{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:GIVNG4DVCOIMVLDWWUCB7SKJW6","short_pith_number":"pith:GIVNG4DV","canonical_record":{"source":{"id":"2308.08234","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-16T09:11:00Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"49a2d7f15c223461d08007cbe0884cfd92ce73aa2b63e0f67f1da01dd5d788cd","abstract_canon_sha256":"e47a807be64744802bbd182aea804770d93e9c35a991b5b4427f3120194ce912"},"schema_version":"1.0"},"canonical_sha256":"322ad370751390caac76b5041fc949b7b5086c011b0e99bc6714e4a6cc8d1e91","source":{"kind":"arxiv","id":"2308.08234","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.08234","created_at":"2026-07-05T06:41:56Z"},{"alias_kind":"arxiv_version","alias_value":"2308.08234v1","created_at":"2026-07-05T06:41:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.08234","created_at":"2026-07-05T06:41:56Z"},{"alias_kind":"pith_short_12","alias_value":"GIVNG4DVCOIM","created_at":"2026-07-05T06:41:56Z"},{"alias_kind":"pith_short_16","alias_value":"GIVNG4DVCOIMVLDW","created_at":"2026-07-05T06:41:56Z"},{"alias_kind":"pith_short_8","alias_value":"GIVNG4DV","created_at":"2026-07-05T06:41:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:GIVNG4DVCOIMVLDWWUCB7SKJW6","target":"record","payload":{"canonical_record":{"source":{"id":"2308.08234","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-16T09:11:00Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"49a2d7f15c223461d08007cbe0884cfd92ce73aa2b63e0f67f1da01dd5d788cd","abstract_canon_sha256":"e47a807be64744802bbd182aea804770d93e9c35a991b5b4427f3120194ce912"},"schema_version":"1.0"},"canonical_sha256":"322ad370751390caac76b5041fc949b7b5086c011b0e99bc6714e4a6cc8d1e91","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:41:56.574188Z","signature_b64":"nGQN+Gh+Vd/4xQD2C1jC7uxWGA8g2MzS25jSV4N8ajtICb40zuypAH7iP0HPBWwO7Ky7gojIe9C1TA5RLXDgDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"322ad370751390caac76b5041fc949b7b5086c011b0e99bc6714e4a6cc8d1e91","last_reissued_at":"2026-07-05T06:41:56.573770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:41:56.573770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.08234","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":"2026-07-05T06:41:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NJTMXMUKpRAtrEHIgnDyR7q0opoDcnlhFoh/bwwFdOXJnkI5WRUjGYWYhwaN364SAkb2zTCPGcqYE7jwAmPJAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:43:35.017914Z"},"content_sha256":"186339248fd78754804e00ca4fc86b6d5e3204c89f4c962e35096d55c05da1c7","schema_version":"1.0","event_id":"sha256:186339248fd78754804e00ca4fc86b6d5e3204c89f4c962e35096d55c05da1c7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:GIVNG4DVCOIMVLDWWUCB7SKJW6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Challenges and Opportunities of Using Transformer-Based Multi-Task Learning in NLP Through ML Lifecycle: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bruno Sarlija, Lovre Torbarina, Lukasz Roguski, Tin Ferkovic, Velimir Mihelcic, Zeljko Kraljevic","submitted_at":"2023-08-16T09:11:00Z","abstract_excerpt":"The increasing adoption of natural language processing (NLP) models across industries has led to practitioners' need for machine learning systems to handle these models efficiently, from training to serving them in production. However, training, deploying, and updating multiple models can be complex, costly, and time-consuming, mainly when using transformer-based pre-trained language models. Multi-Task Learning (MTL) has emerged as a promising approach to improve efficiency and performance through joint training, rather than training separate models. Motivated by this, we first provide an over"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.08234","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/2308.08234/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":"2026-07-05T06:41:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"08iMjHAnNMUAnK2MGHcwo5uMKwmQWdPyepJ6WxxFwzsLtSzxSG+ShLzOtQgYJZXhOLqhP8Et9Sl5MbgDU9LaAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:43:35.023164Z"},"content_sha256":"4a816e2a74e6c94e454e5eb6a13986619479b5154551ffc9f85d02ac6e2d7f71","schema_version":"1.0","event_id":"sha256:4a816e2a74e6c94e454e5eb6a13986619479b5154551ffc9f85d02ac6e2d7f71"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GIVNG4DVCOIMVLDWWUCB7SKJW6/bundle.json","state_url":"https://pith