{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PEYCWU4UIY62X2B54OQZCB2U64","short_pith_number":"pith:PEYCWU4U","canonical_record":{"source":{"id":"2408.01119","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-02T09:00:03Z","cross_cats_sorted":[],"title_canon_sha256":"579246b4421dfd4b9f3df20c2a70651ec7e7b8a56038586e772998499670329b","abstract_canon_sha256":"4c088bae37bf9563031668dd7299709558a8ca234b6f7593b5d13484ccbc4b3c"},"schema_version":"1.0"},"canonical_sha256":"79302b5394463dabe83de3a1910754f72c26f461f8425806269356e6c0d127c3","source":{"kind":"arxiv","id":"2408.01119","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.01119","created_at":"2026-05-18T03:10:12Z"},{"alias_kind":"arxiv_version","alias_value":"2408.01119v4","created_at":"2026-05-18T03:10:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.01119","created_at":"2026-05-18T03:10:12Z"},{"alias_kind":"pith_short_12","alias_value":"PEYCWU4UIY62","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"PEYCWU4UIY62X2B5","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"PEYCWU4U","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PEYCWU4UIY62X2B54OQZCB2U64","target":"record","payload":{"canonical_record":{"source":{"id":"2408.01119","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-02T09:00:03Z","cross_cats_sorted":[],"title_canon_sha256":"579246b4421dfd4b9f3df20c2a70651ec7e7b8a56038586e772998499670329b","abstract_canon_sha256":"4c088bae37bf9563031668dd7299709558a8ca234b6f7593b5d13484ccbc4b3c"},"schema_version":"1.0"},"canonical_sha256":"79302b5394463dabe83de3a1910754f72c26f461f8425806269356e6c0d127c3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:10:12.990645Z","signature_b64":"4BhLvhdLbhtZAOcfuco8GbfhvZr/LIeQMckPwoDzFa6B2VCkVZS6/6AOIo/b98VqTL25US8V44BHiGftm7xaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79302b5394463dabe83de3a1910754f72c26f461f8425806269356e6c0d127c3","last_reissued_at":"2026-05-18T03:10:12.989855Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:10:12.989855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.01119","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:10:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ngBPNDEml6LiydIVb14EKijS8LERi82305A8aTAaRzG/DkYh9IHzgk2t78/Yx7NAemqC6Jo8UieUbMZahjybAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T17:04:59.634455Z"},"content_sha256":"4fee879af92274d61f640104057ad7ae7cb3b15f20bf567d44705b968fa65097","schema_version":"1.0","event_id":"sha256:4fee879af92274d61f640104057ad7ae7cb3b15f20bf567d44705b968fa65097"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PEYCWU4UIY62X2B54OQZCB2U64","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Task Prompt Vectors: Effective Initialization through Multi-Task Soft-Prompt Transfer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ivan Srba, Maria Bielikova, Robert Belanec, Simon Ostermann","submitted_at":"2024-08-02T09:00:03Z","abstract_excerpt":"Prompt tuning is an efficient solution for training large language models (LLMs). However, current soft-prompt-based methods often sacrifice multi-task modularity, requiring the training process to be fully or partially repeated for each newly added task. While recent work on task vectors applied arithmetic operations on full model weights to achieve the desired multi-task performance, a similar approach for soft-prompts is still missing. To this end, we introduce Task Prompt Vectors, created by element-wise difference between weights of tuned soft-prompts and their random initialization. Expe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.01119","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T03:10:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zgEgYGfUaW8/P7MMofD3V595Sz+3s/uP7ePvdzrA7ifgfrLyWJAZSqmWADDqnejVHlIj/jA2+qsMZML6R6UJBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T17:04:59.635041Z"},"content_sha256":"f7a9c3a197653437aacdb4ba8acc8a0716c56e6c4133d5ed953a60cc1ebc434c","schema_version":"1.0","event_id":"sha256:f7a9c3a197653437aacdb4ba8acc8a0716c56e6c4133d5ed953a60cc1ebc434c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PEYCWU4UIY62X2B54OQZCB2U64/bundle.json","state_url":"https://pith.science/pith/PEYCWU4UIY62X2B54OQZCB2U64/