{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CCM4AEI2BD6SQEG5SUDNLIJ7KQ","short_pith_number":"pith:CCM4AEI2","canonical_record":{"source":{"id":"2605.20467","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T20:30:00Z","cross_cats_sorted":[],"title_canon_sha256":"aaaa98048ffb3009e7c12aa1d3842bba089d62400ae93438f966e0c6789890ff","abstract_canon_sha256":"ca1ddea66ca4f638ae3dda403164fae1d25bd34e5f47d8c667f85f90bd94b6ca"},"schema_version":"1.0"},"canonical_sha256":"1099c0111a08fd2810dd9506d5a13f542e285288e0572825a8157efc2a7b221c","source":{"kind":"arxiv","id":"2605.20467","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20467","created_at":"2026-05-21T01:04:38Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20467v1","created_at":"2026-05-21T01:04:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20467","created_at":"2026-05-21T01:04:38Z"},{"alias_kind":"pith_short_12","alias_value":"CCM4AEI2BD6S","created_at":"2026-05-21T01:04:38Z"},{"alias_kind":"pith_short_16","alias_value":"CCM4AEI2BD6SQEG5","created_at":"2026-05-21T01:04:38Z"},{"alias_kind":"pith_short_8","alias_value":"CCM4AEI2","created_at":"2026-05-21T01:04:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CCM4AEI2BD6SQEG5SUDNLIJ7KQ","target":"record","payload":{"canonical_record":{"source":{"id":"2605.20467","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T20:30:00Z","cross_cats_sorted":[],"title_canon_sha256":"aaaa98048ffb3009e7c12aa1d3842bba089d62400ae93438f966e0c6789890ff","abstract_canon_sha256":"ca1ddea66ca4f638ae3dda403164fae1d25bd34e5f47d8c667f85f90bd94b6ca"},"schema_version":"1.0"},"canonical_sha256":"1099c0111a08fd2810dd9506d5a13f542e285288e0572825a8157efc2a7b221c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:38.964811Z","signature_b64":"WlAsvwObYBJ8fGZdTXdyLvyFS5PH221E94Lpc7MSuy7F8iQ3b6rYd2ZmS3MYYBkVWdvsz6oIujfmohCGUvOkAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1099c0111a08fd2810dd9506d5a13f542e285288e0572825a8157efc2a7b221c","last_reissued_at":"2026-05-21T01:04:38.964179Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:38.964179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.20467","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":"2026-05-21T01:04:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EgdhKQGDAYkHarh/Q61G3l7fpCTg6gzghbWphLZVRv/WFR1y/ZLGLIL2e+nN95UU/5FwDqjnrdx4e4j/fnh5AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:22:07.729596Z"},"content_sha256":"3976c412e8e708bddefab4463e5a8a1e5ac667d60365fc096e6b6a499963cb1e","schema_version":"1.0","event_id":"sha256:3976c412e8e708bddefab4463e5a8a1e5ac667d60365fc096e6b6a499963cb1e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CCM4AEI2BD6SQEG5SUDNLIJ7KQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"High Quality Embeddings for Horn Logic Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ashely Hirst, Dean Clark, Jeff Heflin, Jevon Lipsey, Joseph Sanchez, Yasir White, Yifan Zhang","submitted_at":"2026-05-19T20:30:00Z","abstract_excerpt":"Neural networks can be trained to rank the choices made by logical reasoners, resulting in more efficient searches for answers. A key step in this process is creating useful embeddings, i.e., numeric representations of logical statements. This paper introduces and evaluates several approaches to creating embeddings that result in better downstream results. We train embeddings using triplet loss, which requires examples consisting of an anchor, a positive example, and a negative example. We introduce three ideas: generating anchors that are more likely to have repeated terms, generating positiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20467","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/2605.20467/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":"2026-05-21T01:04:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MFwZZtEyHkS0bSUM40KvCusEH8wUgo0S6xHz9OfIj6NxbYfcyEeEL78o20a4oushHFpbsGMt+D2ms6Har3/oBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:22:07.730361Z"},"content_sha256":"5befbbe8826767e058c5dc0bb457a586fa7022dd25620f74bc0a004f907925b5","schema_version":"1.0","event_id":"sha256:5befbbe8826767e058c5dc0bb457a586fa7022dd25620f74bc0a004f907925b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CCM4AEI2BD6SQEG5SUDNLIJ7KQ/bundle.json","state_url":"https://pith.science