{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:QQEJ4SS7B4IVEU5TD3CRAEHIPA","short_pith_number":"pith:QQEJ4SS7","canonical_record":{"source":{"id":"2110.08484","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-16T06:07:59Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"34706e384e3d0b0372cdc88d2886763a4283e54cd9107c9bef9d913b22f6a146","abstract_canon_sha256":"86b975a99155d656526abda85fe07127804834581bf347d84f774da89247d35a"},"schema_version":"1.0"},"canonical_sha256":"84089e4a5f0f115253b31ec51010e8781e448339a3cccfd7cd6fd11b95a2782d","source":{"kind":"arxiv","id":"2110.08484","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.08484","created_at":"2026-07-05T04:05:14Z"},{"alias_kind":"arxiv_version","alias_value":"2110.08484v2","created_at":"2026-07-05T04:05:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.08484","created_at":"2026-07-05T04:05:14Z"},{"alias_kind":"pith_short_12","alias_value":"QQEJ4SS7B4IV","created_at":"2026-07-05T04:05:14Z"},{"alias_kind":"pith_short_16","alias_value":"QQEJ4SS7B4IVEU5T","created_at":"2026-07-05T04:05:14Z"},{"alias_kind":"pith_short_8","alias_value":"QQEJ4SS7","created_at":"2026-07-05T04:05:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:QQEJ4SS7B4IVEU5TD3CRAEHIPA","target":"record","payload":{"canonical_record":{"source":{"id":"2110.08484","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-16T06:07:59Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"34706e384e3d0b0372cdc88d2886763a4283e54cd9107c9bef9d913b22f6a146","abstract_canon_sha256":"86b975a99155d656526abda85fe07127804834581bf347d84f774da89247d35a"},"schema_version":"1.0"},"canonical_sha256":"84089e4a5f0f115253b31ec51010e8781e448339a3cccfd7cd6fd11b95a2782d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:14.015858Z","signature_b64":"22PF8KhryszVdmRTlJFR88KVHkokxG8MIjK1+wf50a7yIQzNUSZFsjHDOycxOU0iaG1o7qSI929Hk2eWT7zxCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84089e4a5f0f115253b31ec51010e8781e448339a3cccfd7cd6fd11b95a2782d","last_reissued_at":"2026-07-05T04:05:14.015396Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:14.015396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.08484","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":"2026-07-05T04:05:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u0ubup+zi1wzmeqsJU+cAM8fAD6E6Iu7SCktC4j6ImJq5Ej8YpGlc/BM/UZ82DKuZz5DcbnTcp4dRUz11ybMCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:06:46.820261Z"},"content_sha256":"6efed95ecf24f9f8bfd7ffaf85dc0b3fe3e2e4271f9b7086138c668928c76e94","schema_version":"1.0","event_id":"sha256:6efed95ecf24f9f8bfd7ffaf85dc0b3fe3e2e4271f9b7086138c668928c76e94"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:QQEJ4SS7B4IVEU5TD3CRAEHIPA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Weizhu Chen, Woojeong Jin, Xiang Ren, Yelong Shen, Yu Cheng","submitted_at":"2021-10-16T06:07:59Z","abstract_excerpt":"Large pre-trained vision-language (VL) models can learn a new task with a handful of examples and generalize to a new task without fine-tuning. However, these VL models are hard to deploy for real-world applications due to their impractically huge sizes and slow inference speed. To solve this limitation, we study prompt-based low-resource learning of VL tasks with our proposed method, FewVLM, relatively smaller than recent few-shot learners. For FewVLM, we pre-train a sequence-to-sequence transformer model with prefix language modeling (PrefixLM) and masked language modeling (MaskedLM). Furthe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.08484","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/2110.08484/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":"2026-07-05T04:05:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t3q1Vaz4El+Z8OPct5yGQsdREmpv/eck0JuGQ/c0khOHMVPH4OAOfMUF5p/EraulQ6CpLYc9gGbP13QMVzXBDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:06:46.820770Z"},"content_sha256":"09c92a0bb93b2b57ae3dc108f70a794d783619309141013d54e3fdbe2a9d1d46","schema_version":"1.0","event_id":"sha256:09c92a0bb93b2b57ae3dc108f70a794d783619309141013d54e3fdbe2a9d1d46"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QQEJ4SS7B4IVEU5TD3CRAEHIPA/bundle.json","state_url":"https://pith.science/pith/QQEJ4SS7B4IVEU5TD3CRAEHIPA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