{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:V5OFYKXZJMGD6WZHVSHQO6AI3D","short_pith_number":"pith:V5OFYKXZ","canonical_record":{"source":{"id":"2605.15505","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-15T00:54:02Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"edc251aaf8313bdf4387953902b9dd1c6d9de3121a6eb726d8e27d509ba5a63c","abstract_canon_sha256":"e3d8f2494e15467321834d38a2a531cb8fd419d4807c51f723d02062ddb80b0c"},"schema_version":"1.0"},"canonical_sha256":"af5c5c2af94b0c3f5b27ac8f077808d8f88b0be5a47c76194ed8302a04a767c5","source":{"kind":"arxiv","id":"2605.15505","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15505","created_at":"2026-05-20T00:01:02Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15505v1","created_at":"2026-05-20T00:01:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15505","created_at":"2026-05-20T00:01:02Z"},{"alias_kind":"pith_short_12","alias_value":"V5OFYKXZJMGD","created_at":"2026-05-20T00:01:02Z"},{"alias_kind":"pith_short_16","alias_value":"V5OFYKXZJMGD6WZH","created_at":"2026-05-20T00:01:02Z"},{"alias_kind":"pith_short_8","alias_value":"V5OFYKXZ","created_at":"2026-05-20T00:01:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:V5OFYKXZJMGD6WZHVSHQO6AI3D","target":"record","payload":{"canonical_record":{"source":{"id":"2605.15505","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-15T00:54:02Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"edc251aaf8313bdf4387953902b9dd1c6d9de3121a6eb726d8e27d509ba5a63c","abstract_canon_sha256":"e3d8f2494e15467321834d38a2a531cb8fd419d4807c51f723d02062ddb80b0c"},"schema_version":"1.0"},"canonical_sha256":"af5c5c2af94b0c3f5b27ac8f077808d8f88b0be5a47c76194ed8302a04a767c5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:02.118932Z","signature_b64":"JtxlVpWVV2VNk9QjaUd8EMEzTOPT2NfxGR1p7dzeFDkFjTI+UKaIzEJ3UDY7qgyju/3DXmwVpDwef3PVTLiiDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af5c5c2af94b0c3f5b27ac8f077808d8f88b0be5a47c76194ed8302a04a767c5","last_reissued_at":"2026-05-20T00:01:02.118129Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:02.118129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.15505","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":"2026-05-20T00:01:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FPhUn52nwWq2DMx+bBdpGP8JppMIzwLJBX8xKH2NrAqzxdfwplSnM2kFxK5o5kryyBct+U7Jy62j0AgcH468Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T15:10:31.563003Z"},"content_sha256":"b7032a1fe0325bc19bb6331caac15591440b137c26cf923bf061eead00d5e670","schema_version":"1.0","event_id":"sha256:b7032a1fe0325bc19bb6331caac15591440b137c26cf923bf061eead00d5e670"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:V5OFYKXZJMGD6WZHVSHQO6AI3D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"X-SYNTH: Beyond Retrieval -- Enterprise Context Synthesis from Observed Human Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Enterprise context synthesis succeeds by deriving relevance from human attention traces instead of retrieving stored system state.","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.AI","authors_text":"George Nychis, Guruprasad Raghavan, Rohan Narayana Murthy","submitted_at":"2026-05-15T00:54:02Z","abstract_excerpt":"In enterprise operations, the context required for an AI agent task is scattered across systems of record, static information stores, and communication channels. What is stored is system state, a lossy representation of the work that actually happened [2, 52]. The prevailing approach [17, 31, 34, 36] retrieves by matching request content to what is stored; for narrow requests this works well. But synthesis quality depends on knowing what to surface and how to interpret it: knowledge specific to each organization, team, and individual [5, 57, 61], present in behavioral patterns, absent from any"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Enterprise context synthesis is not a retrieval problem. It is a relevance problem, and human attention is its most reliable ground truth. On a sales lead identification task, a frontier model unaided achieves 9.5% True Lead Rate (TLR) with 90.5% False Lead Rate (FLR). Augmented with X-SYNTH, TLR rises to 61.9% (6.5x) while FLR falls to 18.8%.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Behavioral traces preceding positive outcomes are distinguishable from those that did not, without external labeling, allowing implicit reward signals in the data to identify causally relevant activity signatures.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"X-SYNTH synthesizes enterprise context from human behavioral attention traces modeled as Digital Twin Signatures using seven per-individual attention filters, raising true lead rate from 9.5% to 61.9% on a sales identification task.