{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5J2YITGCO2LZAWLVGYTGKRXP5S","short_pith_number":"pith:5J2YITGC","canonical_record":{"source":{"id":"2506.00041","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-28T02:50:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f8075fe0802c9af489f2ff1fe76d6f39bffc864490e30609a7ca47a62d3c6a37","abstract_canon_sha256":"01f32f0dd8360ab777f7a792bcbbf1ba2d6eb089896133b1f59784caff58ae64"},"schema_version":"1.0"},"canonical_sha256":"ea75844cc2769790597536266546efeca42a4a00932b64d152c6858fecfe668f","source":{"kind":"arxiv","id":"2506.00041","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00041","created_at":"2026-07-05T12:00:01Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00041v2","created_at":"2026-07-05T12:00:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00041","created_at":"2026-07-05T12:00:01Z"},{"alias_kind":"pith_short_12","alias_value":"5J2YITGCO2LZ","created_at":"2026-07-05T12:00:01Z"},{"alias_kind":"pith_short_16","alias_value":"5J2YITGCO2LZAWLV","created_at":"2026-07-05T12:00:01Z"},{"alias_kind":"pith_short_8","alias_value":"5J2YITGC","created_at":"2026-07-05T12:00:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5J2YITGCO2LZAWLVGYTGKRXP5S","target":"record","payload":{"canonical_record":{"source":{"id":"2506.00041","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-28T02:50:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f8075fe0802c9af489f2ff1fe76d6f39bffc864490e30609a7ca47a62d3c6a37","abstract_canon_sha256":"01f32f0dd8360ab777f7a792bcbbf1ba2d6eb089896133b1f59784caff58ae64"},"schema_version":"1.0"},"canonical_sha256":"ea75844cc2769790597536266546efeca42a4a00932b64d152c6858fecfe668f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:01.636481Z","signature_b64":"kUA1CbrIvdF0PTpHBgK0i+jV2mxgPhxzfr1WJVAFQdgSAEH3nRFMugnnpQrWTJ6hgdqSb9QqO1Ynho8O6pjFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea75844cc2769790597536266546efeca42a4a00932b64d152c6858fecfe668f","last_reissued_at":"2026-07-05T12:00:01.636009Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:01.636009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.00041","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:00:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/X6LivVx+gHyys40cygtBl3gVEzkKluoKFmZ2kXR0MP6l9j6h2cBhRRXjk/Jjb937LNLE/JejBrkMiXZ7C4zBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T07:22:28.930282Z"},"content_sha256":"fac6818a1d172415b6922001b36f75c81c071c55a5db0647c67ae8aa9dbd03b1","schema_version":"1.0","event_id":"sha256:fac6818a1d172415b6922001b36f75c81c071c55a5db0647c67ae8aa9dbd03b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5J2YITGCO2LZAWLVGYTGKRXP5S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Seongwan Park, Taeklim Kim, Youngjoong Ko","submitted_at":"2025-05-28T02:50:17Z","abstract_excerpt":"Despite their strong performance, Dense Passage Retrieval (DPR) models suffer from a lack of interpretability. In this work, we propose a novel interpretability framework that leverages Sparse Autoencoders (SAEs) to decompose previously uninterpretable dense embeddings from DPR models into distinct, interpretable latent concepts. We generate natural language descriptions for each latent concept, enabling human interpretations of both the dense embeddings and the query-document similarity scores of DPR models. We further introduce Concept-Level Sparse Retrieval (CL-SR), a retrieval framework th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00041","kind":"arxiv","version":2},"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/2506.00041/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":"2026-07-05T12:00:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zBFRywPNcmrE5YGpNvX+KWE1IiHVan+EttsOBy/As4NAD7kAwqL0A7bpSDSJKJECVR0HhGe1k0VYYOLKgxMLDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T07:22:28.931182Z"},"content_sha256":"395b1f38453dbf682d87ac9139bd7c3ae6be7c23c9f472a5a2c13cecc84155c5","schema_version":"1.0","event_id":"sha256:395b1f38453dbf682d87ac9139bd7c3ae6be7c23c9f472a5a2c13cecc84155c5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5J2YITGCO2LZAWLVGYTGKRXP5S/bundle.json","state_url":"https://pith.science/pith/5J2YITGCO2LZAWLVGYTGKRXP5S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