{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KF4OG6VXRYTBTH6BLBTO2W3XOY","short_pith_number":"pith:KF4OG6VX","canonical_record":{"source":{"id":"2411.14708","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T03:33:51Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"43e563458670bb9cd51ac0cab47191096880d04f9e4c118c5c802d337fc82d9e","abstract_canon_sha256":"2d81c56ad067e15fb1dbfe2bada261cc42cd673400f21f6d2be85fd9ff371aaf"},"schema_version":"1.0"},"canonical_sha256":"5178e37ab78e26199fc15866ed5b77761e4e45885b4a5c42e78e6931fa38188a","source":{"kind":"arxiv","id":"2411.14708","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14708","created_at":"2026-07-05T10:14:48Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14708v3","created_at":"2026-07-05T10:14:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14708","created_at":"2026-07-05T10:14:48Z"},{"alias_kind":"pith_short_12","alias_value":"KF4OG6VXRYTB","created_at":"2026-07-05T10:14:48Z"},{"alias_kind":"pith_short_16","alias_value":"KF4OG6VXRYTBTH6B","created_at":"2026-07-05T10:14:48Z"},{"alias_kind":"pith_short_8","alias_value":"KF4OG6VX","created_at":"2026-07-05T10:14:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KF4OG6VXRYTBTH6BLBTO2W3XOY","target":"record","payload":{"canonical_record":{"source":{"id":"2411.14708","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T03:33:51Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"43e563458670bb9cd51ac0cab47191096880d04f9e4c118c5c802d337fc82d9e","abstract_canon_sha256":"2d81c56ad067e15fb1dbfe2bada261cc42cd673400f21f6d2be85fd9ff371aaf"},"schema_version":"1.0"},"canonical_sha256":"5178e37ab78e26199fc15866ed5b77761e4e45885b4a5c42e78e6931fa38188a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:48.225916Z","signature_b64":"worwAVKQwMQxFoDnRRnyWjLkahyL0aYGm11Rqk2vNJk54cuEvAUca9S14vrP7YvZNkszYzkvwjAnmkWXiHLBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5178e37ab78e26199fc15866ed5b77761e4e45885b4a5c42e78e6931fa38188a","last_reissued_at":"2026-07-05T10:14:48.225498Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:48.225498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.14708","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":"2026-07-05T10:14:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RhQw7TLK+32BjGx4D3M2pU4VVwosvXRYN3UhgpjjVyMZD+aETgnoFjRyc21LpY9YgEsNPHJbLpfUqAJrzIecDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:19:41.317054Z"},"content_sha256":"ea32930e40a394f7ec485f6a30d809d986ae789f4bb558f8a5575772ab5ccc4d","schema_version":"1.0","event_id":"sha256:ea32930e40a394f7ec485f6a30d809d986ae789f4bb558f8a5575772ab5ccc4d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KF4OG6VXRYTBTH6BLBTO2W3XOY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding LLM Embeddings for Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Bangding Yang, Eric Tang, Xingyou Song","submitted_at":"2024-11-22T03:33:51Z","abstract_excerpt":"With the rise of large language models (LLMs) for flexibly processing information as strings, a natural application is regression, specifically by preprocessing string representations into LLM embeddings as downstream features for metric prediction. In this paper, we provide one of the first comprehensive investigations into embedding-based regression and demonstrate that LLM embeddings as features can be better for high-dimensional regression tasks than using traditional feature engineering. This regression performance can be explained in part due to LLM embeddings over numeric data inherentl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14708","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/2411.14708/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":"2026-07-05T10:14:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f11dYIiOdqZYJt66DvgVHbb2KXNETTuTLvIAHtokdJdlNtmeYHY2WRWgRzp0V4/bpNu7LukbMMom9W39Sst9Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T11:19:41.317909Z"},"content_sha256":"1c82c5f6cb0e08f2d282f6509e7a9fdd3c227e5aa2d9924fb67a5013eefece6c","schema_version":"1.0","event_id":"sha256:1c82c5f6cb0e08f2d282f6509e7a9fdd3c227e5aa2d9924fb67a5013eefece6c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KF4OG6VXRYTBTH6BLBTO2W3XOY/bundle.json","state_url":"https://pith.science