{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MBY5QSUJGOPSVKGSX6O37FIPDF","short_pith_number":"pith:MBY5QSUJ","canonical_record":{"source":{"id":"2403.06402","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T03:28:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e48aa83ab9965988612f3c5946f354b3319df3acc3e67981c150f46b44b5d2c1","abstract_canon_sha256":"d7a13c4811f6bba91b9a95c78487b04e65f86e6d82022fe8c73228288dcdff51"},"schema_version":"1.0"},"canonical_sha256":"6071d84a89339f2aa8d2bf9dbf950f1956d9cd2573e19bfcf5694258de7f1a49","source":{"kind":"arxiv","id":"2403.06402","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06402","created_at":"2026-07-05T10:02:44Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06402v3","created_at":"2026-07-05T10:02:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06402","created_at":"2026-07-05T10:02:44Z"},{"alias_kind":"pith_short_12","alias_value":"MBY5QSUJGOPS","created_at":"2026-07-05T10:02:44Z"},{"alias_kind":"pith_short_16","alias_value":"MBY5QSUJGOPSVKGS","created_at":"2026-07-05T10:02:44Z"},{"alias_kind":"pith_short_8","alias_value":"MBY5QSUJ","created_at":"2026-07-05T10:02:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MBY5QSUJGOPSVKGSX6O37FIPDF","target":"record","payload":{"canonical_record":{"source":{"id":"2403.06402","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T03:28:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e48aa83ab9965988612f3c5946f354b3319df3acc3e67981c150f46b44b5d2c1","abstract_canon_sha256":"d7a13c4811f6bba91b9a95c78487b04e65f86e6d82022fe8c73228288dcdff51"},"schema_version":"1.0"},"canonical_sha256":"6071d84a89339f2aa8d2bf9dbf950f1956d9cd2573e19bfcf5694258de7f1a49","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:44.218090Z","signature_b64":"mdsKetJAqvyTqp7LTL5x7P+zJtHgy+qkqXu0ArEMFVi6YEcW5ND0xMo1E93uBe4BVuA2nm2sEmJjdA6N3nRxDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6071d84a89339f2aa8d2bf9dbf950f1956d9cd2573e19bfcf5694258de7f1a49","last_reissued_at":"2026-07-05T10:02:44.217645Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:44.217645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.06402","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":"2026-07-05T10:02:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bBsNqRbnR6CM0AEUEiieKbFOi3MPaQPslJCUX0L+3P4zLbCPKd0CiSnqzc683T2wGQHCWti7pE8VGKkpsOkNCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T07:30:06.119802Z"},"content_sha256":"25bcdcf986b591533396edb3e36208b7dacebcff58bc699f69e3311fd68581f5","schema_version":"1.0","event_id":"sha256:25bcdcf986b591533396edb3e36208b7dacebcff58bc699f69e3311fd68581f5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MBY5QSUJGOPSVKGSX6O37FIPDF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"One size doesn't fit all: Predicting the Number of Examples for In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Debasis Ganguly, Iadh Ounis, Manish Chandra","submitted_at":"2024-03-11T03:28:13Z","abstract_excerpt":"In-context learning (ICL) refers to the process of adding a small number of localized examples from a training set of labelled data to an LLM's prompt with an objective to effectively control the generative process seeking to improve the downstream task performance. Existing ICL approaches use an identical number of examples (a pre-configured hyper-parameter) for each data instance. Our work alleviates the limitations of this 'one fits all' approach by dynamically predicting the number of examples for each data instance to be used in few-shot inference with LLMs. In particular, we employ a mul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06402","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/2403.06402/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":"2026-07-05T10:02:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LBu8KjgbkG1jtnd3g/FaexiAwOucYS57f/mVBxpuuNJ5TawXMIDckitF7DaXtzRE1LNgTLfFQkyVmesjMifOBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T07:30:06.120420Z"},"content_sha256":"eb62eab155a806703007589099c1b1e69f527ce4478b6dd99bf0a25eca626f2d","schema_version":"1.0","event_id":"sha256:eb62eab155a806703007589099c1b1e69f527ce4478b6dd99bf0a25eca626f2d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MBY5QSUJGOPSVKGSX6O37FIPDF/bundle.json","state_url":"https://pith.science