{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CU5DOTOGSKPXFM5M2PGPS4EJGT","short_pith_number":"pith:CU5DOTOG","canonical_record":{"source":{"id":"2305.16938","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T13:55:17Z","cross_cats_sorted":[],"title_canon_sha256":"5acf9f944c4e16a52b6f841089d126b14789eb5c3646a50cda692c66dae054be","abstract_canon_sha256":"2ed3d6236de250bfc22ba139a7249b7a8192ec503e16051caf211a6bd89b54f4"},"schema_version":"1.0"},"canonical_sha256":"153a374dc6929f72b3acd3ccf9708934e32d017b6423233e98f9fb6f39124111","source":{"kind":"arxiv","id":"2305.16938","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.16938","created_at":"2026-07-05T06:14:58Z"},{"alias_kind":"arxiv_version","alias_value":"2305.16938v2","created_at":"2026-07-05T06:14:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16938","created_at":"2026-07-05T06:14:58Z"},{"alias_kind":"pith_short_12","alias_value":"CU5DOTOGSKPX","created_at":"2026-07-05T06:14:58Z"},{"alias_kind":"pith_short_16","alias_value":"CU5DOTOGSKPXFM5M","created_at":"2026-07-05T06:14:58Z"},{"alias_kind":"pith_short_8","alias_value":"CU5DOTOG","created_at":"2026-07-05T06:14:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CU5DOTOGSKPXFM5M2PGPS4EJGT","target":"record","payload":{"canonical_record":{"source":{"id":"2305.16938","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T13:55:17Z","cross_cats_sorted":[],"title_canon_sha256":"5acf9f944c4e16a52b6f841089d126b14789eb5c3646a50cda692c66dae054be","abstract_canon_sha256":"2ed3d6236de250bfc22ba139a7249b7a8192ec503e16051caf211a6bd89b54f4"},"schema_version":"1.0"},"canonical_sha256":"153a374dc6929f72b3acd3ccf9708934e32d017b6423233e98f9fb6f39124111","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:58.901728Z","signature_b64":"jObQATR2qKi1/SjDzg1ccoWOoqHYBCXBNzCihXz/0hiC2X29ZYnViFw5rfTtx7MzVa0RFfvRudMXNqCMloA/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"153a374dc6929f72b3acd3ccf9708934e32d017b6423233e98f9fb6f39124111","last_reissued_at":"2026-07-05T06:14:58.901300Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:58.901300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.16938","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":"2026-07-05T06:14:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8yASuONHOcRSYrVcv+kC0ywQJafamgTPIkGE7Uvv1T/gr6dqemVeQf4uMDs3vNn9OPPq+GFrw1ugv0xr7GBSCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:55:41.783277Z"},"content_sha256":"535bc0d04b6520ab8b318937b963674beccb44b7970fca80e871e8b299ac474f","schema_version":"1.0","event_id":"sha256:535bc0d04b6520ab8b318937b963674beccb44b7970fca80e871e8b299ac474f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CU5DOTOGSKPXFM5M2PGPS4EJGT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dietrich Klakow, Marius Mosbach, Shauli Ravfogel, Tiago Pimentel, Yanai Elazar","submitted_at":"2023-05-26T13:55:17Z","abstract_excerpt":"Few-shot fine-tuning and in-context learning are two alternative strategies for task adaptation of pre-trained language models. Recently, in-context learning has gained popularity over fine-tuning due to its simplicity and improved out-of-domain generalization, and because extensive evidence shows that fine-tuned models pick up on spurious correlations. Unfortunately, previous comparisons of the two approaches were done using models of different sizes. This raises the question of whether the observed weaker out-of-domain generalization of fine-tuned models is an inherent property of fine-tunin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16938","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/2305.16938/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":"2026-07-05T06:14:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gd4URKalc0rEIrOIy7TfBUB+tcqd+l/iyAae401xBl3aDeIW7nU+NKto2lblHLbHvHUvpmkOYwidVRscbNrzDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:55:41.784134Z"},"content_sha256":"7f0359d58e11f7fd4c63e020482e1ded28b21729ee54c3c21a0e4ab2c99c2813","schema_version":"1.0","event_id":"sha256:7f0359d58e11f7fd4c63e020482e1ded28b21729ee54c3c21a0e4ab2c99c2813"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CU5DOTOGSKPXFM5M2PGPS4EJGT/bundle.json","state_url":"https://pith.science/pith/CU5DOTOGSKPXFM5M2PGPS4EJGT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CU5DOTOGSKPXFM5M2PGPS4EJGT/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":"2026-08-08T22:55:41Z","links":{"resolver":"https://pith.science/pith/CU5DOTOGSKPXFM5M2PGPS4EJGT","bundle":"https://pith.science/pith/CU5DOTOGSKPXFM5M2PGPS4EJGT/bundle.json","state":"https://pith.science/pith/CU5DOTOGSKPXFM5M2PGPS4EJGT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CU5DOTOGSKPXFM5M2PGPS4EJGT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CU5DOTOGSKPXFM5M2PGPS4EJGT","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":"2ed3d6236de250bfc22ba139a7249b7a8192ec503e16051caf211a6bd89b54f4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T13:55:17Z","title_canon_sha256":"5acf9f944c4e16a52b6f841089d126b14789eb5c3646a50cda692c66dae054be"},"schema_version":"1.0","source":{"id":"2305.16938","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.16938","created_at":"2026-07-05T06:14:58Z"},{"alias_kind":"arxiv_version","alias_value":"2305.16938v2","created_at":"2026-07-05T06:14:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16938","created_at":"2026-07-05T06:14:58Z"},{"alias_kind":"pith_short_12","alias_value":"CU5DOTOGSKPX","created_at":"2026-07-05T06:14:58Z"},{"alias_kind":"pith_short_16","alias_value":"CU5DOTOGSKPXFM5M","created_at":"2026-07-05T06:14:58Z"},{"alias_kind":"pith_short_8","alias_value":"CU5DOTOG","created_at":"2026-07-05T06:14:58Z"}],"graph_snapshots":[{"event_id":"sha256:7f0359d58e11f7fd4c63e020482e1ded28b21729ee54c3c21a0e4ab2c99c2813","target":"graph","created_at":"2026-07-05T06:14:58Z","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/2305.16938/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Few-shot fine-tuning and in-context learning are two alternative strategies for task adaptation of pre-trained language models. Recently, in-context learning has gained popularity over fine-tuning due to its simplicity and improved out-of-domain generalization, and because extensive evidence shows that fine-tuned models pick up on spurious correlations. Unfortunately, previous comparisons of the two approaches were done using models of different sizes. This raises the question of whether the observed weaker out-of-domain generalization of fine-tuned models is an inherent property of fine-tunin","authors_text":"Dietrich Klakow, Marius Mosbach, Shauli Ravfogel, Tiago Pimentel, Yanai Elazar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T13:55:17Z","title":"Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16938","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":"sha256:535bc0d04b6520ab8b318937b963674beccb44b7970fca80e871e8b299ac474f","target":"record","created_at":"2026-07-05T06:14:58Z","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":"2ed3d6236de250bfc22ba139a7249b7a8192ec503e16051caf211a6bd89b54f4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T13:55:17Z","title_canon_sha256":"5acf9f944c4e16a52b6f841089d126b14789eb5c3646a50cda692c66dae054be"},"schema_version":"1.0","source":{"id":"2305.16938","kind":"arxiv","version":2}},"canonical_sha256":"153a374dc6929f72b3acd3ccf9708934e32d017b6423233e98f9fb6f39124111","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"153a374dc6929f72b3acd3ccf9708934e32d017b6423233e98f9fb6f39124111","first_computed_at":"2026-07-05T06:14:58.901300Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:58.901300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jObQATR2qKi1/SjDzg1ccoWOoqHYBCXBNzCihXz/0hiC2X29ZYnViFw5rfTtx7MzVa0RFfvRudMXNqCMloA/Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:58.901728Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.16938","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:535bc0d04b6520ab8b318937b963674beccb44b7970fca80e871e8b299ac474f","sha256:7f0359d58e11f7fd4c63e020482e1ded28b21729ee54c3c21a0e4ab2c99c2813"],"state_sha256":"ba66056f8f14f57504c68195481d55bff51dc700dc6464be024a2525bee1eab6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ek06PRnUcOJoN65YP4oPtwiLAJaVy/tYecb8BLaRULqL9mM4sTgYNqVuziLkDGcFBIkhVe3STEeSBBGMldZCBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:55:41.789810Z","bundle_sha256":"3a137600c0aa3255cf124a4b690671ce2b13479447fe074655fab17b7834ce0e"}}