{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:D5CVWIBIB4ADXSYR3MUQM4CPME","short_pith_number":"pith:D5CVWIBI","schema_version":"1.0","canonical_sha256":"1f455b20280f003bcb11db2906704f613b6e553b1535b3ab4bffa2b90d02b191","source":{"kind":"arxiv","id":"2212.04231","version":2},"attestation_state":"computed","paper":{"title":"Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bj\\\"orn Pl\\\"uster, Jae Hee Lee, Jakob Ambsdorf, Lukas Braach, Stefan Wermter","submitted_at":"2022-12-08T12:28:23Z","abstract_excerpt":"Natural language explanations promise to offer intuitively understandable explanations of a neural network's decision process in complex vision-language tasks, as pursued in recent VL-NLE models. While current models offer impressive performance on task accuracy and explanation plausibility, they suffer from a range of issues: Some models feature a modular design where the explanation generation module is poorly integrated with a separate module for task-answer prediction, employ backbone models trained on limited sets of tasks, or incorporate ad hoc solutions to increase performance on single"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2212.04231","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-08T12:28:23Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"e665a2d5be5db1873db367508aa21109340d4d4628d6da2aaff3bdda01a4f933","abstract_canon_sha256":"f84b61bd4c28263c86c957b48f90a62750a43688d1d7f699a735d2b01c6a572f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:56:01.796199Z","signature_b64":"Cbf2dwEwThH53Ddeu9dlCOrTTRD4j9XGDd5dmqrV2mmF6Dp3Wiul9XL1kDJhDyOx0zdoy95bkK11aX54Z9BIDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f455b20280f003bcb11db2906704f613b6e553b1535b3ab4bffa2b90d02b191","last_reissued_at":"2026-07-05T05:56:01.795790Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:56:01.795790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bj\\\"orn Pl\\\"uster, Jae Hee Lee, Jakob Ambsdorf, Lukas Braach, Stefan Wermter","submitted_at":"2022-12-08T12:28:23Z","abstract_excerpt":"Natural language explanations promise to offer intuitively understandable explanations of a neural network's decision process in complex vision-language tasks, as pursued in recent VL-NLE models. While current models offer impressive performance on task accuracy and explanation plausibility, they suffer from a range of issues: Some models feature a modular design where the explanation generation module is poorly integrated with a separate module for task-answer prediction, employ backbone models trained on limited sets of tasks, or incorporate ad hoc solutions to increase performance on single"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.04231","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/2212.04231/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2212.04231","created_at":"2026-07-05T05:56:01.795850+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.04231v2","created_at":"2026-07-05T05:56:01.795850+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.04231","created_at":"2026-07-05T05:56:01.795850+00:00"},{"alias_kind":"pith_short_12","alias_value":"D5CVWIBIB4AD","created_at":"2026-07-05T05:56:01.795850+00:00"},{"alias_kind":"pith_short_16","alias_value":"D5CVWIBIB4ADXSYR","created_at":"2026-07-05T05:56:01.795850+00:00"},{"alias_kind":"pith_short_8","alias_value":"D5CVWIBI","created_at":"2026-07-05T05:56:01.795850+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.17467","citing_title":"Probing Vision-Language Understanding through the Visual Entailment Task: promises and pitfalls","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D5CVWIBIB4ADXSYR3MUQM4CPME","json":"https://pith.science/pith/D5CVWIBIB4ADXSYR3MUQM4CPME.json","graph_json":"https://pith.science/api/pith-number/D5CVWIBIB4ADXSYR3MUQM4CPME/graph.json","events_json":"https://pith.science/api/pith-number/D5CVWIBIB4ADXSYR3MUQM4CPME/events.json","paper":"https://pith.science/paper/D5CVWIBI"},"agent_actions":{"view_html":"https://pith.science/pith/D5CVWIBIB4ADXSYR3MUQM4CPME","download_json":"https://pith.science/pith/D5CVWIBIB4ADXSYR3MUQM4CPME.json","view_paper":"https://pith.science/paper/D5CVWIBI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.04231&json=true","fetch_graph":"https://pith.science/api/pith-number/D5CVWIBIB4ADXSYR3MUQM4CPME/graph.json","fetch_events":"https://pith.science/api/pith-number/D5CVWIBIB4ADXSYR3MUQM4CPME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D5CVWIBIB4ADXSYR3MUQM4CPME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D5CVWIBIB4ADXSYR3MUQM4CPME/action/storage_attestation","attest_author":"https://pith.science/pith/D5CVWIBIB4ADXSYR3MUQM4CPME/action/author_attestation","sign_citation":"https://pith.science/pith/D5CVWIBIB4ADXSYR3MUQM4CPME/action/citation_signature","submit_replication":"https://pith.science/pith/D5CVWIBIB4ADXSYR3MUQM4CPME/action/replication_record"}},"created_at":"2026-07-05T05:56:01.795850+00:00","updated_at":"2026-07-05T05:56:01.795850+00:00"}