/pith/CCM4AEI2BD6SQEG5SUDNLIJ7KQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CCM4AEI2BD6SQEG5SUDNLIJ7KQ/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":"2026-05-25T21:22:07Z","links":{"resolver":"https://pith.science/pith/CCM4AEI2BD6SQEG5SUDNLIJ7KQ","bundle":"https://pith.science/pith/CCM4AEI2BD6SQEG5SUDNLIJ7KQ/bundle.json","state":"https://pith.science/pith/CCM4AEI2BD6SQEG5SUDNLIJ7KQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CCM4AEI2BD6SQEG5SUDNLIJ7KQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CCM4AEI2BD6SQEG5SUDNLIJ7KQ","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":"ca1ddea66ca4f638ae3dda403164fae1d25bd34e5f47d8c667f85f90bd94b6ca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T20:30:00Z","title_canon_sha256":"aaaa98048ffb3009e7c12aa1d3842bba089d62400ae93438f966e0c6789890ff"},"schema_version":"1.0","source":{"id":"2605.20467","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20467","created_at":"2026-05-21T01:04:38Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20467v1","created_at":"2026-05-21T01:04:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20467","created_at":"2026-05-21T01:04:38Z"},{"alias_kind":"pith_short_12","alias_value":"CCM4AEI2BD6S","created_at":"2026-05-21T01:04:38Z"},{"alias_kind":"pith_short_16","alias_value":"CCM4AEI2BD6SQEG5","created_at":"2026-05-21T01:04:38Z"},{"alias_kind":"pith_short_8","alias_value":"CCM4AEI2","created_at":"2026-05-21T01:04:38Z"}],"graph_snapshots":[{"event_id":"sha256:5befbbe8826767e058c5dc0bb457a586fa7022dd25620f74bc0a004f907925b5","target":"graph","created_at":"2026-05-21T01:04:38Z","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/2605.20467/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural networks can be trained to rank the choices made by logical reasoners, resulting in more efficient searches for answers. A key step in this process is creating useful embeddings, i.e., numeric representations of logical statements. This paper introduces and evaluates several approaches to creating embeddings that result in better downstream results. We train embeddings using triplet loss, which requires examples consisting of an anchor, a positive example, and a negative example. We introduce three ideas: generating anchors that are more likely to have repeated terms, generating positiv","authors_text":"Ashely Hirst, Dean Clark, Jeff Heflin, Jevon Lipsey, Joseph Sanchez, Yasir White, Yifan Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T20:30:00Z","title":"High Quality Embeddings for Horn Logic Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20467","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":"sha256:3976c412e8e708bddefab4463e5a8a1e5ac667d60365fc096e6b6a499963cb1e","target":"record","created_at":"2026-05-21T01:04:38Z","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":"ca1ddea66ca4f638ae3dda403164fae1d25bd34e5f47d8c667f85f90bd94b6ca","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-19T20:30:00Z","title_canon_sha256":"aaaa98048ffb3009e7c12aa1d3842bba089d62400ae93438f966e0c6789890ff"},"schema_version":"1.0","source":{"id":"2605.20467","kind":"arxiv","version":1}},"canonical_sha256":"1099c0111a08fd2810dd9506d5a13f542e285288e0572825a8157efc2a7b221c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1099c0111a08fd2810dd9506d5a13f542e285288e0572825a8157efc2a7b221c","first_computed_at":"2026-05-21T01:04:38.964179Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:38.964179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WlAsvwObYBJ8fGZdTXdyLvyFS5PH221E94Lpc7MSuy7F8iQ3b6rYd2ZmS3MYYBkVWdvsz6oIujfmohCGUvOkAw==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:38.964811Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20467","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3976c412e8e708bddefab4463e5a8a1e5ac667d60365fc096e6b6a499963cb1e","sha256:5befbbe8826767e058c5dc0bb457a586fa7022dd25620f74bc0a004f907925b5"],"state_sha256":"6c25f00b1c5db57753704d33b1f19edd1685802b9fae688ad11bb68cc5d6939d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9JARaJYwYZ8RFUL2LdB6YQd0v5U0XLbeDZgNOMQ+z+8EJTGX264ij/TJWKy1bqwLhcZG/s+DRaJRwBU+kVggBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T21:22:07.734070Z","bundle_sha256":"2702ea92f7db173a6d3015e36ad17e0eda3c06bc75b041fbc6157f9ad2e871fb"}}