{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:7GWVWHM6QQCGREQNM3HSOT6XZG","short_pith_number":"pith:7GWVWHM6","canonical_record":{"source":{"id":"2210.17301","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-31T13:26:08Z","cross_cats_sorted":[],"title_canon_sha256":"21fc6c77d20edc0f29e84f26f95cab502f5704547317c8fb82e58a5d5028ae10","abstract_canon_sha256":"600e28877053fce3f44ca1484cc005af0b6bff9d88be0a64155ef6b22cbb1ac3"},"schema_version":"1.0"},"canonical_sha256":"f9ad5b1d9e840468920d66cf274fd7c9836fec7b471ac432ba774e50f424bb50","source":{"kind":"arxiv","id":"2210.17301","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.17301","created_at":"2026-07-05T05:11:56Z"},{"alias_kind":"arxiv_version","alias_value":"2210.17301v1","created_at":"2026-07-05T05:11:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.17301","created_at":"2026-07-05T05:11:56Z"},{"alias_kind":"pith_short_12","alias_value":"7GWVWHM6QQCG","created_at":"2026-07-05T05:11:56Z"},{"alias_kind":"pith_short_16","alias_value":"7GWVWHM6QQCGREQN","created_at":"2026-07-05T05:11:56Z"},{"alias_kind":"pith_short_8","alias_value":"7GWVWHM6","created_at":"2026-07-05T05:11:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:7GWVWHM6QQCGREQNM3HSOT6XZG","target":"record","payload":{"canonical_record":{"source":{"id":"2210.17301","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-31T13:26:08Z","cross_cats_sorted":[],"title_canon_sha256":"21fc6c77d20edc0f29e84f26f95cab502f5704547317c8fb82e58a5d5028ae10","abstract_canon_sha256":"600e28877053fce3f44ca1484cc005af0b6bff9d88be0a64155ef6b22cbb1ac3"},"schema_version":"1.0"},"canonical_sha256":"f9ad5b1d9e840468920d66cf274fd7c9836fec7b471ac432ba774e50f424bb50","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:56.879420Z","signature_b64":"u/OOhYOziM3ZpZmR6S0WWi6oOqPvH1LlgVI5pWiqLdkA/t9QsYXIumcUEThzPk8+2NxAI8S1/Lgyk5ZVgYFsAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9ad5b1d9e840468920d66cf274fd7c9836fec7b471ac432ba774e50f424bb50","last_reissued_at":"2026-07-05T05:11:56.878907Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:56.878907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.17301","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":"2026-07-05T05:11:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jMm5uiDB88Vxx2gMqHPlEJ883oSjxbUTVseTaMtwj/B1u00ONLVhVlUOx3LyfxkjI96QYYAnC/TZ687sE7m3CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:36:57.689187Z"},"content_sha256":"e7c88017c037652192942934a170b8e33088c592c76547fc0bc798a3e10a2089","schema_version":"1.0","event_id":"sha256:e7c88017c037652192942934a170b8e33088c592c76547fc0bc798a3e10a2089"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:7GWVWHM6QQCGREQNM3HSOT6XZG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Effective Cross-Task Transfer Learning for Explainable Natural Language Inference with T5","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aline Villavicencio, Harish Tayyar Madabushi, Irina Bigoulaeva, Iryna Gurevych, Rachneet Sachdeva","submitted_at":"2022-10-31T13:26:08Z","abstract_excerpt":"We compare sequential fine-tuning with a model for multi-task learning in the context where we are interested in boosting performance on two tasks, one of which depends on the other. We test these models on the FigLang2022 shared task which requires participants to predict language inference labels on figurative language along with corresponding textual explanations of the inference predictions. Our results show that while sequential multi-task learning can be tuned to be good at the first of two target tasks, it performs less well on the second and additionally struggles with overfitting. Our"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.17301","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/2210.17301/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":"2026-07-05T05:11:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BPXSdjmxeOsiL7LwoMEk4uQq7j+rvL43HJOw8Zt2k+lVFd6kHMequNEoaMRpzqHJiUEaB1617YIjzpnwScHgDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:36:57.689779Z"},"content_sha256":"f91dc4adde1bd85e688bba563917f6d036b77484ee0d394c30a703f4e750d4ee","schema_version":"1.0","event_id":"sha256:f91dc4adde1bd85e688bba563917f6d036b77484ee0d394c30a703f4e750d4ee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7GWVWHM6QQCGREQNM3HSOT6XZG/bundle.json","state_url":"https://pith