{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:BZQIUAKNV4SW6QFMNMYP3YNP3O","short_pith_number":"pith:BZQIUAKN","canonical_record":{"source":{"id":"2108.13161","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-30T12:29:25Z","cross_cats_sorted":["cs.AI","cs.CV","cs.IR","cs.LG"],"title_canon_sha256":"5c1f6ecc998edfc12f76c61795c99f5a7d7545dd49b54906923994275f8e7ad7","abstract_canon_sha256":"c6b5fa09366fc77eadb06395a173c0aa08ab78347d7c9b12bdd35451c347538f"},"schema_version":"1.0"},"canonical_sha256":"0e608a014daf256f40ac6b30fde1afdb967b8230476f3a101170c6359ecf8a9d","source":{"kind":"arxiv","id":"2108.13161","version":7},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.13161","created_at":"2026-07-05T05:35:42Z"},{"alias_kind":"arxiv_version","alias_value":"2108.13161v7","created_at":"2026-07-05T05:35:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.13161","created_at":"2026-07-05T05:35:42Z"},{"alias_kind":"pith_short_12","alias_value":"BZQIUAKNV4SW","created_at":"2026-07-05T05:35:42Z"},{"alias_kind":"pith_short_16","alias_value":"BZQIUAKNV4SW6QFM","created_at":"2026-07-05T05:35:42Z"},{"alias_kind":"pith_short_8","alias_value":"BZQIUAKN","created_at":"2026-07-05T05:35:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:BZQIUAKNV4SW6QFMNMYP3YNP3O","target":"record","payload":{"canonical_record":{"source":{"id":"2108.13161","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-30T12:29:25Z","cross_cats_sorted":["cs.AI","cs.CV","cs.IR","cs.LG"],"title_canon_sha256":"5c1f6ecc998edfc12f76c61795c99f5a7d7545dd49b54906923994275f8e7ad7","abstract_canon_sha256":"c6b5fa09366fc77eadb06395a173c0aa08ab78347d7c9b12bdd35451c347538f"},"schema_version":"1.0"},"canonical_sha256":"0e608a014daf256f40ac6b30fde1afdb967b8230476f3a101170c6359ecf8a9d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:35:42.013398Z","signature_b64":"NMcyPtlYOp52ZN+8IJJ01Aci3E7jbTyqno35NM4/VpI8fL10xpD/anjYy11yhHZdwo0iQTtroK5idSXFp8DnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e608a014daf256f40ac6b30fde1afdb967b8230476f3a101170c6359ecf8a9d","last_reissued_at":"2026-07-05T05:35:42.012912Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:35:42.012912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.13161","source_version":7,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:35:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XhrUA89f7GO8qrxDwZvr5vt7HR770dG2d3URgVQJM5qtz+ZVcvMolqK6d02p9o5hgetVXAx63F31xVAwF3/FAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T17:17:50.852347Z"},"content_sha256":"8e274bd8e0568d73f536891ecfd4cf174be6f676ec40a475662da7211c322e95","schema_version":"1.0","event_id":"sha256:8e274bd8e0568d73f536891ecfd4cf174be6f676ec40a475662da7211c322e95"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:BZQIUAKNV4SW6QFMNMYP3YNP3O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chuanqi Tan, Fei Huang, Huajun Chen, Luoqiu Li, Ningyu Zhang, Shumin Deng, Xiang Chen, Zhen Bi","submitted_at":"2021-08-30T12:29:25Z","abstract_excerpt":"Large-scale pre-trained language models have contributed significantly to natural language processing by demonstrating remarkable abilities as few-shot learners. However, their effectiveness depends mainly on scaling the model parameters and prompt design, hindering their implementation in most real-world applications. This study proposes a novel pluggable, extensible, and efficient approach named DifferentiAble pRompT (DART), which can convert small language models into better few-shot learners without any prompt engineering. The main principle behind this approach involves reformulating pote"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.13161","kind":"arxiv","version":7},"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/2108.13161/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":"2026-07-05T05:35:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lFilXPydC/pQxadeE9Cd8XvsKLTc028PFVhr77GwTOpvNrLM6IEJTaiG2pHcPWHvotyidlBVKi0L/CGT7AlaCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T17:17:50.852848Z"},"content_sha256":"b153794256310e15a44c23fd4d44c637863ffc5074f9ab32687a6e01728b3f5e","schema_version":"1.0","event_id":"sha256:b153794256310e15a44c23fd4d44c637863ffc5074f9ab32687a6e01728b3f5e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BZQIUAKNV4SW6QFMNMYP3YNP3O/bundle.json","state_url":"https://pith.science/pith/BZQIUAKNV4SW6QFMNMYP3YNP3