{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:VJT7QGIXE6VCOZQKYKFVHI7CC5","short_pith_number":"pith:VJT7QGIX","canonical_record":{"source":{"id":"2607.00023","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-19T02:39:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8465f1c9f9b952b2496226616de57627c770c55c312bfe90989fe330c6d4a7d4","abstract_canon_sha256":"0a8825b5cd78e5885e32521f9a0ee850c970e30edabc3484739543ac342b542a"},"schema_version":"1.0"},"canonical_sha256":"aa67f8191727aa27660ac28b53a3e21762b580783e0be1ddcf2fcc16486e6a71","source":{"kind":"arxiv","id":"2607.00023","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.00023","created_at":"2026-07-02T00:18:31Z"},{"alias_kind":"arxiv_version","alias_value":"2607.00023v1","created_at":"2026-07-02T00:18:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00023","created_at":"2026-07-02T00:18:31Z"},{"alias_kind":"pith_short_12","alias_value":"VJT7QGIXE6VC","created_at":"2026-07-02T00:18:31Z"},{"alias_kind":"pith_short_16","alias_value":"VJT7QGIXE6VCOZQK","created_at":"2026-07-02T00:18:31Z"},{"alias_kind":"pith_short_8","alias_value":"VJT7QGIX","created_at":"2026-07-02T00:18:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:VJT7QGIXE6VCOZQKYKFVHI7CC5","target":"record","payload":{"canonical_record":{"source":{"id":"2607.00023","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-19T02:39:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8465f1c9f9b952b2496226616de57627c770c55c312bfe90989fe330c6d4a7d4","abstract_canon_sha256":"0a8825b5cd78e5885e32521f9a0ee850c970e30edabc3484739543ac342b542a"},"schema_version":"1.0"},"canonical_sha256":"aa67f8191727aa27660ac28b53a3e21762b580783e0be1ddcf2fcc16486e6a71","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T00:18:31.572256Z","signature_b64":"QRB+oAwKtMPf9O7SPrrEFG/J119R38EmetmM/HxTQ6WLyK+O9r9K6aK/mJ7rRmMByOZUUyYT7TDkB68zxPx1CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa67f8191727aa27660ac28b53a3e21762b580783e0be1ddcf2fcc16486e6a71","last_reissued_at":"2026-07-02T00:18:31.571183Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T00:18:31.571183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.00023","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":"2026-07-02T00:18:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pnjLEUp4iM8+JrTbsBLdUNGWgxDsnRtjS1IPOEeKlgVpWDbcI1suNSD52Z1xZG6xIHYb49DOE9yR0RE+7V2lBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T18:06:13.275992Z"},"content_sha256":"c75913acdcfdfaee23350e5fedca6b3fa881740971d98515e329604c29c22570","schema_version":"1.0","event_id":"sha256:c75913acdcfdfaee23350e5fedca6b3fa881740971d98515e329604c29c22570"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:VJT7QGIXE6VCOZQKYKFVHI7CC5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Aligning Sentence Embeddings to Human Concepts via Sparse Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Songkuk Kim, Wonseok Shin","submitted_at":"2026-06-19T02:39:50Z","abstract_excerpt":"Dense sentence embeddings are fundamental to modern Retrieval-Augmented Generation (RAG) systems but suffer from a lack of interpretability due to feature superposition. This opacity hinders the alignment of retrieval processes with human intent, as the entangled representations are difficult to analyze or control. In this work, we propose a method to disentangle the dense representations of sentence transformers (e.g., E5) into human-interpretable concepts using Top-k Sparse Autoencoders (SAEs). We demonstrate that these disentangled features align with specific semantic, syntactic, and pragm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00023","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/2607.00023/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":"2026-07-02T00:18:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bOSijFNFBKWjLlJsv0wA7DMIHt4nUK5IHhA7wpgUHlF7ToK8mSs3LcM5zDq1Qp5F0PJ39rCQ5GtqKkl+RLXwDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T18:06:13.276555Z"},"content_sha256":"f70a21dc2985ea8d1cb3c819b27f3d6bbc6f824f129e127e181deb8e4e22664d","schema_version":"1.0","event_id":"sha256:f70a21dc2985ea8d1cb3c819b27f3d6bbc6f824f129e127e181deb8e4e22664d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VJT7QGIXE6VCOZQKYKFVHI7CC5/bundle.json","state_url":"https://pith