{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:JGWRKJIY5FR6LRX46DC27LMVIO","short_pith_number":"pith:JGWRKJIY","canonical_record":{"source":{"id":"2210.12587","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-23T01:33:16Z","cross_cats_sorted":[],"title_canon_sha256":"59fbb5a869bde4ed5d5e6182b0ed98449d40a5193d38dd0e89900adbb4046e25","abstract_canon_sha256":"29288bd5d1e04c4e736939b3cb91fbc9e6b4bd002f9f31656fb91d1c514c1627"},"schema_version":"1.0"},"canonical_sha256":"49ad152518e963e5c6fcf0c5afad954398fb0fc4b7606d6ffb1254519cc83063","source":{"kind":"arxiv","id":"2210.12587","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.12587","created_at":"2026-07-05T05:47:04Z"},{"alias_kind":"arxiv_version","alias_value":"2210.12587v3","created_at":"2026-07-05T05:47:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.12587","created_at":"2026-07-05T05:47:04Z"},{"alias_kind":"pith_short_12","alias_value":"JGWRKJIY5FR6","created_at":"2026-07-05T05:47:04Z"},{"alias_kind":"pith_short_16","alias_value":"JGWRKJIY5FR6LRX4","created_at":"2026-07-05T05:47:04Z"},{"alias_kind":"pith_short_8","alias_value":"JGWRKJIY","created_at":"2026-07-05T05:47:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:JGWRKJIY5FR6LRX46DC27LMVIO","target":"record","payload":{"canonical_record":{"source":{"id":"2210.12587","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-23T01:33:16Z","cross_cats_sorted":[],"title_canon_sha256":"59fbb5a869bde4ed5d5e6182b0ed98449d40a5193d38dd0e89900adbb4046e25","abstract_canon_sha256":"29288bd5d1e04c4e736939b3cb91fbc9e6b4bd002f9f31656fb91d1c514c1627"},"schema_version":"1.0"},"canonical_sha256":"49ad152518e963e5c6fcf0c5afad954398fb0fc4b7606d6ffb1254519cc83063","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:04.469466Z","signature_b64":"4ljO8KDvgEkgqdLDpe0gjyafxcD7fdR4rlQOf/8NUB9lRqZA4I+i586nwE1orhPzPO7y9Mhs6cGPnMVyknAGCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49ad152518e963e5c6fcf0c5afad954398fb0fc4b7606d6ffb1254519cc83063","last_reissued_at":"2026-07-05T05:47:04.468960Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:04.468960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.12587","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:47:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RDvC/ZKbfQQSBeuR1DGFd+XIkrlU7fQ3Eh6xDquc2BXDx9DDRm6AY+W18SA5DC6Geb0c2/b5pGcrq/tjlT3LBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:14:30.780859Z"},"content_sha256":"5dd1b3502293002f438e651b8772fc29ef1d23cfe4a9caa84f5d29acc2b1aa8c","schema_version":"1.0","event_id":"sha256:5dd1b3502293002f438e651b8772fc29ef1d23cfe4a9caa84f5d29acc2b1aa8c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:JGWRKJIY5FR6LRX46DC27LMVIO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model ensemble instead of prompt fusion: a sample-specific knowledge transfer method for few-shot prompt tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Caiming Xiong, Chen Xing, Chien-Sheng Wu, Prafulla Kumar Choubey, Xiangyu Peng","submitted_at":"2022-10-23T01:33:16Z","abstract_excerpt":"Prompt tuning approaches, which learn task-specific soft prompts for a downstream task conditioning on frozen pre-trained models, have attracted growing interest due to its parameter efficiency. With large language models and sufficient training data, prompt tuning performs comparably to full-model tuning. However, with limited training samples in few-shot settings, prompt tuning fails to match the performance of full-model fine-tuning. In this work, we focus on improving the few-shot performance of prompt tuning by transferring knowledge from soft prompts of source tasks. Recognizing the good"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.12587","kind":"arxiv","version":3},"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/2210.12587/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":"2026-07-05T05:47:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gFGgp7W5CHEjPJFURi7k8oV6zPuvEnrl0YhVG41ZiNZ7RbFhIT/4wS/dPeQstRYlUTDlVxyG14iTrRbgEdTOCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:14:30.781228Z"},"content_sha256":"ecc5631d95c1bebba66826e65d5cac781407e94a97b558d0414989f839f7fc66","schema_version":"1.0","event_id":"sha256:ecc5631d95c1bebba66826e65d5cac781407e94a97b558d0414989f839f7fc66"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JGWRKJIY5FR6LRX46DC27LMVIO/bundle.json","state_url":"https://pith.science/pith/JGWRKJIY5FR6LRX46DC27LMVIO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JGWRKJIY5FR6LRX46DC27LMVIO/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":"2026-07-07T12:14:30Z","links":{"resolver":"https://pith.science/pith/JGWRKJIY5FR6LRX46DC27LMVIO","bundle":"https://pith.science/pith/JGWRKJIY5FR6LRX46DC27LMVIO/bundle.json","state":"https://pith.science/pith/JGWRKJIY5FR6LRX46DC27LMVIO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JGWRKJIY5FR6LRX46DC27LMVIO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:JGWRKJIY5FR6LRX46DC27LMVIO","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":"29288bd5d1e04c4e736939b3cb91fbc9e6b4bd002f9f31656fb91d1c514c1627","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-23T01:33:16Z","title_canon_sha256":"59fbb5a869bde4ed5d5e6182b0ed98449d40a5193d38dd0e89900adbb4046e25"},"schema_version":"1.0","source":{"id":"2210.12587","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.12587","created_at":"2026-07-05T05:47:04Z"},{"alias_kind":"arxiv_version","alias_value":"2210.12587v3","created_at":"2026-07-05T05:47:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.12587","created_at":"2026-07-05T05:47:04Z"},{"alias_kind":"pith_short_12","alias_value":"JGWRKJIY5FR6","created_at":"2026-07-05T05:47:04Z"},{"alias_kind":"pith_short_16","alias_value":"JGWRKJIY5FR6LRX4","created_at":"2026-07-05T05:47:04Z"},{"alias_kind":"pith_short_8","alias_value":"JGWRKJIY","created_at":"2026-07-05T05:47:04Z"}],"graph_snapshots":[{"event_id":"sha256:ecc5631d95c1bebba66826e65d5cac781407e94a97b558d0414989f839f7fc66","target":"graph","created_at":"2026-07-05T05:47:04Z","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/2210.12587/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prompt tuning approaches, which learn task-specific soft prompts for a downstream task conditioning on frozen pre-trained models, have attracted growing interest due to its parameter efficiency. With large language models and sufficient training data, prompt tuning performs comparably to full-model tuning. However, with limited training samples in few-shot settings, prompt tuning fails to match the performance of full-model fine-tuning. In this work, we focus on improving the few-shot performance of prompt tuning by transferring knowledge from soft prompts of source tasks. Recognizing the good","authors_text":"Caiming Xiong, Chen Xing, Chien-Sheng Wu, Prafulla Kumar Choubey, Xiangyu Peng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-23T01:33:16Z","title":"Model ensemble instead of prompt fusion: a sample-specific knowledge transfer method for few-shot prompt tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.12587","kind":"arxiv","version":3},"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":"sha256:5dd1b3502293002f438e651b8772fc29ef1d23cfe4a9caa84f5d29acc2b1aa8c","target":"record","created_at":"2026-07-05T05:47:04Z","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":"29288bd5d1e04c4e736939b3cb91fbc9e6b4bd002f9f31656fb91d1c514c1627","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-23T01:33:16Z","title_canon_sha256":"59fbb5a869bde4ed5d5e6182b0ed98449d40a5193d38dd0e89900adbb4046e25"},"schema_version":"1.0","source":{"id":"2210.12587","kind":"arxiv","version":3}},"canonical_sha256":"49ad152518e963e5c6fcf0c5afad954398fb0fc4b7606d6ffb1254519cc83063","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"49ad152518e963e5c6fcf0c5afad954398fb0fc4b7606d6ffb1254519cc83063","first_computed_at":"2026-07-05T05:47:04.468960Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:47:04.468960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4ljO8KDvgEkgqdLDpe0gjyafxcD7fdR4rlQOf/8NUB9lRqZA4I+i586nwE1orhPzPO7y9Mhs6cGPnMVyknAGCg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:47:04.469466Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.12587","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5dd1b3502293002f438e651b8772fc29ef1d23cfe4a9caa84f5d29acc2b1aa8c","sha256:ecc5631d95c1bebba66826e65d5cac781407e94a97b558d0414989f839f7fc66"],"state_sha256":"22da79b748d8dd76769183afb1f751b326c8d6a6741dc4a65df06f3ec745103d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+lerqZvh6JmWtODYGfC/in4GkhkbENPLDARD4y4v18PegQ3jspiwPH3JNIJj6NuwDCkzhKjqRL9aSCtfqrtbBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:14:30.783139Z","bundle_sha256":"911249e5fe8ac13cc9799176f5a3335194388ba8e372882d89b3e3a3a1e05a61"}}