{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FXZNXMFWA7ABUL6DUXSNH5H5XA","short_pith_number":"pith:FXZNXMFW","schema_version":"1.0","canonical_sha256":"2df2dbb0b607c01a2fc3a5e4d3f4fdb83701e1dee2ab018b46880f03f86e79bd","source":{"kind":"arxiv","id":"2312.07405","version":1},"attestation_state":"computed","paper":{"title":"ICL Markup: Structuring In-Context Learning using Soft-Token Tags","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ashton Anderson, Marc-Etienne Brunet, Richard Zemel","submitted_at":"2023-12-12T16:25:05Z","abstract_excerpt":"Large pretrained language models (LLMs) can be rapidly adapted to a wide variety of tasks via a text-to-text approach, where the instruction and input are fed to the model in natural language. Combined with in-context learning (ICL), this paradigm is impressively flexible and powerful. However, it also burdens users with an overwhelming number of choices, many of them arbitrary. Inspired by markup languages like HTML, we contribute a method of using soft-token tags to compose prompt templates. This approach reduces arbitrary decisions and streamlines the application of ICL. Our method is a for"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2312.07405","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-12T16:25:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"67bcec5c3e387f2bf2f993c42189973f2cc7cb6e36b9645bf4c83c14cda3e2c0","abstract_canon_sha256":"1be6a15b693694e5b6f6ab539023c3a10cb66390065f5349315b1ab86ce8bf6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:23:19.242982Z","signature_b64":"pmNT6XZ1MTnIAesz3/dpONJByjE7I8/3TEpJUIpBmiEEfjgSRmUT5e56gQfzr9N87nke3v4je3gFNXveGbwECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2df2dbb0b607c01a2fc3a5e4d3f4fdb83701e1dee2ab018b46880f03f86e79bd","last_reissued_at":"2026-07-05T07:23:19.242515Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:23:19.242515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ICL Markup: Structuring In-Context Learning using Soft-Token Tags","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ashton Anderson, Marc-Etienne Brunet, Richard Zemel","submitted_at":"2023-12-12T16:25:05Z","abstract_excerpt":"Large pretrained language models (LLMs) can be rapidly adapted to a wide variety of tasks via a text-to-text approach, where the instruction and input are fed to the model in natural language. Combined with in-context learning (ICL), this paradigm is impressively flexible and powerful. However, it also burdens users with an overwhelming number of choices, many of them arbitrary. Inspired by markup languages like HTML, we contribute a method of using soft-token tags to compose prompt templates. This approach reduces arbitrary decisions and streamlines the application of ICL. Our method is a for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07405","kind":"arxiv","version":1},"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/2312.07405/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2312.07405","created_at":"2026-07-05T07:23:19.242573+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.07405v1","created_at":"2026-07-05T07:23:19.242573+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07405","created_at":"2026-07-05T07:23:19.242573+00:00"},{"alias_kind":"pith_short_12","alias_value":"FXZNXMFWA7AB","created_at":"2026-07-05T07:23:19.242573+00:00"},{"alias_kind":"pith_short_16","alias_value":"FXZNXMFWA7ABUL6D","created_at":"2026-07-05T07:23:19.242573+00:00"},{"alias_kind":"pith_short_8","alias_value":"FXZNXMFW","created_at":"2026-07-05T07:23:19.242573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2301.00234","citing_title":"A Survey on In-context Learning","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FXZNXMFWA7ABUL6DUXSNH5H5XA","json":"https://pith.science/pith/FXZNXMFWA7ABUL6DUXSNH5H5XA.json","graph_json":"https://pith.science/api/pith-number/FXZNXMFWA7ABUL6DUXSNH5H5XA/graph.json","events_json":"https://pith.science/api/pith-number/FXZNXMFWA7ABUL6DUXSNH5H5XA/events.json","paper":"https://pith.science/paper/FXZNXMFW"},"agent_actions":{"view_html":"https://pith.science/pith/FXZNXMFWA7ABUL6DUXSNH5H5XA","download_json":"https://pith.science/pith/FXZNXMFWA7ABUL6DUXSNH5H5XA.json","view_paper":"https://pith.science/paper/FXZNXMFW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.07405&json=true","fetch_graph":"https://pith.science/api/pith-number/FXZNXMFWA7ABUL6DUXSNH5H5XA/graph.json","fetch_events":"https://pith.science/api/pith-number/FXZNXMFWA7ABUL6DUXSNH5H5XA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FXZNXMFWA7ABUL6DUXSNH5H5XA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FXZNXMFWA7ABUL6DUXSNH5H5XA/action/storage_attestation","attest_author":"https://pith.science/pith/FXZNXMFWA7ABUL6DUXSNH5H5XA/action/author_attestation","sign_citation":"https://pith.science/pith/FXZNXMFWA7ABUL6DUXSNH5H5XA/action/citation_signature","submit_replication":"https://pith.science/pith/FXZNXMFWA7ABUL6DUXSNH5H5XA/action/replication_record"}},"created_at":"2026-07-05T07:23:19.242573+00:00","updated_at":"2026-07-05T07:23:19.242573+00:00"}