{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FXZNXMFWA7ABUL6DUXSNH5H5XA","short_pith_number":"pith:FXZNXMFW","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"},"canonical_sha256":"2df2dbb0b607c01a2fc3a5e4d3f4fdb83701e1dee2ab018b46880f03f86e79bd","source":{"kind":"arxiv","id":"2312.07405","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.07405","created_at":"2026-07-05T07:23:19Z"},{"alias_kind":"arxiv_version","alias_value":"2312.07405v1","created_at":"2026-07-05T07:23:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07405","created_at":"2026-07-05T07:23:19Z"},{"alias_kind":"pith_short_12","alias_value":"FXZNXMFWA7AB","created_at":"2026-07-05T07:23:19Z"},{"alias_kind":"pith_short_16","alias_value":"FXZNXMFWA7ABUL6D","created_at":"2026-07-05T07:23:19Z"},{"alias_kind":"pith_short_8","alias_value":"FXZNXMFW","created_at":"2026-07-05T07:23:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FXZNXMFWA7ABUL6DUXSNH5H5XA","target":"record","payload":{"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"},"canonical_sha256":"2df2dbb0b607c01a2fc3a5e4d3f4fdb83701e1dee2ab018b46880f03f86e79bd","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"},"source_kind":"arxiv","source_id":"2312.07405","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:23:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KTAgOAE1zZkGDuei2HUJI6C8OMgm9xRQKEA76XSoa8I54an7P4x0toMQDabjMnof1f4+XxhtbMkLqMnPeH5MDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T13:43:13.977377Z"},"content_sha256":"4f71883fb5ea94ef4c490161a567f794d57a2cf124bc3a537b1398b45e62f3fc","schema_version":"1.0","event_id":"sha256:4f71883fb5ea94ef4c490161a567f794d57a2cf124bc3a537b1398b45e62f3fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FXZNXMFWA7ABUL6DUXSNH5H5XA","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:23:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FHnu+iYaOV/VnM6cIQ72ueRm1EyyvvZzDStaolW6kisCbGymKHFL6+1HvsVil2XD6fQXxvUs334T+/OTuOWrAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T13:43:13.978227Z"},"content_sha256":"5c07fb29b497287f1859cc0502cd3f946707ee5d4025576053b2542cba84a1ce","schema_version":"1.0","event_id":"sha256:5c07fb29b497287f1859cc0502cd3f946707ee5d4025576053b2542cba84a1ce"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FXZNXMFWA7ABUL6DUXSNH5H5XA/bundle.json","state_url":"https://pith.science/pith/FXZNXMFWA7ABUL6DUXSNH5H5XA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FXZNXMFWA7ABUL6DUXSNH5H5XA/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":"2026-08-10T13:43:13Z","links":{"resolver":"https://pith.science/pith/FXZNXMFWA7ABUL6DUXSNH5H5XA","bundle":"https://pith.science/pith/FXZNXMFWA7ABUL6DUXSNH5H5XA/bundle.json","state":"https://pith.science/pith/FXZNXMFWA7ABUL6DUXSNH5H5XA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FXZNXMFWA7ABUL6DUXSNH5H5XA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FXZNXMFWA7ABUL6DUXSNH5H5XA","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":"1be6a15b693694e5b6f6ab539023c3a10cb66390065f5349315b1ab86ce8bf6c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-12T16:25:05Z","title_canon_sha256":"67bcec5c3e387f2bf2f993c42189973f2cc7cb6e36b9645bf4c83c14cda3e2c0"},"schema_version":"1.0","source":{"id":"2312.07405","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.07405","created_at":"2026-07-05T07:23:19Z"},{"alias_kind":"arxiv_version","alias_value":"2312.07405v1","created_at":"2026-07-05T07:23:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07405","created_at":"2026-07-05T07:23:19Z"},{"alias_kind":"pith_short_12","alias_value":"FXZNXMFWA7AB","created_at":"2026-07-05T07:23:19Z"},{"alias_kind":"pith_short_16","alias_value":"FXZNXMFWA7ABUL6D","created_at":"2026-07-05T07:23:19Z"},{"alias_kind":"pith_short_8","alias_value":"FXZNXMFW","created_at":"2026-07-05T07:23:19Z"}],"graph_snapshots":[{"event_id":"sha256:5c07fb29b497287f1859cc0502cd3f946707ee5d4025576053b2542cba84a1ce","target":"graph","created_at":"2026-07-05T07:23:19Z","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/2312.07405/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ashton Anderson, Marc-Etienne Brunet, Richard Zemel","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-12T16:25:05Z","title":"ICL Markup: Structuring In-Context Learning using Soft-Token Tags"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07405","kind":"arxiv","version":1},"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":"sha256:4f71883fb5ea94ef4c490161a567f794d57a2cf124bc3a537b1398b45e62f3fc","target":"record","created_at":"2026-07-05T07:23:19Z","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":"1be6a15b693694e5b6f6ab539023c3a10cb66390065f5349315b1ab86ce8bf6c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-12T16:25:05Z","title_canon_sha256":"67bcec5c3e387f2bf2f993c42189973f2cc7cb6e36b9645bf4c83c14cda3e2c0"},"schema_version":"1.0","source":{"id":"2312.07405","kind":"arxiv","version":1}},"canonical_sha256":"2df2dbb0b607c01a2fc3a5e4d3f4fdb83701e1dee2ab018b46880f03f86e79bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2df2dbb0b607c01a2fc3a5e4d3f4fdb83701e1dee2ab018b46880f03f86e79bd","first_computed_at":"2026-07-05T07:23:19.242515Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:23:19.242515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pmNT6XZ1MTnIAesz3/dpONJByjE7I8/3TEpJUIpBmiEEfjgSRmUT5e56gQfzr9N87nke3v4je3gFNXveGbwECg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:23:19.242982Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.07405","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f71883fb5ea94ef4c490161a567f794d57a2cf124bc3a537b1398b45e62f3fc","sha256:5c07fb29b497287f1859cc0502cd3f946707ee5d4025576053b2542cba84a1ce"],"state_sha256":"79203606050629c728fed24aae05aa8888d96ab03e05c89983a8572f6348aa39"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QhcPdZd6s5kolpMgaXpOwyOQFzMaCkpfVaRmr+F6hZ4aA+fJhkMsgKxjdf5dSxR/SoRpsaaMjsTYRa+TbXl8DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T13:43:13.983812Z","bundle_sha256":"867012df69a981c76ec8ea38bc84a778fb5fabd48bbf5aa1b5334e018880a51d"}}