/Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:21:59.382541Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.01951","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b691c352cc35213e1198aef0bfb79dcecc1f84f36834ec6f05c88cf7477867ad","sha256:c61eecdae589c67b79f3224551529c9d6fd3a073b7177d8ba9d65f6a63f844f9"],"state_sha256":"d6c6fed65263f6bcc7905939bfe5f4c69b2cfdc26c3f008acd08d71c6c93291d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/cG3bTSRSUA5kBqyuE3I0bd0PC7Rwh5m188N2KuqF0jfdahM+QxZdKQhawcbGjg8JJdC3GteoRVGJtUcC1TiBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:19:51.143072Z","bundle_sha256":"34f30c9587c722794f0e4797c498f7e409f7bd42438c9cd6fa7a6c75ae0d71be"}}