.science/pith/GIVNG4DVCOIMVLDWWUCB7SKJW6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GIVNG4DVCOIMVLDWWUCB7SKJW6/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":"2026-08-03T21:43:35Z","links":{"resolver":"https://pith.science/pith/GIVNG4DVCOIMVLDWWUCB7SKJW6","bundle":"https://pith.science/pith/GIVNG4DVCOIMVLDWWUCB7SKJW6/bundle.json","state":"https://pith.science/pith/GIVNG4DVCOIMVLDWWUCB7SKJW6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GIVNG4DVCOIMVLDWWUCB7SKJW6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GIVNG4DVCOIMVLDWWUCB7SKJW6","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":"e47a807be64744802bbd182aea804770d93e9c35a991b5b4427f3120194ce912","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-16T09:11:00Z","title_canon_sha256":"49a2d7f15c223461d08007cbe0884cfd92ce73aa2b63e0f67f1da01dd5d788cd"},"schema_version":"1.0","source":{"id":"2308.08234","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.08234","created_at":"2026-07-05T06:41:56Z"},{"alias_kind":"arxiv_version","alias_value":"2308.08234v1","created_at":"2026-07-05T06:41:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.08234","created_at":"2026-07-05T06:41:56Z"},{"alias_kind":"pith_short_12","alias_value":"GIVNG4DVCOIM","created_at":"2026-07-05T06:41:56Z"},{"alias_kind":"pith_short_16","alias_value":"GIVNG4DVCOIMVLDW","created_at":"2026-07-05T06:41:56Z"},{"alias_kind":"pith_short_8","alias_value":"GIVNG4DV","created_at":"2026-07-05T06:41:56Z"}],"graph_snapshots":[{"event_id":"sha256:4a816e2a74e6c94e454e5eb6a13986619479b5154551ffc9f85d02ac6e2d7f71","target":"graph","created_at":"2026-07-05T06:41:56Z","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/2308.08234/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The increasing adoption of natural language processing (NLP) models across industries has led to practitioners' need for machine learning systems to handle these models efficiently, from training to serving them in production. However, training, deploying, and updating multiple models can be complex, costly, and time-consuming, mainly when using transformer-based pre-trained language models. Multi-Task Learning (MTL) has emerged as a promising approach to improve efficiency and performance through joint training, rather than training separate models. Motivated by this, we first provide an over","authors_text":"Bruno Sarlija, Lovre Torbarina, Lukasz Roguski, Tin Ferkovic, Velimir Mihelcic, Zeljko Kraljevic","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-16T09:11:00Z","title":"Challenges and Opportunities of Using Transformer-Based Multi-Task Learning in NLP Through ML Lifecycle: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.08234","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":"sha256:186339248fd78754804e00ca4fc86b6d5e3204c89f4c962e35096d55c05da1c7","target":"record","created_at":"2026-07-05T06:41:56Z","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":"e47a807be64744802bbd182aea804770d93e9c35a991b5b4427f3120194ce912","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-16T09:11:00Z","title_canon_sha256":"49a2d7f15c223461d08007cbe0884cfd92ce73aa2b63e0f67f1da01dd5d788cd"},"schema_version":"1.0","source":{"id":"2308.08234","kind":"arxiv","version":1}},"canonical_sha256":"322ad370751390caac76b5041fc949b7b5086c011b0e99bc6714e4a6cc8d1e91","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"322ad370751390caac76b5041fc949b7b5086c011b0e99bc6714e4a6cc8d1e91","first_computed_at":"2026-07-05T06:41:56.573770Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:41:56.573770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nGQN+Gh+Vd/4xQD2C1jC7uxWGA8g2MzS25jSV4N8ajtICb40zuypAH7iP0HPBWwO7Ky7gojIe9C1TA5RLXDgDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:41:56.574188Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.08234","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:186339248fd78754804e00ca4fc86b6d5e3204c89f4c962e35096d55c05da1c7","sha256:4a816e2a74e6c94e454e5eb6a13986619479b5154551ffc9f85d02ac6e2d7f71"],"state_sha256":"3d0c2f294d4177bf7f2cf0d2a332e90af7546b5e4f77a413cb6aae78b9db3e7b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"83ATe5VFSq1BrYcY07gMAZxOlb1MJj2doVXSAxYrtg0o7HvddW0vk0TAs3qoB+EkBMMVsUYRzdXhHC7z103ACg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T21:43:35.033620Z","bundle_sha256":"56e754269e2aa821713f8b4ced5ca555071a40ad1b4c99f16ccc01e36cebdf16"}}