/pith/MBY5QSUJGOPSVKGSX6O37FIPDF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MBY5QSUJGOPSVKGSX6O37FIPDF/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":"2026-08-20T07:30:06Z","links":{"resolver":"https://pith.science/pith/MBY5QSUJGOPSVKGSX6O37FIPDF","bundle":"https://pith.science/pith/MBY5QSUJGOPSVKGSX6O37FIPDF/bundle.json","state":"https://pith.science/pith/MBY5QSUJGOPSVKGSX6O37FIPDF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MBY5QSUJGOPSVKGSX6O37FIPDF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MBY5QSUJGOPSVKGSX6O37FIPDF","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":"d7a13c4811f6bba91b9a95c78487b04e65f86e6d82022fe8c73228288dcdff51","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T03:28:13Z","title_canon_sha256":"e48aa83ab9965988612f3c5946f354b3319df3acc3e67981c150f46b44b5d2c1"},"schema_version":"1.0","source":{"id":"2403.06402","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06402","created_at":"2026-07-05T10:02:44Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06402v3","created_at":"2026-07-05T10:02:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06402","created_at":"2026-07-05T10:02:44Z"},{"alias_kind":"pith_short_12","alias_value":"MBY5QSUJGOPS","created_at":"2026-07-05T10:02:44Z"},{"alias_kind":"pith_short_16","alias_value":"MBY5QSUJGOPSVKGS","created_at":"2026-07-05T10:02:44Z"},{"alias_kind":"pith_short_8","alias_value":"MBY5QSUJ","created_at":"2026-07-05T10:02:44Z"}],"graph_snapshots":[{"event_id":"sha256:eb62eab155a806703007589099c1b1e69f527ce4478b6dd99bf0a25eca626f2d","target":"graph","created_at":"2026-07-05T10:02:44Z","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/2403.06402/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In-context learning (ICL) refers to the process of adding a small number of localized examples from a training set of labelled data to an LLM's prompt with an objective to effectively control the generative process seeking to improve the downstream task performance. Existing ICL approaches use an identical number of examples (a pre-configured hyper-parameter) for each data instance. Our work alleviates the limitations of this 'one fits all' approach by dynamically predicting the number of examples for each data instance to be used in few-shot inference with LLMs. In particular, we employ a mul","authors_text":"Debasis Ganguly, Iadh Ounis, Manish Chandra","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T03:28:13Z","title":"One size doesn't fit all: Predicting the Number of Examples for In-Context Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06402","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":"sha256:25bcdcf986b591533396edb3e36208b7dacebcff58bc699f69e3311fd68581f5","target":"record","created_at":"2026-07-05T10:02:44Z","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":"d7a13c4811f6bba91b9a95c78487b04e65f86e6d82022fe8c73228288dcdff51","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T03:28:13Z","title_canon_sha256":"e48aa83ab9965988612f3c5946f354b3319df3acc3e67981c150f46b44b5d2c1"},"schema_version":"1.0","source":{"id":"2403.06402","kind":"arxiv","version":3}},"canonical_sha256":"6071d84a89339f2aa8d2bf9dbf950f1956d9cd2573e19bfcf5694258de7f1a49","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6071d84a89339f2aa8d2bf9dbf950f1956d9cd2573e19bfcf5694258de7f1a49","first_computed_at":"2026-07-05T10:02:44.217645Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:44.217645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mdsKetJAqvyTqp7LTL5x7P+zJtHgy+qkqXu0ArEMFVi6YEcW5ND0xMo1E93uBe4BVuA2nm2sEmJjdA6N3nRxDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:44.218090Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.06402","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:25bcdcf986b591533396edb3e36208b7dacebcff58bc699f69e3311fd68581f5","sha256:eb62eab155a806703007589099c1b1e69f527ce4478b6dd99bf0a25eca626f2d"],"state_sha256":"8dcd7557c6752b193c432b01181ac1e52f3d849cb06258e35451416aeb5c1611"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oQ9uNnCXVPdvXD0WK1FPkxfiNRiK+qYq1e8jBZ8o05xXQdanSQA3xqch+jdJa1COzXI029GqXFUsn01puujPBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T07:30:06.126633Z","bundle_sha256":"6e950bccb84e044d5863491a23306915b1fd6a16b595dcc943865aca6840faa5"}}