{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6KTUYXQX3DUG6JIQ6VMLNJFLSM","short_pith_number":"pith:6KTUYXQX","canonical_record":{"source":{"id":"2305.19912","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-05-31T14:45:25Z","cross_cats_sorted":[],"title_canon_sha256":"93ab1d87cbf82defac5a45863d78afd60808e18d2a1717a5509e79c7d43d1951","abstract_canon_sha256":"3f35af6fa1413d3107c69641abd1ea102f900ad5cd0c94a833110d8df74f23f3"},"schema_version":"1.0"},"canonical_sha256":"f2a74c5e17d8e86f2510f558b6a4ab930fa37df3e0c8605928432d42999f8b6b","source":{"kind":"arxiv","id":"2305.19912","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.19912","created_at":"2026-07-05T06:16:04Z"},{"alias_kind":"arxiv_version","alias_value":"2305.19912v1","created_at":"2026-07-05T06:16:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19912","created_at":"2026-07-05T06:16:04Z"},{"alias_kind":"pith_short_12","alias_value":"6KTUYXQX3DUG","created_at":"2026-07-05T06:16:04Z"},{"alias_kind":"pith_short_16","alias_value":"6KTUYXQX3DUG6JIQ","created_at":"2026-07-05T06:16:04Z"},{"alias_kind":"pith_short_8","alias_value":"6KTUYXQX","created_at":"2026-07-05T06:16:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6KTUYXQX3DUG6JIQ6VMLNJFLSM","target":"record","payload":{"canonical_record":{"source":{"id":"2305.19912","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-05-31T14:45:25Z","cross_cats_sorted":[],"title_canon_sha256":"93ab1d87cbf82defac5a45863d78afd60808e18d2a1717a5509e79c7d43d1951","abstract_canon_sha256":"3f35af6fa1413d3107c69641abd1ea102f900ad5cd0c94a833110d8df74f23f3"},"schema_version":"1.0"},"canonical_sha256":"f2a74c5e17d8e86f2510f558b6a4ab930fa37df3e0c8605928432d42999f8b6b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:04.750487Z","signature_b64":"mnjXJRVAdZOYHerZu3a2NBATyjG2+ykmNjl1zDf5P6zxe6xYW+Iri/YFJE2daxen3ZcEhwRTRiCRBbhlQ/ysBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2a74c5e17d8e86f2510f558b6a4ab930fa37df3e0c8605928432d42999f8b6b","last_reissued_at":"2026-07-05T06:16:04.750022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:04.750022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.19912","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":"2026-07-05T06:16:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ThwHOCHw0JgRIh1c+3BPvS9xVzJoqDVzRRj7jJraTTApEcAhhN96v1XEEYILjms6uB7rbWKL+7f3v+D40DtWCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T20:21:14.453512Z"},"content_sha256":"3e7ab065177cc0fe836b2879572e1d610ccbf8ca6c24a0138f41e806f4506a30","schema_version":"1.0","event_id":"sha256:3e7ab065177cc0fe836b2879572e1d610ccbf8ca6c24a0138f41e806f4506a30"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6KTUYXQX3DUG6JIQ6VMLNJFLSM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Structure-Aware Language Model Pretraining Improves Dense Retrieval on Structured Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chenyan Xiong, Ge Yu, Shi Yu, Xinze Li, Yu Gu, Zhenghao Liu, Zhiyuan Liu","submitted_at":"2023-05-31T14:45:25Z","abstract_excerpt":"This paper presents Structure Aware Dense Retrieval (SANTA) model, which encodes user queries and structured data in one universal embedding space for retrieving structured data. SANTA proposes two pretraining methods to make language models structure-aware and learn effective representations for structured data: 1) Structured Data Alignment, which utilizes the natural alignment relations between structured data and unstructured data for structure-aware pretraining. It contrastively trains language models to represent multi-modal text data and teaches models to distinguish matched structured d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19912","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/2305.19912/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":"2026-07-05T06:16:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jpxgq1rcS6ZSmGtMyyYSwiCn9rGeoMpXALIsE+kUx4BxZ325QnpC6KiYbZUItJD6LjG+Ro26Qq6AeUk+fnPQBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T20:21:14.454062Z"},"content_sha256":"ebbbd95493be60befc29e2676c0ddbd29a16479fb15e4aff3bbb5df73ccafdda","schema_version":"1.0","event_id":"sha256:ebbbd95493be60befc29e2676c0ddbd29a16479fb15e4aff3bbb5df73ccafdda"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6KTUYXQX3DUG6JIQ6VMLNJFLSM/bundle.json","state_url":"https://