{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:3LX4Q7U4HOK2RMA3DKFNFVVO6B","short_pith_number":"pith:3LX4Q7U4","canonical_record":{"source":{"id":"2304.04576","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-10T13:28:35Z","cross_cats_sorted":[],"title_canon_sha256":"4e735deee764322dddc7785704518032518234330d9151822a3c2959cf7044ac","abstract_canon_sha256":"bc55a15e461f41338879e8bf33fae5a6822a4782286c36306da8f45fee6b7b61"},"schema_version":"1.0"},"canonical_sha256":"daefc87e9c3b95a8b01b1a8ad2d6aef050f38866de9b00b53ae7d229739a0665","source":{"kind":"arxiv","id":"2304.04576","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.04576","created_at":"2026-07-05T05:59:27Z"},{"alias_kind":"arxiv_version","alias_value":"2304.04576v1","created_at":"2026-07-05T05:59:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04576","created_at":"2026-07-05T05:59:27Z"},{"alias_kind":"pith_short_12","alias_value":"3LX4Q7U4HOK2","created_at":"2026-07-05T05:59:27Z"},{"alias_kind":"pith_short_16","alias_value":"3LX4Q7U4HOK2RMA3","created_at":"2026-07-05T05:59:27Z"},{"alias_kind":"pith_short_8","alias_value":"3LX4Q7U4","created_at":"2026-07-05T05:59:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:3LX4Q7U4HOK2RMA3DKFNFVVO6B","target":"record","payload":{"canonical_record":{"source":{"id":"2304.04576","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-10T13:28:35Z","cross_cats_sorted":[],"title_canon_sha256":"4e735deee764322dddc7785704518032518234330d9151822a3c2959cf7044ac","abstract_canon_sha256":"bc55a15e461f41338879e8bf33fae5a6822a4782286c36306da8f45fee6b7b61"},"schema_version":"1.0"},"canonical_sha256":"daefc87e9c3b95a8b01b1a8ad2d6aef050f38866de9b00b53ae7d229739a0665","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:27.621856Z","signature_b64":"Tx/pbKS9uAi6wxaWcFBCmRzHilo1aRkkbgx0TyGC6uKWYmuMd+m7mnRB8XF856bast/RPlytncaxouJMIWTkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"daefc87e9c3b95a8b01b1a8ad2d6aef050f38866de9b00b53ae7d229739a0665","last_reissued_at":"2026-07-05T05:59:27.621374Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:27.621374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.04576","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":"2026-07-05T05:59:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qcOPmKB+FiOL98FtcK97Cc+QcpBqbOAsnTicsOBXMmu4tM1A/5lqG4nV3KjlrieYb4sc5q8KoI8mQ2iuHWiXAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T15:15:17.423293Z"},"content_sha256":"e907fd8a6b29f9dff638496a78b4a02ec38e0db798dc6b8268c7aee00eaf2f68","schema_version":"1.0","event_id":"sha256:e907fd8a6b29f9dff638496a78b4a02ec38e0db798dc6b8268c7aee00eaf2f68"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:3LX4Q7U4HOK2RMA3DKFNFVVO6B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learnings from Data Integration for Augmented Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alon Halevy, Jane Dwivedi-Yu","submitted_at":"2023-04-10T13:28:35Z","abstract_excerpt":"One of the limitations of large language models is that they do not have access to up-to-date, proprietary or personal data. As a result, there are multiple efforts to extend language models with techniques for accessing external data. In that sense, LLMs share the vision of data integration systems whose goal is to provide seamless access to a large collection of heterogeneous data sources. While the details and the techniques of LLMs differ greatly from those of data integration, this paper shows that some of the lessons learned from research on data integration can elucidate the research pa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04576","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/2304.04576/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":"2026-07-05T05:59:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"olIp37YMHe1ccmHJhKJKRa1TZM6md2WJdYo4nvBkEtIi9y7hL3Rm/0WrQJAumYx9SJyRsW8NgU2BIV7Dt9SqBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T15:15:17.424182Z"},"content_sha256":"d99ff33f7f433fbb637655122d53d16614eb3900ec555bf51e029e12022a0e50","schema_version":"1.0","event_id":"sha256:d99ff33f7f433fbb637655122d53d16614eb3900ec555bf51e029e12022a0e50"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3LX4Q7U4HOK2RMA3DKFNFVVO6B/bundle.json","state_url":"https://pith