5J2YITGCO2LZAWLVGYTGKRXP5S/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":"2026-08-14T07:22:28Z","links":{"resolver":"https://pith.science/pith/5J2YITGCO2LZAWLVGYTGKRXP5S","bundle":"https://pith.science/pith/5J2YITGCO2LZAWLVGYTGKRXP5S/bundle.json","state":"https://pith.science/pith/5J2YITGCO2LZAWLVGYTGKRXP5S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5J2YITGCO2LZAWLVGYTGKRXP5S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5J2YITGCO2LZAWLVGYTGKRXP5S","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":"01f32f0dd8360ab777f7a792bcbbf1ba2d6eb089896133b1f59784caff58ae64","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-28T02:50:17Z","title_canon_sha256":"f8075fe0802c9af489f2ff1fe76d6f39bffc864490e30609a7ca47a62d3c6a37"},"schema_version":"1.0","source":{"id":"2506.00041","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00041","created_at":"2026-07-05T12:00:01Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00041v2","created_at":"2026-07-05T12:00:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00041","created_at":"2026-07-05T12:00:01Z"},{"alias_kind":"pith_short_12","alias_value":"5J2YITGCO2LZ","created_at":"2026-07-05T12:00:01Z"},{"alias_kind":"pith_short_16","alias_value":"5J2YITGCO2LZAWLV","created_at":"2026-07-05T12:00:01Z"},{"alias_kind":"pith_short_8","alias_value":"5J2YITGC","created_at":"2026-07-05T12:00:01Z"}],"graph_snapshots":[{"event_id":"sha256:395b1f38453dbf682d87ac9139bd7c3ae6be7c23c9f472a5a2c13cecc84155c5","target":"graph","created_at":"2026-07-05T12:00:01Z","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/2506.00041/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite their strong performance, Dense Passage Retrieval (DPR) models suffer from a lack of interpretability. In this work, we propose a novel interpretability framework that leverages Sparse Autoencoders (SAEs) to decompose previously uninterpretable dense embeddings from DPR models into distinct, interpretable latent concepts. We generate natural language descriptions for each latent concept, enabling human interpretations of both the dense embeddings and the query-document similarity scores of DPR models. We further introduce Concept-Level Sparse Retrieval (CL-SR), a retrieval framework th","authors_text":"Seongwan Park, Taeklim Kim, Youngjoong Ko","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-28T02:50:17Z","title":"Decoding Dense Embeddings: Sparse Autoencoders for Interpreting and Discretizing Dense Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00041","kind":"arxiv","version":2},"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:fac6818a1d172415b6922001b36f75c81c071c55a5db0647c67ae8aa9dbd03b1","target":"record","created_at":"2026-07-05T12:00:01Z","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":"01f32f0dd8360ab777f7a792bcbbf1ba2d6eb089896133b1f59784caff58ae64","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-05-28T02:50:17Z","title_canon_sha256":"f8075fe0802c9af489f2ff1fe76d6f39bffc864490e30609a7ca47a62d3c6a37"},"schema_version":"1.0","source":{"id":"2506.00041","kind":"arxiv","version":2}},"canonical_sha256":"ea75844cc2769790597536266546efeca42a4a00932b64d152c6858fecfe668f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea75844cc2769790597536266546efeca42a4a00932b64d152c6858fecfe668f","first_computed_at":"2026-07-05T12:00:01.636009Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:00:01.636009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kUA1CbrIvdF0PTpHBgK0i+jV2mxgPhxzfr1WJVAFQdgSAEH3nRFMugnnpQrWTJ6hgdqSb9QqO1Ynho8O6pjFAg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:00:01.636481Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00041","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fac6818a1d172415b6922001b36f75c81c071c55a5db0647c67ae8aa9dbd03b1","sha256:395b1f38453dbf682d87ac9139bd7c3ae6be7c23c9f472a5a2c13cecc84155c5"],"state_sha256":"44e7a66de339a16b51ccebe962b11cf84c96652c85d0aba42c78c9c55fca8d3d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"163qCcpT8rKz3O8lYHNXodsHpT2/6dQbEj2cuOHEjFFRJhI4xHFJeIXTvm8qwClv1zj9sgP4/D56/BuJXVlGBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T07:22:28.937522Z","bundle_sha256":"2920c8b80305cb3de32f4f40cb66fb5ef85944e34ba341a05eb3dd9109110c10"}}