{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:Q5BWL2UFXFXODBDUZGO65VF2YA","short_pith_number":"pith:Q5BWL2UF","canonical_record":{"source":{"id":"2309.10954","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-19T22:41:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e052a9444e14e56e35d913f967927b17b0191556e546e0294ad5c23a72260fc9","abstract_canon_sha256":"4099b160944ca9b39a41c417d539c03b8a7df7d5ebc712bd5a544538d98643f7"},"schema_version":"1.0"},"canonical_sha256":"874365ea85b96ee18474c99deed4bac012c5733e828a743dd7a319caa81b4999","source":{"kind":"arxiv","id":"2309.10954","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.10954","created_at":"2026-07-05T07:20:53Z"},{"alias_kind":"arxiv_version","alias_value":"2309.10954v2","created_at":"2026-07-05T07:20:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10954","created_at":"2026-07-05T07:20:53Z"},{"alias_kind":"pith_short_12","alias_value":"Q5BWL2UFXFXO","created_at":"2026-07-05T07:20:53Z"},{"alias_kind":"pith_short_16","alias_value":"Q5BWL2UFXFXODBDU","created_at":"2026-07-05T07:20:53Z"},{"alias_kind":"pith_short_8","alias_value":"Q5BWL2UF","created_at":"2026-07-05T07:20:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:Q5BWL2UFXFXODBDUZGO65VF2YA","target":"record","payload":{"canonical_record":{"source":{"id":"2309.10954","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-19T22:41:44Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e052a9444e14e56e35d913f967927b17b0191556e546e0294ad5c23a72260fc9","abstract_canon_sha256":"4099b160944ca9b39a41c417d539c03b8a7df7d5ebc712bd5a544538d98643f7"},"schema_version":"1.0"},"canonical_sha256":"874365ea85b96ee18474c99deed4bac012c5733e828a743dd7a319caa81b4999","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:20:53.901656Z","signature_b64":"Pl7CcPmScv1jQLGphlRhjud+Zb7qKQBs3bphunHnDsuuzrA8cWf2hLxftTzSTH3h5toa0SRzlPgu0QqqzIt3Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"874365ea85b96ee18474c99deed4bac012c5733e828a743dd7a319caa81b4999","last_reissued_at":"2026-07-05T07:20:53.901197Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:20:53.901197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.10954","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":"2026-07-05T07:20:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zDNJ6KLEm1vWSaj51rMNwywRGdb0LA8Gn0MG0NICru+oudBslDzvVPOE/3xt2xPhsi+1nKKFb7ItTxyVynEsDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T14:42:13.442783Z"},"content_sha256":"6093bbe6fa3c5f49c0724117e0619795ba599ea5b84245681732ab8e0b716f95","schema_version":"1.0","event_id":"sha256:6093bbe6fa3c5f49c0724117e0619795ba599ea5b84245681732ab8e0b716f95"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:Q5BWL2UFXFXODBDUZGO65VF2YA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"In-Context Learning for Text Classification with Many Labels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aristides Milios, Dzmitry Bahdanau, Siva Reddy","submitted_at":"2023-09-19T22:41:44Z","abstract_excerpt":"In-context learning (ICL) using large language models for tasks with many labels is challenging due to the limited context window, which makes it difficult to fit a sufficient number of examples in the prompt. In this paper, we use a pre-trained dense retrieval model to bypass this limitation, giving the model only a partial view of the full label space for each inference call. Testing with recent open-source LLMs (OPT, LLaMA), we set new state of the art performance in few-shot settings for three common intent classification datasets, with no finetuning. We also surpass fine-tuned performance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10954","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/2309.10954/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":"2026-07-05T07:20:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K7gqL+IrVu46ZO0U9vdXNMVNvCWBzDz2qp2pE/qP7cs9ZW0m1eWnqjS1x0JSTLuFXBlGdv+6MLnsGSgM5LQ2Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T14:42:13.443721Z"},"content_sha256":"92ed8b6327604db982d8a3591aefa775b2b0bb180ca76fa64ad80efdab31f765","schema_version":"1.0","event_id":"sha256:92ed8b6327604db982d8a3591aefa775b2b0bb180ca76fa64ad80efdab31f765"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q5BWL2UFXFXODBDUZGO65VF2YA/bundle.json","state_url":"https://pith.science/pith/Q5BWL2UFXFXODBDUZGO65VF2YA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q5BWL2UFXFXODBDUZGO65VF2YA/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":"2026-08-20T14:42:13Z","links":{"resolver":"https://pith.science/pith/Q5BWL2UFXFXODBDUZGO65VF2YA","bundle":"https://pith.science/pith/Q5BWL2UFXFXODBDUZGO65VF2YA/bundle.json","state":"https://pith.science/pith/Q5BWL2UFXFXODBDUZGO65VF2YA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q5BWL2UFXFXODBDUZGO65VF2YA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Q5BWL2UFXFXODBDUZGO65VF2YA","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":"4099b160944ca9b39a41c417d539c03b8a7df7d5ebc712bd5a544538d98643f7","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-19T22:41:44Z","title_canon_sha256":"e052a9444e14e56e35d913f967927b17b0191556e546e0294ad5c23a72260fc9"},"schema_version":"1.0","source":{"id":"2309.10954","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.10954","created_at":"2026-07-05T07:20:53Z"},{"alias_kind":"arxiv_version","alias_value":"2309.10954v2","created_at":"2026-07-05T07:20:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.10954","created_at":"2026-07-05T07:20:53Z"},{"alias_kind":"pith_short_12","alias_value":"Q5BWL2UFXFXO","created_at":"2026-07-05T07:20:53Z"},{"alias_kind":"pith_short_16","alias_value":"Q5BWL2UFXFXODBDU","created_at":"2026-07-05T07:20:53Z"},{"alias_kind":"pith_short_8","alias_value":"Q5BWL2UF","created_at":"2026-07-05T07:20:53Z"}],"graph_snapshots":[{"event_id":"sha256:92ed8b6327604db982d8a3591aefa775b2b0bb180ca76fa64ad80efdab31f765","target":"graph","created_at":"2026-07-05T07:20:53Z","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/2309.10954/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In-context learning (ICL) using large language models for tasks with many labels is challenging due to the limited context window, which makes it difficult to fit a sufficient number of examples in the prompt. In this paper, we use a pre-trained dense retrieval model to bypass this limitation, giving the model only a partial view of the full label space for each inference call. Testing with recent open-source LLMs (OPT, LLaMA), we set new state of the art performance in few-shot settings for three common intent classification datasets, with no finetuning. We also surpass fine-tuned performance","authors_text":"Aristides Milios, Dzmitry Bahdanau, Siva Reddy","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-19T22:41:44Z","title":"In-Context Learning for Text Classification with Many Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.10954","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":"sha256:6093bbe6fa3c5f49c0724117e0619795ba599ea5b84245681732ab8e0b716f95","target":"record","created_at":"2026-07-05T07:20:53Z","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":"4099b160944ca9b39a41c417d539c03b8a7df7d5ebc712bd5a544538d98643f7","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-09-19T22:41:44Z","title_canon_sha256":"e052a9444e14e56e35d913f967927b17b0191556e546e0294ad5c23a72260fc9"},"schema_version":"1.0","source":{"id":"2309.10954","kind":"arxiv","version":2}},"canonical_sha256":"874365ea85b96ee18474c99deed4bac012c5733e828a743dd7a319caa81b4999","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"874365ea85b96ee18474c99deed4bac012c5733e828a743dd7a319caa81b4999","first_computed_at":"2026-07-05T07:20:53.901197Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:20:53.901197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Pl7CcPmScv1jQLGphlRhjud+Zb7qKQBs3bphunHnDsuuzrA8cWf2hLxftTzSTH3h5toa0SRzlPgu0QqqzIt3Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:20:53.901656Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.10954","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6093bbe6fa3c5f49c0724117e0619795ba599ea5b84245681732ab8e0b716f95","sha256:92ed8b6327604db982d8a3591aefa775b2b0bb180ca76fa64ad80efdab31f765"],"state_sha256":"2029643e183111a4393228832feea4c1ec86c1b43e2e08408722aa41d60d9840"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O/PYwWOTfTwP/j/+mDiETEDyG0GHn15ZgfoJyWX13nDCFue48ZFGtjU1MZAYqcRRpvFDnkvye8+8pyDPo7owDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T14:42:13.449438Z","bundle_sha256":"92f718064e609cadd20ae4bc770ec7eb2c177ebc0e95e71a14bf4082f6ba63a3"}}