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PEYCWU4UIY62X2B54OQZCB2U64/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":"2026-05-19T17:04:59Z","links":{"resolver":"https://pith.science/pith/PEYCWU4UIY62X2B54OQZCB2U64","bundle":"https://pith.science/pith/PEYCWU4UIY62X2B54OQZCB2U64/bundle.json","state":"https://pith.science/pith/PEYCWU4UIY62X2B54OQZCB2U64/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PEYCWU4UIY62X2B54OQZCB2U64/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PEYCWU4UIY62X2B54OQZCB2U64","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":"4c088bae37bf9563031668dd7299709558a8ca234b6f7593b5d13484ccbc4b3c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-02T09:00:03Z","title_canon_sha256":"579246b4421dfd4b9f3df20c2a70651ec7e7b8a56038586e772998499670329b"},"schema_version":"1.0","source":{"id":"2408.01119","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.01119","created_at":"2026-05-18T03:10:12Z"},{"alias_kind":"arxiv_version","alias_value":"2408.01119v4","created_at":"2026-05-18T03:10:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.01119","created_at":"2026-05-18T03:10:12Z"},{"alias_kind":"pith_short_12","alias_value":"PEYCWU4UIY62","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"PEYCWU4UIY62X2B5","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"PEYCWU4U","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:f7a9c3a197653437aacdb4ba8acc8a0716c56e6c4133d5ed953a60cc1ebc434c","target":"graph","created_at":"2026-05-18T03:10:12Z","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"},"paper":{"abstract_excerpt":"Prompt tuning is an efficient solution for training large language models (LLMs). However, current soft-prompt-based methods often sacrifice multi-task modularity, requiring the training process to be fully or partially repeated for each newly added task. While recent work on task vectors applied arithmetic operations on full model weights to achieve the desired multi-task performance, a similar approach for soft-prompts is still missing. To this end, we introduce Task Prompt Vectors, created by element-wise difference between weights of tuned soft-prompts and their random initialization. Expe","authors_text":"Ivan Srba, Maria Bielikova, Robert Belanec, Simon Ostermann","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-02T09:00:03Z","title":"Task Prompt Vectors: Effective Initialization through Multi-Task Soft-Prompt Transfer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.01119","kind":"arxiv","version":4},"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":"sha256:4fee879af92274d61f640104057ad7ae7cb3b15f20bf567d44705b968fa65097","target":"record","created_at":"2026-05-18T03:10:12Z","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":"4c088bae37bf9563031668dd7299709558a8ca234b6f7593b5d13484ccbc4b3c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-02T09:00:03Z","title_canon_sha256":"579246b4421dfd4b9f3df20c2a70651ec7e7b8a56038586e772998499670329b"},"schema_version":"1.0","source":{"id":"2408.01119","kind":"arxiv","version":4}},"canonical_sha256":"79302b5394463dabe83de3a1910754f72c26f461f8425806269356e6c0d127c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"79302b5394463dabe83de3a1910754f72c26f461f8425806269356e6c0d127c3","first_computed_at":"2026-05-18T03:10:12.989855Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:10:12.989855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4BhLvhdLbhtZAOcfuco8GbfhvZr/LIeQMckPwoDzFa6B2VCkVZS6/6AOIo/b98VqTL25US8V44BHiGftm7xaDA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:10:12.990645Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.01119","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fee879af92274d61f640104057ad7ae7cb3b15f20bf567d44705b968fa65097","sha256:f7a9c3a197653437aacdb4ba8acc8a0716c56e6c4133d5ed953a60cc1ebc434c"],"state_sha256":"8504aa94fe5ceae56b5d75ca2b064293ecabd8a80e9cae934330dd4746161986"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k5/lGg6OStS3dgfW/7VSEAvzzFWELkauURpH3ER4LW8YxnzHBLdjGmOQf6yAbz4iNjPKdKgPDFeAzdaUs/q7BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T17:04:59.637966Z","bundle_sha256":"88edf9e9a4383d9364382ba647dcbd5010c485b269128b1140a01a003d067eb3"}}