{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6VG6X7P6YZZMMUI6ZL346R2A2N","short_pith_number":"pith:6VG6X7P6","canonical_record":{"source":{"id":"2607.10016","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-10T22:36:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f5abae41461f54a6ae4c3ad07d6b5e33f49d8219587d103fb3473f857c8adf93","abstract_canon_sha256":"92b6c86d73aa0f1852b610239cc09bdfce9cd3d6ae8bc40a837f87467bd861dd"},"schema_version":"1.0"},"canonical_sha256":"f54debfdfec672c6511ecaf7cf4740d357d21ae8109556a9763aa42a7791616e","source":{"kind":"arxiv","id":"2607.10016","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.10016","created_at":"2026-07-14T00:18:47Z"},{"alias_kind":"arxiv_version","alias_value":"2607.10016v1","created_at":"2026-07-14T00:18:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10016","created_at":"2026-07-14T00:18:47Z"},{"alias_kind":"pith_short_12","alias_value":"6VG6X7P6YZZM","created_at":"2026-07-14T00:18:47Z"},{"alias_kind":"pith_short_16","alias_value":"6VG6X7P6YZZMMUI6","created_at":"2026-07-14T00:18:47Z"},{"alias_kind":"pith_short_8","alias_value":"6VG6X7P6","created_at":"2026-07-14T00:18:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6VG6X7P6YZZMMUI6ZL346R2A2N","target":"record","payload":{"canonical_record":{"source":{"id":"2607.10016","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-10T22:36:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f5abae41461f54a6ae4c3ad07d6b5e33f49d8219587d103fb3473f857c8adf93","abstract_canon_sha256":"92b6c86d73aa0f1852b610239cc09bdfce9cd3d6ae8bc40a837f87467bd861dd"},"schema_version":"1.0"},"canonical_sha256":"f54debfdfec672c6511ecaf7cf4740d357d21ae8109556a9763aa42a7791616e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T00:18:47.727926Z","signature_b64":"vUwSRtw133Kf8eDtCirKpkL45kYqBKrxWi9hF6SDJH6ko+u69QXKZZHwA1Qxxp06JyauD7+2TUAzsEsIKMzGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f54debfdfec672c6511ecaf7cf4740d357d21ae8109556a9763aa42a7791616e","last_reissued_at":"2026-07-14T00:18:47.727149Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T00:18:47.727149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.10016","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":"2026-07-14T00:18:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QBfXPYXh0fN8qSAt5RGrAUv+RcltGHvxPMwiJz2ou2RXVybYY1FGrGWSDu+N6KvYcnYWDGF0YsUR4AuKZS1nBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:13:30.627366Z"},"content_sha256":"e4186e62e174820769352b2b74b8abaf0a7f2e2e0111c261e77558c0f729d0d8","schema_version":"1.0","event_id":"sha256:e4186e62e174820769352b2b74b8abaf0a7f2e2e0111c261e77558c0f729d0d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6VG6X7P6YZZMMUI6ZL346R2A2N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tokenizing Numerical and Embedding Features for LLM RecSys","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Anil Ramakrishna, Ankit Peshin, Carl Hu, Chiyu Zhang, Feng Qi, Johnson Lui, Justin Johnson, Kaushik Rangadurai, Luke Simon, Zhe Xu","submitted_at":"2026-07-10T22:36:13Z","abstract_excerpt":"Large language models (LLMs) are increasingly used as backbone architectures for recommender systems because of their strong sequence modeling and representation learning capabilities. However, most LLM-based recommenders operate primarily on discrete textual tokens, whereas practical recommendation pipelines also rely on continuous numerical features and dense embedding features produced by upstream feature engineering or pretrained encoders. This mismatch limits the ability of LLM-based models to exploit fine-grained non-textual signals. We propose a soft-token fusion framework that maps num"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10016","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/2607.10016/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":"2026-07-14T00:18:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sxrmay8jiP5+KbXanNN1LK+TX90Zl27eN/XnGnDvLqS8A0ibAdW1Nr4EPo1M/5mZr6oFyh65uyMs8ojVY0BbDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:13:30.627845Z"},"content_sha256":"e7a60c391dcf297584f32197a012fabe3e112bd933bb3dc70207392bf4f779d8","schema_version":"1.0","event_id":"sha256:e7a60c391dcf297584f32197a012fabe3e112bd933bb3dc70207392bf4f779d8"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:6VG6X7P6YZZMMUI6ZL346R2A2N","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1109/ICDM.2018.00035.Brian) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"doi: 10.1109/ICDM. 2018.00035. Brian Lester, Rami Al-Rfou, and Noah Constant. The power of scale for parameter-efficient prompt tuning. InProceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 3045–3059,","arxiv_id":"2607.10016","detector":"doi_compliance","evidence":{"ref_index":8,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"doi: 10.1109/ICDM. 2018.00035. Brian Lester, Rami Al-Rfou, and Noah Constant. The power of scale for parameter-efficient prompt tuning. InProceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 