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Enterprise context synthesis succeeds by deriving relevance from human attention traces instead of retrieving stored system state.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"1397cecf8ebc026abe7d01b04f9fcc2665aa8e6d07aa33a3ab5b5b93d8db5edb"},"source":{"id":"2605.15505","kind":"arxiv","version":1},"verdict":{"id":"1af2ce9e-52ce-47e5-80c8-fbd74ddbe1b1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T15:53:45.435925Z","strongest_claim":"Enterprise context synthesis is not a retrieval problem. It is a relevance problem, and human attention is its most reliable ground truth. On a sales lead identification task, a frontier model unaided achieves 9.5% True Lead Rate (TLR) with 90.5% False Lead Rate (FLR). Augmented with X-SYNTH, TLR rises to 61.9% (6.5x) while FLR falls to 18.8%.","one_line_summary":"X-SYNTH synthesizes enterprise context from human behavioral attention traces modeled as Digital Twin Signatures using seven per-individual attention filters, raising true lead rate from 9.5% to 61.9% on a sales identification task.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Behavioral traces preceding positive outcomes are distinguishable from those that did not, without external labeling, allowing implicit reward signals in the data to identify causally relevant activity signatures.","pith_extraction_headline":"Enterprise context synthesis succeeds by deriving relevance from human attention traces instead of retrieving stored system state."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15505/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-19T16:04:35.997623Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T16:01:17.938079Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"cited_work_retraction","ran_at":"2026-05-19T14:51:55.575300Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T14:21:54.060147Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"shingle_duplication","ran_at":"2026-05-19T13:49:41.852007Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T13:49:41.390899Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.638767Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"3089752f18d3f2d3a90d4b31e5923666348dda7ad69ebdeac66af34886736ced"},"references":{"count":76,"sample":[{"doi":"","year":2006,"title":"Eugene Agichtein, Eric Brill, and Susan Dumais. 2006. Improving Web Search Ranking by Incorporating User Behavior Information. InACM SIGIR Conference on Research and Development in Information Retriev","work_id":"cee6010d-2bb1-4d6c-9a74-fc4ac33c64b5","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Anonymous. 2025. ENTROPHY: Multi-Modal User Interaction Data from Live Enterprise Business Workflows. InAdvances in Neural Information Processing Systems (NeurIPS). Workfabric AI / Soroco","work_id":"a0120ba7-7a43-494a-a660-27a74c19495b","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2024. Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection. InInternational Conference on Learning Re","work_id":"fa6de1ad-98e4-4361-84dc-ce5255a64d9b","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2005,"title":"Jakob E. Bardram. 2005. Activity-Based Computing: Support for Mobility and Collaboration in Ubiquitous Computing.Personal and Ubiquitous Computing9, 5 (2005), 312–322","work_id":"10fa04b5-6e18-4f48-8af2-3ab4df8633d8","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2012,"title":"Paul N. Bennett, Ryen W. White, Wei Chu, Susan T. Dumais, Peter Bailey, Fedor Borisyuk, and Xiaoyuan Cui. 2012. Modeling the Impact of Short- and Long-Term Behavior on Search Personalization. InACM SI","work_id":"16af3dc4-1544-4a7e-8a07-1176e6c26b25","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":76,"snapshot_sha256":"22acc01b2c31c75b3e50386d7821e41616ec2fc4b5581020bd549608466191b4","internal_anchors":2},"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":"1af2ce9e-52ce-47e5-80c8-fbd74ddbe1b1"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:01:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bAaTkab/jL7VRD8q0gWy6sRnJDprFmAmZ7qLoK/38U97Ug4fZMjrIey4aFmk9+LD5JaFa3Tqk7HlbBnjZzuICw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T15:10:31.564638Z"},"content_sha256":"5f5bd80fed3dcc5401b679cfc4445116f5ab7373ba4260ead01483d2effeb633","schema_version":"1.0","event_id":"sha256:5f5bd80fed3dcc5401b679cfc4445116f5ab7373ba4260ead01483d2effeb633"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V5OFYKXZJMGD6WZHVSHQO6AI3D/bundle.json","state_url":"https