/pith/KF4OG6VXRYTBTH6BLBTO2W3XOY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KF4OG6VXRYTBTH6BLBTO2W3XOY/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":"2026-08-10T11:19:41Z","links":{"resolver":"https://pith.science/pith/KF4OG6VXRYTBTH6BLBTO2W3XOY","bundle":"https://pith.science/pith/KF4OG6VXRYTBTH6BLBTO2W3XOY/bundle.json","state":"https://pith.science/pith/KF4OG6VXRYTBTH6BLBTO2W3XOY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KF4OG6VXRYTBTH6BLBTO2W3XOY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KF4OG6VXRYTBTH6BLBTO2W3XOY","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":"2d81c56ad067e15fb1dbfe2bada261cc42cd673400f21f6d2be85fd9ff371aaf","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T03:33:51Z","title_canon_sha256":"43e563458670bb9cd51ac0cab47191096880d04f9e4c118c5c802d337fc82d9e"},"schema_version":"1.0","source":{"id":"2411.14708","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14708","created_at":"2026-07-05T10:14:48Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14708v3","created_at":"2026-07-05T10:14:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14708","created_at":"2026-07-05T10:14:48Z"},{"alias_kind":"pith_short_12","alias_value":"KF4OG6VXRYTB","created_at":"2026-07-05T10:14:48Z"},{"alias_kind":"pith_short_16","alias_value":"KF4OG6VXRYTBTH6B","created_at":"2026-07-05T10:14:48Z"},{"alias_kind":"pith_short_8","alias_value":"KF4OG6VX","created_at":"2026-07-05T10:14:48Z"}],"graph_snapshots":[{"event_id":"sha256:1c82c5f6cb0e08f2d282f6509e7a9fdd3c227e5aa2d9924fb67a5013eefece6c","target":"graph","created_at":"2026-07-05T10:14:48Z","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/2411.14708/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the rise of large language models (LLMs) for flexibly processing information as strings, a natural application is regression, specifically by preprocessing string representations into LLM embeddings as downstream features for metric prediction. In this paper, we provide one of the first comprehensive investigations into embedding-based regression and demonstrate that LLM embeddings as features can be better for high-dimensional regression tasks than using traditional feature engineering. This regression performance can be explained in part due to LLM embeddings over numeric data inherentl","authors_text":"Bangding Yang, Eric Tang, Xingyou Song","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T03:33:51Z","title":"Understanding LLM Embeddings for Regression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14708","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:ea32930e40a394f7ec485f6a30d809d986ae789f4bb558f8a5575772ab5ccc4d","target":"record","created_at":"2026-07-05T10:14:48Z","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":"2d81c56ad067e15fb1dbfe2bada261cc42cd673400f21f6d2be85fd9ff371aaf","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T03:33:51Z","title_canon_sha256":"43e563458670bb9cd51ac0cab47191096880d04f9e4c118c5c802d337fc82d9e"},"schema_version":"1.0","source":{"id":"2411.14708","kind":"arxiv","version":3}},"canonical_sha256":"5178e37ab78e26199fc15866ed5b77761e4e45885b4a5c42e78e6931fa38188a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5178e37ab78e26199fc15866ed5b77761e4e45885b4a5c42e78e6931fa38188a","first_computed_at":"2026-07-05T10:14:48.225498Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:48.225498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"worwAVKQwMQxFoDnRRnyWjLkahyL0aYGm11Rqk2vNJk54cuEvAUca9S14vrP7YvZNkszYzkvwjAnmkWXiHLBBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:48.225916Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14708","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea32930e40a394f7ec485f6a30d809d986ae789f4bb558f8a5575772ab5ccc4d","sha256:1c82c5f6cb0e08f2d282f6509e7a9fdd3c227e5aa2d9924fb67a5013eefece6c"],"state_sha256":"17b6d5303ced6566dd2e6c831ab1893d4d97e495bdb158aa6a5b4602d212edbb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VXFps1ce6gkLUv61toHoISNAKm9LCGYW8X56o1C7ngkj9Toh++1xddefGOqTUf60H4cH0HAAU5Tef//ojNVJBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T11:19:41.323610Z","bundle_sha256":"41e1b2903e6e39799dec8dae58e08afa2aa5e8b9b65850eb9b37e16dd47431f4"}}