{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:6LVZYE2XAWUKSBBZLK4BOXT4OA","short_pith_number":"pith:6LVZYE2X","canonical_record":{"source":{"id":"2110.07904","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-15T07:35:58Z","cross_cats_sorted":[],"title_canon_sha256":"556f0c5acd9af0b6937ab0e14e3b2ec76c964a6f73d5e5f0ebd7d08f15929582","abstract_canon_sha256":"c227cee7ee1970149acc6cd06c8ef089c90af765bbd5146f872297b4d5ff373d"},"schema_version":"1.0"},"canonical_sha256":"f2eb9c135705a8a904395ab8175e7c702b839a12355bba9eca2e5fa5e3e4cdae","source":{"kind":"arxiv","id":"2110.07904","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.07904","created_at":"2026-07-05T04:06:00Z"},{"alias_kind":"arxiv_version","alias_value":"2110.07904v2","created_at":"2026-07-05T04:06:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07904","created_at":"2026-07-05T04:06:00Z"},{"alias_kind":"pith_short_12","alias_value":"6LVZYE2XAWUK","created_at":"2026-07-05T04:06:00Z"},{"alias_kind":"pith_short_16","alias_value":"6LVZYE2XAWUKSBBZ","created_at":"2026-07-05T04:06:00Z"},{"alias_kind":"pith_short_8","alias_value":"6LVZYE2X","created_at":"2026-07-05T04:06:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:6LVZYE2XAWUKSBBZLK4BOXT4OA","target":"record","payload":{"canonical_record":{"source":{"id":"2110.07904","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-15T07:35:58Z","cross_cats_sorted":[],"title_canon_sha256":"556f0c5acd9af0b6937ab0e14e3b2ec76c964a6f73d5e5f0ebd7d08f15929582","abstract_canon_sha256":"c227cee7ee1970149acc6cd06c8ef089c90af765bbd5146f872297b4d5ff373d"},"schema_version":"1.0"},"canonical_sha256":"f2eb9c135705a8a904395ab8175e7c702b839a12355bba9eca2e5fa5e3e4cdae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:00.208667Z","signature_b64":"35ZD+rf8+e4k3w3qliKaFVpysXEOoAVbUKZ9Tvh1cNIb6XEuFHI7NnoRy5aDMooncDOlFzONnwmwQsMuAkWXCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2eb9c135705a8a904395ab8175e7c702b839a12355bba9eca2e5fa5e3e4cdae","last_reissued_at":"2026-07-05T04:06:00.208228Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:00.208228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.07904","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:06:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ysWJPtCjac46E45JSBes3ZDWj8dQLyuDMIBEi2BPqGpyGbVI/bPCyiJYXywC2VIvvUQ4ZB88wye/7G6x4CAoCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T06:17:09.694890Z"},"content_sha256":"cdaea27d82b839a903964bd54c47f19811c95b5a037f38b67eb35dd0ad9253bc","schema_version":"1.0","event_id":"sha256:cdaea27d82b839a903964bd54c47f19811c95b5a037f38b67eb35dd0ad9253bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:6LVZYE2XAWUKSBBZLK4BOXT4OA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Brian Lester, Daniel Cer, Noah Constant, Rami Al-Rfou, Tu Vu","submitted_at":"2021-10-15T07:35:58Z","abstract_excerpt":"There has been growing interest in parameter-efficient methods to apply pre-trained language models to downstream tasks. Building on the Prompt Tuning approach of Lester et al. (2021), which learns task-specific soft prompts to condition a frozen pre-trained model to perform different tasks, we propose a novel prompt-based transfer learning approach called SPoT: Soft Prompt Transfer. SPoT first learns a prompt on one or more source tasks and then uses it to initialize the prompt for a target task. We show that SPoT significantly boosts the performance of Prompt Tuning across many tasks. More r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07904","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/2110.07904/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":"2026-07-05T04:06:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tFoMALL/BJ/GX9CbUBhjd6xhqdwHxxhhRn8JtDgTNHlYVrURYEXr19BnlFA+FgRq26HxqxIdY7v+oGLyjELNAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T06:17:09.695411Z"},"content_sha256":"b4787f9fd0dbc1b3e23d17bf2ef446c9741fe9db195cbc78c539918cb0e308ab","schema_version":"1.0","event_id":"sha256:b4787f9fd0dbc1b3e23d17bf2ef446c9741fe9db195cbc78c539918cb0e308ab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6LVZYE2XAWUKSBBZLK4BOXT4OA/bundle.json","state_url":"https://pith.science/pith/6LVZYE2XAWUKSBBZLK4BOXT4OA