O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BZQIUAKNV4SW6QFMNMYP3YNP3O/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":"2026-08-23T17:17:50Z","links":{"resolver":"https://pith.science/pith/BZQIUAKNV4SW6QFMNMYP3YNP3O","bundle":"https://pith.science/pith/BZQIUAKNV4SW6QFMNMYP3YNP3O/bundle.json","state":"https://pith.science/pith/BZQIUAKNV4SW6QFMNMYP3YNP3O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BZQIUAKNV4SW6QFMNMYP3YNP3O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:BZQIUAKNV4SW6QFMNMYP3YNP3O","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":"c6b5fa09366fc77eadb06395a173c0aa08ab78347d7c9b12bdd35451c347538f","cross_cats_sorted":["cs.AI","cs.CV","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-30T12:29:25Z","title_canon_sha256":"5c1f6ecc998edfc12f76c61795c99f5a7d7545dd49b54906923994275f8e7ad7"},"schema_version":"1.0","source":{"id":"2108.13161","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.13161","created_at":"2026-07-05T05:35:42Z"},{"alias_kind":"arxiv_version","alias_value":"2108.13161v7","created_at":"2026-07-05T05:35:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.13161","created_at":"2026-07-05T05:35:42Z"},{"alias_kind":"pith_short_12","alias_value":"BZQIUAKNV4SW","created_at":"2026-07-05T05:35:42Z"},{"alias_kind":"pith_short_16","alias_value":"BZQIUAKNV4SW6QFM","created_at":"2026-07-05T05:35:42Z"},{"alias_kind":"pith_short_8","alias_value":"BZQIUAKN","created_at":"2026-07-05T05:35:42Z"}],"graph_snapshots":[{"event_id":"sha256:b153794256310e15a44c23fd4d44c637863ffc5074f9ab32687a6e01728b3f5e","target":"graph","created_at":"2026-07-05T05:35:42Z","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/2108.13161/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale pre-trained language models have contributed significantly to natural language processing by demonstrating remarkable abilities as few-shot learners. However, their effectiveness depends mainly on scaling the model parameters and prompt design, hindering their implementation in most real-world applications. This study proposes a novel pluggable, extensible, and efficient approach named DifferentiAble pRompT (DART), which can convert small language models into better few-shot learners without any prompt engineering. The main principle behind this approach involves reformulating pote","authors_text":"Chuanqi Tan, Fei Huang, Huajun Chen, Luoqiu Li, Ningyu Zhang, Shumin Deng, Xiang Chen, Zhen Bi","cross_cats":["cs.AI","cs.CV","cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-30T12:29:25Z","title":"Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.13161","kind":"arxiv","version":7},"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":"sha256:8e274bd8e0568d73f536891ecfd4cf174be6f676ec40a475662da7211c322e95","target":"record","created_at":"2026-07-05T05:35:42Z","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":"c6b5fa09366fc77eadb06395a173c0aa08ab78347d7c9b12bdd35451c347538f","cross_cats_sorted":["cs.AI","cs.CV","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-30T12:29:25Z","title_canon_sha256":"5c1f6ecc998edfc12f76c61795c99f5a7d7545dd49b54906923994275f8e7ad7"},"schema_version":"1.0","source":{"id":"2108.13161","kind":"arxiv","version":7}},"canonical_sha256":"0e608a014daf256f40ac6b30fde1afdb967b8230476f3a101170c6359ecf8a9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e608a014daf256f40ac6b30fde1afdb967b8230476f3a101170c6359ecf8a9d","first_computed_at":"2026-07-05T05:35:42.012912Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:35:42.012912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NMcyPtlYOp52ZN+8IJJ01Aci3E7jbTyqno35NM4/VpI8fL10xpD/anjYy11yhHZdwo0iQTtroK5idSXFp8DnBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:35:42.013398Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.13161","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e274bd8e0568d73f536891ecfd4cf174be6f676ec40a475662da7211c322e95","sha256:b153794256310e15a44c23fd4d44c637863ffc5074f9ab32687a6e01728b3f5e"],"state_sha256":"4aae9572b09a8026e9604a4f7b5380058923158c76ee40ae7633a91329af67b1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BduMjlXUCVNDA9BrdlfxaAE2+D1Ea+ks8p91ko+dsHkXTFXFH0ONO5OqCJQ/bTrM27SLHpBEpmPsOTFmrxPNCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T17:17:50.856469Z","bundle_sha256":"8cd5dbd1534c3bbddb8b470f0036ea8df41e594290589870f44d35d58657a318"}}