.science/pith/7GWVWHM6QQCGREQNM3HSOT6XZG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7GWVWHM6QQCGREQNM3HSOT6XZG/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":"2026-08-11T19:36:57Z","links":{"resolver":"https://pith.science/pith/7GWVWHM6QQCGREQNM3HSOT6XZG","bundle":"https://pith.science/pith/7GWVWHM6QQCGREQNM3HSOT6XZG/bundle.json","state":"https://pith.science/pith/7GWVWHM6QQCGREQNM3HSOT6XZG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7GWVWHM6QQCGREQNM3HSOT6XZG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:7GWVWHM6QQCGREQNM3HSOT6XZG","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":"600e28877053fce3f44ca1484cc005af0b6bff9d88be0a64155ef6b22cbb1ac3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-31T13:26:08Z","title_canon_sha256":"21fc6c77d20edc0f29e84f26f95cab502f5704547317c8fb82e58a5d5028ae10"},"schema_version":"1.0","source":{"id":"2210.17301","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.17301","created_at":"2026-07-05T05:11:56Z"},{"alias_kind":"arxiv_version","alias_value":"2210.17301v1","created_at":"2026-07-05T05:11:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.17301","created_at":"2026-07-05T05:11:56Z"},{"alias_kind":"pith_short_12","alias_value":"7GWVWHM6QQCG","created_at":"2026-07-05T05:11:56Z"},{"alias_kind":"pith_short_16","alias_value":"7GWVWHM6QQCGREQN","created_at":"2026-07-05T05:11:56Z"},{"alias_kind":"pith_short_8","alias_value":"7GWVWHM6","created_at":"2026-07-05T05:11:56Z"}],"graph_snapshots":[{"event_id":"sha256:f91dc4adde1bd85e688bba563917f6d036b77484ee0d394c30a703f4e750d4ee","target":"graph","created_at":"2026-07-05T05:11:56Z","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/2210.17301/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We compare sequential fine-tuning with a model for multi-task learning in the context where we are interested in boosting performance on two tasks, one of which depends on the other. We test these models on the FigLang2022 shared task which requires participants to predict language inference labels on figurative language along with corresponding textual explanations of the inference predictions. Our results show that while sequential multi-task learning can be tuned to be good at the first of two target tasks, it performs less well on the second and additionally struggles with overfitting. Our","authors_text":"Aline Villavicencio, Harish Tayyar Madabushi, Irina Bigoulaeva, Iryna Gurevych, Rachneet Sachdeva","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-31T13:26:08Z","title":"Effective Cross-Task Transfer Learning for Explainable Natural Language Inference with T5"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.17301","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:e7c88017c037652192942934a170b8e33088c592c76547fc0bc798a3e10a2089","target":"record","created_at":"2026-07-05T05:11:56Z","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":"600e28877053fce3f44ca1484cc005af0b6bff9d88be0a64155ef6b22cbb1ac3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-31T13:26:08Z","title_canon_sha256":"21fc6c77d20edc0f29e84f26f95cab502f5704547317c8fb82e58a5d5028ae10"},"schema_version":"1.0","source":{"id":"2210.17301","kind":"arxiv","version":1}},"canonical_sha256":"f9ad5b1d9e840468920d66cf274fd7c9836fec7b471ac432ba774e50f424bb50","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9ad5b1d9e840468920d66cf274fd7c9836fec7b471ac432ba774e50f424bb50","first_computed_at":"2026-07-05T05:11:56.878907Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:11:56.878907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u/OOhYOziM3ZpZmR6S0WWi6oOqPvH1LlgVI5pWiqLdkA/t9QsYXIumcUEThzPk8+2NxAI8S1/Lgyk5ZVgYFsAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:11:56.879420Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.17301","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7c88017c037652192942934a170b8e33088c592c76547fc0bc798a3e10a2089","sha256:f91dc4adde1bd85e688bba563917f6d036b77484ee0d394c30a703f4e750d4ee"],"state_sha256":"c96a4f1cadd73a821738b0db3ede9ef4a3b2ea04b051a7d0b73b1fca408cf74d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hRjiXhSwTQS4hQRbM5Dzi1rTtgKgIaUMXAfuuPTx416TWPvap3F5CJCq2WbQv1K+pgtIKwrY8zAOcbASBv1dDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T19:36:57.695183Z","bundle_sha256":"f2295102ff73c9638458520b8d7a9c2a405ff5226c98edbccc9ef9abb09a335e"}}