://pith.science/pith/V5OFYKXZJMGD6WZHVSHQO6AI3D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V5OFYKXZJMGD6WZHVSHQO6AI3D/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":"2026-05-23T15:10:31Z","links":{"resolver":"https://pith.science/pith/V5OFYKXZJMGD6WZHVSHQO6AI3D","bundle":"https://pith.science/pith/V5OFYKXZJMGD6WZHVSHQO6AI3D/bundle.json","state":"https://pith.science/pith/V5OFYKXZJMGD6WZHVSHQO6AI3D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V5OFYKXZJMGD6WZHVSHQO6AI3D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:V5OFYKXZJMGD6WZHVSHQO6AI3D","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":"e3d8f2494e15467321834d38a2a531cb8fd419d4807c51f723d02062ddb80b0c","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-15T00:54:02Z","title_canon_sha256":"edc251aaf8313bdf4387953902b9dd1c6d9de3121a6eb726d8e27d509ba5a63c"},"schema_version":"1.0","source":{"id":"2605.15505","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15505","created_at":"2026-05-20T00:01:02Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15505v1","created_at":"2026-05-20T00:01:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15505","created_at":"2026-05-20T00:01:02Z"},{"alias_kind":"pith_short_12","alias_value":"V5OFYKXZJMGD","created_at":"2026-05-20T00:01:02Z"},{"alias_kind":"pith_short_16","alias_value":"V5OFYKXZJMGD6WZH","created_at":"2026-05-20T00:01:02Z"},{"alias_kind":"pith_short_8","alias_value":"V5OFYKXZ","created_at":"2026-05-20T00:01:02Z"}],"graph_snapshots":[{"event_id":"sha256:5f5bd80fed3dcc5401b679cfc4445116f5ab7373ba4260ead01483d2effeb633","target":"graph","created_at":"2026-05-20T00:01:02Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Enterprise context synthesis is not a retrieval problem. It is a relevance problem, and human attention is its most reliable ground truth. On a sales lead identification task, a frontier model unaided achieves 9.5% True Lead Rate (TLR) with 90.5% False Lead Rate (FLR). Augmented with X-SYNTH, TLR rises to 61.9% (6.5x) while FLR falls to 18.8%."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"Behavioral traces preceding positive outcomes are distinguishable from those that did not, without external labeling, allowing implicit reward signals in the data to identify causally relevant activity signatures."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"X-SYNTH synthesizes enterprise context from human behavioral attention traces modeled as Digital Twin Signatures using seven per-individual attention filters, raising true lead rate from 9.5% to 61.9% on a sales identification task."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Enterprise context synthesis succeeds by deriving relevance from human attention traces instead of retrieving stored system state."}],"snapshot_sha256":"1397cecf8ebc026abe7d01b04f9fcc2665aa8e6d07aa33a3ab5b5b93d8db5edb"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T16:04:35.997623Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T16:01:17.938079Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"cited_work_retraction","ran_at":"2026-05-19T14:51:55.575300Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T14:21:54.060147Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"shingle_duplication","ran_at":"2026-05-19T13:49:41.852007Z","status":"skipped","version":"0.1.0"},{"findings_count":0,"name":"citation_quote_validity","ran_at":"2026-05-19T13:49:41.390899Z","status":"skipped","version":"0.1.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.638767Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.15505/integrity.json","findings":[],"snapshot_sha256":"3089752f18d3f2d3a90d4b31e5923666348dda7ad69ebdeac66af34886736ced","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In enterprise operations, the context required for an AI agent task is scattered across systems of record, static information stores, and communication channels. What is stored is system state, a lossy representation of the work that actually happened [2, 52]. The prevailing approach [17, 31, 34, 36] retrieves by matching request content to what is stored; for narrow requests this works well. But synthesis quality depends on knowing what to surface and how to interpret it: knowledge specific to each organization, team, and individual [5, 57, 61], present in behavioral patterns, absent from any","authors_text":"George Nychis, Guruprasad Raghavan, Rohan Narayana Murthy","cross_cats":["cs.IR","cs.LG"],"headline":"Enterprise context synthesis succeeds by deriving relevance from human attention traces instead of retrieving stored system state.