3045–3059,","reconstructed_doi":"10.1109/ICDM.2018.00035.Brian"},"severity":"advisory","ref_index":8,"audited_at":"2026-07-14T01:03:10.525421Z","event_type":"pith.integrity.v1","detected_doi":"10.1109/ICDM.2018.00035.Brian","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"711643ae5935b9fb78b6492b8592ecb36f9acbb337ee63208e575e0e50e48380","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.0.0","detected_arxiv_id":null,"integrity_event_id":13095,"payload_sha256":"7917abb5d8a447fd3606c0b88ac4104a52b43cbb18c9e0007dd05c0bb43cf1c3","signature_b64":"lX+STivdEyyGfgsj0Tq25PNEbSghWY9wrM7mAf3FV8K9W1b4v7EyvTmg2tfOrky4dX1rlSfY5oa08k+PxCaBBQ==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-14T01:05:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J84f5QylfgRSS8azFjnbz+1nu7xrGJXaDV3eWPd2BpdaQLTM6b1u7YVQMHdt0yAE5BvG5FVeORtehw/9el3IDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:13:30.630145Z"},"content_sha256":"e7716a8f924fdf4a2e2f7aff8d9e515fd921723070f9351f16e8c2276d72d2db","schema_version":"1.0","event_id":"sha256:e7716a8f924fdf4a2e2f7aff8d9e515fd921723070f9351f16e8c2276d72d2db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6VG6X7P6YZZMMUI6ZL346R2A2N/bundle.json","state_url":"https://pith.science/pith/6VG6X7P6YZZMMUI6ZL346R2A2N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6VG6X7P6YZZMMUI6ZL346R2A2N/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":"2026-08-05T07:13:30Z","links":{"resolver":"https://pith.science/pith/6VG6X7P6YZZMMUI6ZL346R2A2N","bundle":"https://pith.science/pith/6VG6X7P6YZZMMUI6ZL346R2A2N/bundle.json","state":"https://pith.science/pith/6VG6X7P6YZZMMUI6ZL346R2A2N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6VG6X7P6YZZMMUI6ZL346R2A2N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6VG6X7P6YZZMMUI6ZL346R2A2N","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"92b6c86d73aa0f1852b610239cc09bdfce9cd3d6ae8bc40a837f87467bd861dd","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-10T22:36:13Z","title_canon_sha256":"f5abae41461f54a6ae4c3ad07d6b5e33f49d8219587d103fb3473f857c8adf93"},"schema_version":"1.0","source":{"id":"2607.10016","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.10016","created_at":"2026-07-14T00:18:47Z"},{"alias_kind":"arxiv_version","alias_value":"2607.10016v1","created_at":"2026-07-14T00:18:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10016","created_at":"2026-07-14T00:18:47Z"},{"alias_kind":"pith_short_12","alias_value":"6VG6X7P6YZZM","created_at":"2026-07-14T00:18:47Z"},{"alias_kind":"pith_short_16","alias_value":"6VG6X7P6YZZMMUI6","created_at":"2026-07-14T00:18:47Z"},{"alias_kind":"pith_short_8","alias_value":"6VG6X7P6","created_at":"2026-07-14T00:18:47Z"}],"graph_snapshots":[{"event_id":"sha256:e7a60c391dcf297584f32197a012fabe3e112bd933bb3dc70207392bf4f779d8","target":"graph","created_at":"2026-07-14T00:18:47Z","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/2607.10016/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly used as backbone architectures for recommender systems because of their strong sequence modeling and representation learning capabilities. However, most LLM-based recommenders operate primarily on discrete textual tokens, whereas practical recommendation pipelines also rely on continuous numerical features and dense embedding features produced by upstream feature engineering or pretrained encoders. This mismatch limits the ability of LLM-based models to exploit fine-grained non-textual signals. We propose a soft-token fusion framework that maps num","authors_text":"Anil Ramakrishna, Ankit Peshin, Carl Hu, Chiyu Zhang, Feng Qi, Johnson Lui, Justin Johnson, Kaushik Rangadurai, Luke Simon, Zhe Xu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-10T22:36:13Z","title":"Tokenizing Numerical and Embedding Features for LLM RecSys"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10016","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:e4186e62e174820769352b2b74b8abaf0a7f2e2e0111c261e77558c0f729d0d8","target":"record","created_at":"2026-07-14T00:18:47Z","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":"92b6c86d73aa0f1852b610239cc09bdfce9cd3d6ae8bc40a837f87467bd861dd","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-10T22:36:13Z","title_canon_sha256":"f5abae41461f54a6ae4c3ad07d6b5e33f49d8219587d103fb3473f857c8adf93"},"schema_version":"1.0","source":{"id":"2607.10016","kind":"arxiv","version":1}},"canonical_sha256":"f54debfdfec672c6511ecaf7cf4740d357d21ae8109556a9763aa42a7791616e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f54debfdfec672c6511ecaf7cf4740d357d21ae8109556a9763aa42a7791616e","first_computed_at":"2026-07-14T00:18:47.727149Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T00:18:47.727149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vUwSRtw133Kf8eDtCirKpkL45kYqBKrxWi9hF6SDJH6ko+u69QXKZZHwA1Qxxp06JyauD7+2TUAzsEsIKMzGBw==","signature_status":"signed_v1","signed_at":"2026-07-14T00:18:47.727926Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.10016","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4186e62e174820769352b2b74b8abaf0a7f2e2e0111c261e77558c0f729d0d8","sha256:e7a60c391dcf297584f32197a012fabe3e112bd933bb3dc70207392bf4f779d8","sha256:e7716a8f924fdf4a2e2f7aff8d9e515fd921723070f9351f16e8c2276d72d2db"],"state_sha256":"ebd405fcb3ffd78823c479bf9eff979ae5f9dd317b801313c005437b0745430d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y3SYwbsCTvi4unSz75GjSDk8Mm5oHCWR7iksksDL3OTclXAtkTXWgWW5uCalLpEYRJiNto32sZJu1OD5fBFfDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T07:13:30.632372Z","bundle_sha256":"f166519b50d8ae12ac9e2ffe991147b118ed8e31a381d07a1c74993b75946c35"}}