.science/pith/VJT7QGIXE6VCOZQKYKFVHI7CC5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VJT7QGIXE6VCOZQKYKFVHI7CC5/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":"2026-08-20T18:06:13Z","links":{"resolver":"https://pith.science/pith/VJT7QGIXE6VCOZQKYKFVHI7CC5","bundle":"https://pith.science/pith/VJT7QGIXE6VCOZQKYKFVHI7CC5/bundle.json","state":"https://pith.science/pith/VJT7QGIXE6VCOZQKYKFVHI7CC5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VJT7QGIXE6VCOZQKYKFVHI7CC5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VJT7QGIXE6VCOZQKYKFVHI7CC5","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":"0a8825b5cd78e5885e32521f9a0ee850c970e30edabc3484739543ac342b542a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-19T02:39:50Z","title_canon_sha256":"8465f1c9f9b952b2496226616de57627c770c55c312bfe90989fe330c6d4a7d4"},"schema_version":"1.0","source":{"id":"2607.00023","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.00023","created_at":"2026-07-02T00:18:31Z"},{"alias_kind":"arxiv_version","alias_value":"2607.00023v1","created_at":"2026-07-02T00:18:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00023","created_at":"2026-07-02T00:18:31Z"},{"alias_kind":"pith_short_12","alias_value":"VJT7QGIXE6VC","created_at":"2026-07-02T00:18:31Z"},{"alias_kind":"pith_short_16","alias_value":"VJT7QGIXE6VCOZQK","created_at":"2026-07-02T00:18:31Z"},{"alias_kind":"pith_short_8","alias_value":"VJT7QGIX","created_at":"2026-07-02T00:18:31Z"}],"graph_snapshots":[{"event_id":"sha256:f70a21dc2985ea8d1cb3c819b27f3d6bbc6f824f129e127e181deb8e4e22664d","target":"graph","created_at":"2026-07-02T00:18:31Z","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/2607.00023/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dense sentence embeddings are fundamental to modern Retrieval-Augmented Generation (RAG) systems but suffer from a lack of interpretability due to feature superposition. This opacity hinders the alignment of retrieval processes with human intent, as the entangled representations are difficult to analyze or control. In this work, we propose a method to disentangle the dense representations of sentence transformers (e.g., E5) into human-interpretable concepts using Top-k Sparse Autoencoders (SAEs). We demonstrate that these disentangled features align with specific semantic, syntactic, and pragm","authors_text":"Songkuk Kim, Wonseok Shin","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-19T02:39:50Z","title":"Aligning Sentence Embeddings to Human Concepts via Sparse Autoencoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00023","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:c75913acdcfdfaee23350e5fedca6b3fa881740971d98515e329604c29c22570","target":"record","created_at":"2026-07-02T00:18:31Z","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":"0a8825b5cd78e5885e32521f9a0ee850c970e30edabc3484739543ac342b542a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-19T02:39:50Z","title_canon_sha256":"8465f1c9f9b952b2496226616de57627c770c55c312bfe90989fe330c6d4a7d4"},"schema_version":"1.0","source":{"id":"2607.00023","kind":"arxiv","version":1}},"canonical_sha256":"aa67f8191727aa27660ac28b53a3e21762b580783e0be1ddcf2fcc16486e6a71","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa67f8191727aa27660ac28b53a3e21762b580783e0be1ddcf2fcc16486e6a71","first_computed_at":"2026-07-02T00:18:31.571183Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T00:18:31.571183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QRB+oAwKtMPf9O7SPrrEFG/J119R38EmetmM/HxTQ6WLyK+O9r9K6aK/mJ7rRmMByOZUUyYT7TDkB68zxPx1CA==","signature_status":"signed_v1","signed_at":"2026-07-02T00:18:31.572256Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.00023","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c75913acdcfdfaee23350e5fedca6b3fa881740971d98515e329604c29c22570","sha256:f70a21dc2985ea8d1cb3c819b27f3d6bbc6f824f129e127e181deb8e4e22664d"],"state_sha256":"35f7661ce06eb7dca344c098e52a5ee1ba25180df9299388fa2473e45b5e74f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SNLNU3HRhbDUYK96HIyluD2v/X2t7qYYGEj9maXlR52rw10ClfnqDJVUl+sAasWrv07V7LL9CoNXu3ZDcmskDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T18:06:13.280175Z","bundle_sha256":"df8ebf535c767b4d0527156b5d3fc8d81f214d55bbee7ff317773240cb9d0417"}}