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-15T00:54:02Z","title":"X-SYNTH: Beyond Retrieval -- Enterprise Context Synthesis from Observed Human Attention"},"references":{"count":76,"internal_anchors":2,"resolved_work":76,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Eugene Agichtein, Eric Brill, and Susan Dumais. 2006. Improving Web Search Ranking by Incorporating User Behavior Information. InACM SIGIR Conference on Research and Development in Information Retriev","work_id":"cee6010d-2bb1-4d6c-9a74-fc4ac33c64b5","year":2006},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Anonymous. 2025. ENTROPHY: Multi-Modal User Interaction Data from Live Enterprise Business Workflows. InAdvances in Neural Information Processing Systems (NeurIPS). Workfabric AI / Soroco","work_id":"a0120ba7-7a43-494a-a660-27a74c19495b","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2024. Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection. InInternational Conference on Learning Re","work_id":"fa6de1ad-98e4-4361-84dc-ce5255a64d9b","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Jakob E. Bardram. 2005. Activity-Based Computing: Support for Mobility and Collaboration in Ubiquitous Computing.Personal and Ubiquitous Computing9, 5 (2005), 312–322","work_id":"10fa04b5-6e18-4f48-8af2-3ab4df8633d8","year":2005},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Paul N. Bennett, Ryen W. White, Wei Chu, Susan T. Dumais, Peter Bailey, Fedor Borisyuk, and Xiaoyuan Cui. 2012. Modeling the Impact of Short- and Long-Term Behavior on Search Personalization. InACM SI","work_id":"16af3dc4-1544-4a7e-8a07-1176e6c26b25","year":2012}],"snapshot_sha256":"22acc01b2c31c75b3e50386d7821e41616ec2fc4b5581020bd549608466191b4"},"source":{"id":"2605.15505","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T15:53:45.435925Z","id":"1af2ce9e-52ce-47e5-80c8-fbd74ddbe1b1","model_set":{"reader":"grok-4.3"},"one_line_summary":"X-SYNTH synthesizes enterprise context from human behavioral attention traces modeled as Digital Twin Signatures using seven per-individual attention filters, raising true lead rate from 9.5% to 61.9% on a sales identification task.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Enterprise context synthesis succeeds by deriving relevance from human attention traces instead of retrieving stored system state.","strongest_claim":"Enterprise context synthesis is not a retrieval problem. It is a relevance problem, and human attention is its most reliable ground truth. On a sales lead identification task, a frontier model unaided achieves 9.5% True Lead Rate (TLR) with 90.5% False Lead Rate (FLR). Augmented with X-SYNTH, TLR rises to 61.9% (6.5x) while FLR falls to 18.8%.","weakest_assumption":"Behavioral traces preceding positive outcomes are distinguishable from those that did not, without external labeling, allowing implicit reward signals in the data to identify causally relevant activity signatures."}},"verdict_id":"1af2ce9e-52ce-47e5-80c8-fbd74ddbe1b1"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b7032a1fe0325bc19bb6331caac15591440b137c26cf923bf061eead00d5e670","target":"record","created_at":"2026-05-20T00:01:02Z","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":"e3d8f2494e15467321834d38a2a531cb8fd419d4807c51f723d02062ddb80b0c","cross_cats_sorted":["cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-15T00:54:02Z","title_canon_sha256":"edc251aaf8313bdf4387953902b9dd1c6d9de3121a6eb726d8e27d509ba5a63c"},"schema_version":"1.0","source":{"id":"2605.15505","kind":"arxiv","version":1}},"canonical_sha256":"af5c5c2af94b0c3f5b27ac8f077808d8f88b0be5a47c76194ed8302a04a767c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af5c5c2af94b0c3f5b27ac8f077808d8f88b0be5a47c76194ed8302a04a767c5","first_computed_at":"2026-05-20T00:01:02.118129Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:02.118129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JtxlVpWVV2VNk9QjaUd8EMEzTOPT2NfxGR1p7dzeFDkFjTI+UKaIzEJ3UDY7qgyju/3DXmwVpDwef3PVTLiiDA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:02.118932Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15505","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7032a1fe0325bc19bb6331caac15591440b137c26cf923bf061eead00d5e670","sha256:5f5bd80fed3dcc5401b679cfc4445116f5ab7373ba4260ead01483d2effeb633"],"state_sha256":"e6d8aca4081124b565473fa41b269d17e75a701f4c89c3c56d76569771096ff3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ymutxzgAOVFF1QLlyoKLa4NKhLV927A5+iWIByVuo2kQd4781ICU9iyL2whfOSoc/PHNtkZbp0TYESs3cZefBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T15:10:31.570820Z","bundle_sha256":"a40ebc32507a0c0b264070d9a4331c6e6fa505cddfa105680d3da7ebcb5a4f5d"}}