QQEJ4SS7B4IVEU5TD3CRAEHIPA/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":"2026-08-08T08:06:46Z","links":{"resolver":"https://pith.science/pith/QQEJ4SS7B4IVEU5TD3CRAEHIPA","bundle":"https://pith.science/pith/QQEJ4SS7B4IVEU5TD3CRAEHIPA/bundle.json","state":"https://pith.science/pith/QQEJ4SS7B4IVEU5TD3CRAEHIPA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QQEJ4SS7B4IVEU5TD3CRAEHIPA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:QQEJ4SS7B4IVEU5TD3CRAEHIPA","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":"86b975a99155d656526abda85fe07127804834581bf347d84f774da89247d35a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-16T06:07:59Z","title_canon_sha256":"34706e384e3d0b0372cdc88d2886763a4283e54cd9107c9bef9d913b22f6a146"},"schema_version":"1.0","source":{"id":"2110.08484","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.08484","created_at":"2026-07-05T04:05:14Z"},{"alias_kind":"arxiv_version","alias_value":"2110.08484v2","created_at":"2026-07-05T04:05:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.08484","created_at":"2026-07-05T04:05:14Z"},{"alias_kind":"pith_short_12","alias_value":"QQEJ4SS7B4IV","created_at":"2026-07-05T04:05:14Z"},{"alias_kind":"pith_short_16","alias_value":"QQEJ4SS7B4IVEU5T","created_at":"2026-07-05T04:05:14Z"},{"alias_kind":"pith_short_8","alias_value":"QQEJ4SS7","created_at":"2026-07-05T04:05:14Z"}],"graph_snapshots":[{"event_id":"sha256:09c92a0bb93b2b57ae3dc108f70a794d783619309141013d54e3fdbe2a9d1d46","target":"graph","created_at":"2026-07-05T04:05:14Z","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/2110.08484/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large pre-trained vision-language (VL) models can learn a new task with a handful of examples and generalize to a new task without fine-tuning. However, these VL models are hard to deploy for real-world applications due to their impractically huge sizes and slow inference speed. To solve this limitation, we study prompt-based low-resource learning of VL tasks with our proposed method, FewVLM, relatively smaller than recent few-shot learners. For FewVLM, we pre-train a sequence-to-sequence transformer model with prefix language modeling (PrefixLM) and masked language modeling (MaskedLM). Furthe","authors_text":"Weizhu Chen, Woojeong Jin, Xiang Ren, Yelong Shen, Yu Cheng","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-16T06:07:59Z","title":"A Good Prompt Is Worth Millions of Parameters: Low-resource Prompt-based Learning for Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.08484","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":"sha256:6efed95ecf24f9f8bfd7ffaf85dc0b3fe3e2e4271f9b7086138c668928c76e94","target":"record","created_at":"2026-07-05T04:05:14Z","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":"86b975a99155d656526abda85fe07127804834581bf347d84f774da89247d35a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-10-16T06:07:59Z","title_canon_sha256":"34706e384e3d0b0372cdc88d2886763a4283e54cd9107c9bef9d913b22f6a146"},"schema_version":"1.0","source":{"id":"2110.08484","kind":"arxiv","version":2}},"canonical_sha256":"84089e4a5f0f115253b31ec51010e8781e448339a3cccfd7cd6fd11b95a2782d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84089e4a5f0f115253b31ec51010e8781e448339a3cccfd7cd6fd11b95a2782d","first_computed_at":"2026-07-05T04:05:14.015396Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:05:14.015396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"22PF8KhryszVdmRTlJFR88KVHkokxG8MIjK1+wf50a7yIQzNUSZFsjHDOycxOU0iaG1o7qSI929Hk2eWT7zxCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:05:14.015858Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.08484","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6efed95ecf24f9f8bfd7ffaf85dc0b3fe3e2e4271f9b7086138c668928c76e94","sha256:09c92a0bb93b2b57ae3dc108f70a794d783619309141013d54e3fdbe2a9d1d46"],"state_sha256":"51cdaa30ea1b5718f6613c4c8aed189ebd467475a414841f7353259089e5d662"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vLWea2j5vVHvkJy/16PezhBL0Py+wO1Qo+nP7MvyXzDeaoMWatni44iOiSjYsRKj53CU/9VQr4EDxu/FM2MMAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T08:06:46.825610Z","bundle_sha256":"04c909dd9f9eb724cb9156378d1f964d283020ab12f7a648a075693325ad9487"}}