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6LVZYE2XAWUKSBBZLK4BOXT4OA/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":"2026-08-22T06:17:09Z","links":{"resolver":"https://pith.science/pith/6LVZYE2XAWUKSBBZLK4BOXT4OA","bundle":"https://pith.science/pith/6LVZYE2XAWUKSBBZLK4BOXT4OA/bundle.json","state":"https://pith.science/pith/6LVZYE2XAWUKSBBZLK4BOXT4OA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6LVZYE2XAWUKSBBZLK4BOXT4OA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6LVZYE2XAWUKSBBZLK4BOXT4OA","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":"c227cee7ee1970149acc6cd06c8ef089c90af765bbd5146f872297b4d5ff373d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-15T07:35:58Z","title_canon_sha256":"556f0c5acd9af0b6937ab0e14e3b2ec76c964a6f73d5e5f0ebd7d08f15929582"},"schema_version":"1.0","source":{"id":"2110.07904","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.07904","created_at":"2026-07-05T04:06:00Z"},{"alias_kind":"arxiv_version","alias_value":"2110.07904v2","created_at":"2026-07-05T04:06:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07904","created_at":"2026-07-05T04:06:00Z"},{"alias_kind":"pith_short_12","alias_value":"6LVZYE2XAWUK","created_at":"2026-07-05T04:06:00Z"},{"alias_kind":"pith_short_16","alias_value":"6LVZYE2XAWUKSBBZ","created_at":"2026-07-05T04:06:00Z"},{"alias_kind":"pith_short_8","alias_value":"6LVZYE2X","created_at":"2026-07-05T04:06:00Z"}],"graph_snapshots":[{"event_id":"sha256:b4787f9fd0dbc1b3e23d17bf2ef446c9741fe9db195cbc78c539918cb0e308ab","target":"graph","created_at":"2026-07-05T04:06:00Z","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/2110.07904/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There has been growing interest in parameter-efficient methods to apply pre-trained language models to downstream tasks. Building on the Prompt Tuning approach of Lester et al. (2021), which learns task-specific soft prompts to condition a frozen pre-trained model to perform different tasks, we propose a novel prompt-based transfer learning approach called SPoT: Soft Prompt Transfer. SPoT first learns a prompt on one or more source tasks and then uses it to initialize the prompt for a target task. We show that SPoT significantly boosts the performance of Prompt Tuning across many tasks. More r","authors_text":"Brian Lester, Daniel Cer, Noah Constant, Rami Al-Rfou, Tu Vu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-15T07:35:58Z","title":"SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07904","kind":"arxiv","version":2},"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:cdaea27d82b839a903964bd54c47f19811c95b5a037f38b67eb35dd0ad9253bc","target":"record","created_at":"2026-07-05T04:06:00Z","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":"c227cee7ee1970149acc6cd06c8ef089c90af765bbd5146f872297b4d5ff373d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-15T07:35:58Z","title_canon_sha256":"556f0c5acd9af0b6937ab0e14e3b2ec76c964a6f73d5e5f0ebd7d08f15929582"},"schema_version":"1.0","source":{"id":"2110.07904","kind":"arxiv","version":2}},"canonical_sha256":"f2eb9c135705a8a904395ab8175e7c702b839a12355bba9eca2e5fa5e3e4cdae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2eb9c135705a8a904395ab8175e7c702b839a12355bba9eca2e5fa5e3e4cdae","first_computed_at":"2026-07-05T04:06:00.208228Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:06:00.208228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"35ZD+rf8+e4k3w3qliKaFVpysXEOoAVbUKZ9Tvh1cNIb6XEuFHI7NnoRy5aDMooncDOlFzONnwmwQsMuAkWXCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:06:00.208667Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.07904","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cdaea27d82b839a903964bd54c47f19811c95b5a037f38b67eb35dd0ad9253bc","sha256:b4787f9fd0dbc1b3e23d17bf2ef446c9741fe9db195cbc78c539918cb0e308ab"],"state_sha256":"c325bc8e13e8103569c2aa356a64535dbe3cb604e42cfdf18a0c643b4c954048"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H6l1OZhyglPeB8LAFYPv2gAFPYFK5+ihTio7KsP0ukN6nAuo48NdtU74ScnM7h9r3ZbVeXn52lvo6MvDg+krDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T06:17:09.700304Z","bundle_sha256":"42923aa3970ee070167771b7c010fb2351f2148468b1c400a62c1a34cab01250"}}