.science/pith/3LX4Q7U4HOK2RMA3DKFNFVVO6B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3LX4Q7U4HOK2RMA3DKFNFVVO6B/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":"2026-08-21T15:15:17Z","links":{"resolver":"https://pith.science/pith/3LX4Q7U4HOK2RMA3DKFNFVVO6B","bundle":"https://pith.science/pith/3LX4Q7U4HOK2RMA3DKFNFVVO6B/bundle.json","state":"https://pith.science/pith/3LX4Q7U4HOK2RMA3DKFNFVVO6B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3LX4Q7U4HOK2RMA3DKFNFVVO6B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3LX4Q7U4HOK2RMA3DKFNFVVO6B","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":"bc55a15e461f41338879e8bf33fae5a6822a4782286c36306da8f45fee6b7b61","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-10T13:28:35Z","title_canon_sha256":"4e735deee764322dddc7785704518032518234330d9151822a3c2959cf7044ac"},"schema_version":"1.0","source":{"id":"2304.04576","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.04576","created_at":"2026-07-05T05:59:27Z"},{"alias_kind":"arxiv_version","alias_value":"2304.04576v1","created_at":"2026-07-05T05:59:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04576","created_at":"2026-07-05T05:59:27Z"},{"alias_kind":"pith_short_12","alias_value":"3LX4Q7U4HOK2","created_at":"2026-07-05T05:59:27Z"},{"alias_kind":"pith_short_16","alias_value":"3LX4Q7U4HOK2RMA3","created_at":"2026-07-05T05:59:27Z"},{"alias_kind":"pith_short_8","alias_value":"3LX4Q7U4","created_at":"2026-07-05T05:59:27Z"}],"graph_snapshots":[{"event_id":"sha256:d99ff33f7f433fbb637655122d53d16614eb3900ec555bf51e029e12022a0e50","target":"graph","created_at":"2026-07-05T05:59:27Z","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/2304.04576/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One of the limitations of large language models is that they do not have access to up-to-date, proprietary or personal data. As a result, there are multiple efforts to extend language models with techniques for accessing external data. In that sense, LLMs share the vision of data integration systems whose goal is to provide seamless access to a large collection of heterogeneous data sources. While the details and the techniques of LLMs differ greatly from those of data integration, this paper shows that some of the lessons learned from research on data integration can elucidate the research pa","authors_text":"Alon Halevy, Jane Dwivedi-Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-10T13:28:35Z","title":"Learnings from Data Integration for Augmented Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04576","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:e907fd8a6b29f9dff638496a78b4a02ec38e0db798dc6b8268c7aee00eaf2f68","target":"record","created_at":"2026-07-05T05:59:27Z","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":"bc55a15e461f41338879e8bf33fae5a6822a4782286c36306da8f45fee6b7b61","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-10T13:28:35Z","title_canon_sha256":"4e735deee764322dddc7785704518032518234330d9151822a3c2959cf7044ac"},"schema_version":"1.0","source":{"id":"2304.04576","kind":"arxiv","version":1}},"canonical_sha256":"daefc87e9c3b95a8b01b1a8ad2d6aef050f38866de9b00b53ae7d229739a0665","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"daefc87e9c3b95a8b01b1a8ad2d6aef050f38866de9b00b53ae7d229739a0665","first_computed_at":"2026-07-05T05:59:27.621374Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:59:27.621374Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Tx/pbKS9uAi6wxaWcFBCmRzHilo1aRkkbgx0TyGC6uKWYmuMd+m7mnRB8XF856bast/RPlytncaxouJMIWTkAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:59:27.621856Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.04576","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e907fd8a6b29f9dff638496a78b4a02ec38e0db798dc6b8268c7aee00eaf2f68","sha256:d99ff33f7f433fbb637655122d53d16614eb3900ec555bf51e029e12022a0e50"],"state_sha256":"320a97c448fb8b00ec56f849bf2a93b0954eb0b52976161c67549ee54d8a6cc5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EZc91D7qHQgohkqRsGOOPkYYsnf4QoS5D36flMdvPkKVm6TyDomzQiOU00d+q8XVFAb57tuD0jMzCS/baqMqBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T15:15:17.515844Z","bundle_sha256":"090fbe523c1244849a266fe378e561757408faaf8d607f95dfb0cf9a10026f20"}}