{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IERXCBZNPLMOA4QNN7Y2A5GG5Z","short_pith_number":"pith:IERXCBZN","canonical_record":{"source":{"id":"2502.12200","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-16T05:50:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"32d926fa3ddcc2c1b53d2e8effd5c62309afa1067e7b0b72e0ad2a98bedb076e","abstract_canon_sha256":"de8899f16c6c1938754f7518027087d309540ab2213b899004d503e8476b88e4"},"schema_version":"1.0"},"canonical_sha256":"412371072d7ad8e0720d6ff1a074c6ee5bbab54c776be17780e65f657af2fa62","source":{"kind":"arxiv","id":"2502.12200","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12200","created_at":"2026-07-05T10:15:51Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12200v1","created_at":"2026-07-05T10:15:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12200","created_at":"2026-07-05T10:15:51Z"},{"alias_kind":"pith_short_12","alias_value":"IERXCBZNPLMO","created_at":"2026-07-05T10:15:51Z"},{"alias_kind":"pith_short_16","alias_value":"IERXCBZNPLMOA4QN","created_at":"2026-07-05T10:15:51Z"},{"alias_kind":"pith_short_8","alias_value":"IERXCBZN","created_at":"2026-07-05T10:15:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IERXCBZNPLMOA4QNN7Y2A5GG5Z","target":"record","payload":{"canonical_record":{"source":{"id":"2502.12200","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-16T05:50:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"32d926fa3ddcc2c1b53d2e8effd5c62309afa1067e7b0b72e0ad2a98bedb076e","abstract_canon_sha256":"de8899f16c6c1938754f7518027087d309540ab2213b899004d503e8476b88e4"},"schema_version":"1.0"},"canonical_sha256":"412371072d7ad8e0720d6ff1a074c6ee5bbab54c776be17780e65f657af2fa62","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:51.782551Z","signature_b64":"XtJ7f9mgIyjvPi/2kGq4rmGytzrVZ57wUlucnfd4ZVZVfblitgTgEBLkOWwP9uCylEthYjE3uTsHb5SEmJuFCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"412371072d7ad8e0720d6ff1a074c6ee5bbab54c776be17780e65f657af2fa62","last_reissued_at":"2026-07-05T10:15:51.781874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:51.781874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.12200","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":"2026-07-05T10:15:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BSZp61jg5x5ehn65Ona/8dfmALIzBCTgpKw+PdIhUkGAiyottFjJDTi8/Q19HOiMne8vbIlRmRvL9C7qs1UrAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-23T22:08:58.454495Z"},"content_sha256":"7c78be878276db99f684ad06126f8af4078e26bd2f0aeda2b2bd53ce3ec7b8e8","schema_version":"1.0","event_id":"sha256:7c78be878276db99f684ad06126f8af4078e26bd2f0aeda2b2bd53ce3ec7b8e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IERXCBZNPLMOA4QNN7Y2A5GG5Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient and Effective Prompt Tuning via Prompt Decomposition and Compressed Outer Product","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Enneng Yang, Guibing Guo, Haoyu Xu, Jianzhe Zhao, Pengxiang Lan, Xingwei Wang, Yuliang Liang","submitted_at":"2025-02-16T05:50:12Z","abstract_excerpt":"Prompt tuning (PT) offers a cost-effective alternative to fine-tuning large-scale pre-trained language models (PLMs), requiring only a few parameters in soft prompt tokens added before the input text. However, existing PT approaches face two significant issues: (i) They overlook intrinsic semantic associations between soft prompt tokens, leading to high discreteness and limited interactions, thus reducing the model's comprehension and effectiveness in complex tasks. (ii) Due to the complexity of downstream tasks, long soft prompt is necessitated to improve performance, but prompt length correl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12200","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/2502.12200/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":"2026-07-05T10:15:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X+NIEnItibsvqB4F91wY7U8FrA5uGAIRJOP2kYfTKjr63t7lhVrUHGF67IMMT1v8wyJ758uq8vEb5qIhhyKKDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-23T22:08:58.454867Z"},"content_sha256":"47e78191782ed1b1fac52b1001db651993b06c30f6d8d7b03dfe5d0bcf289270","schema_version":"1.0","event_id":"sha256:47e78191782ed1b1fac52b1001db651993b06c30f6d8d7b03dfe5d0bcf289270"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IERXCBZNPLMOA4QNN7Y2A5GG5Z/bundle.json","state_url":"https://pith.science/pith/IERXCBZNPLMOA4QNN7Y2A5GG5Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IERXCBZNPLMOA4QNN7Y2A5GG5Z/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":"2026-07-23T22:08:58Z","links":{"resolver":"https://pith.science/pith/IERXCBZNPLMOA4QNN7Y2A5GG5Z","bundle":"https://pith.science/pith/IERXCBZNPLMOA4QNN7Y2A5GG5Z/bundle.json","state":"https://pith.science/pith/IERXCBZNPLMOA4QNN7Y2A5GG5Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IERXCBZNPLMOA4QNN7Y2A5GG5Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IERXCBZNPLMOA4QNN7Y2A5GG5Z","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":"de8899f16c6c1938754f7518027087d309540ab2213b899004d503e8476b88e4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-16T05:50:12Z","title_canon_sha256":"32d926fa3ddcc2c1b53d2e8effd5c62309afa1067e7b0b72e0ad2a98bedb076e"},"schema_version":"1.0","source":{"id":"2502.12200","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12200","created_at":"2026-07-05T10:15:51Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12200v1","created_at":"2026-07-05T10:15:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12200","created_at":"2026-07-05T10:15:51Z"},{"alias_kind":"pith_short_12","alias_value":"IERXCBZNPLMO","created_at":"2026-07-05T10:15:51Z"},{"alias_kind":"pith_short_16","alias_value":"IERXCBZNPLMOA4QN","created_at":"2026-07-05T10:15:51Z"},{"alias_kind":"pith_short_8","alias_value":"IERXCBZN","created_at":"2026-07-05T10:15:51Z"}],"graph_snapshots":[{"event_id":"sha256:47e78191782ed1b1fac52b1001db651993b06c30f6d8d7b03dfe5d0bcf289270","target":"graph","created_at":"2026-07-05T10:15:51Z","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/2502.12200/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prompt tuning (PT) offers a cost-effective alternative to fine-tuning large-scale pre-trained language models (PLMs), requiring only a few parameters in soft prompt tokens added before the input text. However, existing PT approaches face two significant issues: (i) They overlook intrinsic semantic associations between soft prompt tokens, leading to high discreteness and limited interactions, thus reducing the model's comprehension and effectiveness in complex tasks. (ii) Due to the complexity of downstream tasks, long soft prompt is necessitated to improve performance, but prompt length correl","authors_text":"Enneng Yang, Guibing Guo, Haoyu Xu, Jianzhe Zhao, Pengxiang Lan, Xingwei Wang, Yuliang Liang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-16T05:50:12Z","title":"Efficient and Effective Prompt Tuning via Prompt Decomposition and Compressed Outer Product"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12200","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":"sha256:7c78be878276db99f684ad06126f8af4078e26bd2f0aeda2b2bd53ce3ec7b8e8","target":"record","created_at":"2026-07-05T10:15:51Z","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":"de8899f16c6c1938754f7518027087d309540ab2213b899004d503e8476b88e4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-16T05:50:12Z","title_canon_sha256":"32d926fa3ddcc2c1b53d2e8effd5c62309afa1067e7b0b72e0ad2a98bedb076e"},"schema_version":"1.0","source":{"id":"2502.12200","kind":"arxiv","version":1}},"canonical_sha256":"412371072d7ad8e0720d6ff1a074c6ee5bbab54c776be17780e65f657af2fa62","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"412371072d7ad8e0720d6ff1a074c6ee5bbab54c776be17780e65f657af2fa62","first_computed_at":"2026-07-05T10:15:51.781874Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:15:51.781874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XtJ7f9mgIyjvPi/2kGq4rmGytzrVZ57wUlucnfd4ZVZVfblitgTgEBLkOWwP9uCylEthYjE3uTsHb5SEmJuFCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:15:51.782551Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.12200","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c78be878276db99f684ad06126f8af4078e26bd2f0aeda2b2bd53ce3ec7b8e8","sha256:47e78191782ed1b1fac52b1001db651993b06c30f6d8d7b03dfe5d0bcf289270"],"state_sha256":"a8ea43234ea9a75cdf3d39a4738b249f44b80af80c2e6f2b1a425f2d54da35ee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aQmmRP4l11tFn5+SLJO6tyqlbcZJB23vz5wcia8kEmh0wBHE886VRCYr0OhIER8p97NIIj56hUFTSKym7fknDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-23T22:08:58.457026Z","bundle_sha256":"354b113c1cdce47a58fc901fe88c450d33b0f16ef394e5d702b8685d648d98d5"}}