pith.science/pith/6KTUYXQX3DUG6JIQ6VMLNJFLSM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6KTUYXQX3DUG6JIQ6VMLNJFLSM/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":"2026-08-15T20:21:14Z","links":{"resolver":"https://pith.science/pith/6KTUYXQX3DUG6JIQ6VMLNJFLSM","bundle":"https://pith.science/pith/6KTUYXQX3DUG6JIQ6VMLNJFLSM/bundle.json","state":"https://pith.science/pith/6KTUYXQX3DUG6JIQ6VMLNJFLSM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6KTUYXQX3DUG6JIQ6VMLNJFLSM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6KTUYXQX3DUG6JIQ6VMLNJFLSM","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":"3f35af6fa1413d3107c69641abd1ea102f900ad5cd0c94a833110d8df74f23f3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-05-31T14:45:25Z","title_canon_sha256":"93ab1d87cbf82defac5a45863d78afd60808e18d2a1717a5509e79c7d43d1951"},"schema_version":"1.0","source":{"id":"2305.19912","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.19912","created_at":"2026-07-05T06:16:04Z"},{"alias_kind":"arxiv_version","alias_value":"2305.19912v1","created_at":"2026-07-05T06:16:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19912","created_at":"2026-07-05T06:16:04Z"},{"alias_kind":"pith_short_12","alias_value":"6KTUYXQX3DUG","created_at":"2026-07-05T06:16:04Z"},{"alias_kind":"pith_short_16","alias_value":"6KTUYXQX3DUG6JIQ","created_at":"2026-07-05T06:16:04Z"},{"alias_kind":"pith_short_8","alias_value":"6KTUYXQX","created_at":"2026-07-05T06:16:04Z"}],"graph_snapshots":[{"event_id":"sha256:ebbbd95493be60befc29e2676c0ddbd29a16479fb15e4aff3bbb5df73ccafdda","target":"graph","created_at":"2026-07-05T06:16:04Z","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/2305.19912/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents Structure Aware Dense Retrieval (SANTA) model, which encodes user queries and structured data in one universal embedding space for retrieving structured data. SANTA proposes two pretraining methods to make language models structure-aware and learn effective representations for structured data: 1) Structured Data Alignment, which utilizes the natural alignment relations between structured data and unstructured data for structure-aware pretraining. It contrastively trains language models to represent multi-modal text data and teaches models to distinguish matched structured d","authors_text":"Chenyan Xiong, Ge Yu, Shi Yu, Xinze Li, Yu Gu, Zhenghao Liu, Zhiyuan Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-05-31T14:45:25Z","title":"Structure-Aware Language Model Pretraining Improves Dense Retrieval on Structured Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19912","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":"sha256:3e7ab065177cc0fe836b2879572e1d610ccbf8ca6c24a0138f41e806f4506a30","target":"record","created_at":"2026-07-05T06:16:04Z","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":"3f35af6fa1413d3107c69641abd1ea102f900ad5cd0c94a833110d8df74f23f3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-05-31T14:45:25Z","title_canon_sha256":"93ab1d87cbf82defac5a45863d78afd60808e18d2a1717a5509e79c7d43d1951"},"schema_version":"1.0","source":{"id":"2305.19912","kind":"arxiv","version":1}},"canonical_sha256":"f2a74c5e17d8e86f2510f558b6a4ab930fa37df3e0c8605928432d42999f8b6b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2a74c5e17d8e86f2510f558b6a4ab930fa37df3e0c8605928432d42999f8b6b","first_computed_at":"2026-07-05T06:16:04.750022Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:16:04.750022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mnjXJRVAdZOYHerZu3a2NBATyjG2+ykmNjl1zDf5P6zxe6xYW+Iri/YFJE2daxen3ZcEhwRTRiCRBbhlQ/ysBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:16:04.750487Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.19912","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e7ab065177cc0fe836b2879572e1d610ccbf8ca6c24a0138f41e806f4506a30","sha256:ebbbd95493be60befc29e2676c0ddbd29a16479fb15e4aff3bbb5df73ccafdda"],"state_sha256":"090b05a65b6a7e7b82dd39ae0284d073f15700876a2262fe1b9c97e8ce7b4670"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZnyKyZL0ZDmMHk9oM7jEN9AvYAOUrZLs4SYv5Prd4b6OBxtA9J72Ekax88BHq7x2GElaP6723ebhBashO3JbCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T20:21:14.457921Z","bundle_sha256":"a830927e11f75f3834f67ab0500d69afe86ff633d4e2e07ce0d9dc53d6cf2509"}}