{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CG3PZN22PGSOM5C3SAWTASJPPF","short_pith_number":"pith:CG3PZN22","canonical_record":{"source":{"id":"2508.09363","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-12T21:45:10Z","cross_cats_sorted":[],"title_canon_sha256":"c4b0e805da3314571bc8bb4f362e40ffb6843657002dd2844eedd94d483c6723","abstract_canon_sha256":"783c6f1693168e5c09fd241c490163e373097ac97367b31778e15e33583e338c"},"schema_version":"1.0"},"canonical_sha256":"11b6fcb75a79a4e6745b902d30492f7968f3ff6ee5d112ac42a8dc21737a4f2f","source":{"kind":"arxiv","id":"2508.09363","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.09363","created_at":"2026-07-05T11:53:13Z"},{"alias_kind":"arxiv_version","alias_value":"2508.09363v1","created_at":"2026-07-05T11:53:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09363","created_at":"2026-07-05T11:53:13Z"},{"alias_kind":"pith_short_12","alias_value":"CG3PZN22PGSO","created_at":"2026-07-05T11:53:13Z"},{"alias_kind":"pith_short_16","alias_value":"CG3PZN22PGSOM5C3","created_at":"2026-07-05T11:53:13Z"},{"alias_kind":"pith_short_8","alias_value":"CG3PZN22","created_at":"2026-07-05T11:53:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CG3PZN22PGSOM5C3SAWTASJPPF","target":"record","payload":{"canonical_record":{"source":{"id":"2508.09363","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-12T21:45:10Z","cross_cats_sorted":[],"title_canon_sha256":"c4b0e805da3314571bc8bb4f362e40ffb6843657002dd2844eedd94d483c6723","abstract_canon_sha256":"783c6f1693168e5c09fd241c490163e373097ac97367b31778e15e33583e338c"},"schema_version":"1.0"},"canonical_sha256":"11b6fcb75a79a4e6745b902d30492f7968f3ff6ee5d112ac42a8dc21737a4f2f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:13.445263Z","signature_b64":"+2sE22aGFQxwTrgUvIDhUtfqz9oPYwSVvSIi54LaUUFJpZTAJFYRHLLwdEaUpQEca/9NZ0MVJvrExTDXeQ+gDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11b6fcb75a79a4e6745b902d30492f7968f3ff6ee5d112ac42a8dc21737a4f2f","last_reissued_at":"2026-07-05T11:53:13.444811Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:13.444811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.09363","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":"2026-07-05T11:53:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EW11wOOToqhqLi271I5HlHIw7/HEwICZo0fGx8oR9eJ1tqeWQ84JHnV2VHYSHlko76RrTzUI40x4o22EOAf1Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:14:39.676380Z"},"content_sha256":"1f5146124f0f127f223670b6a681e6bd695b815c96c0eae3f73f56911f1a4bee","schema_version":"1.0","event_id":"sha256:1f5146124f0f127f223670b6a681e6bd695b815c96c0eae3f73f56911f1a4bee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CG3PZN22PGSOM5C3SAWTASJPPF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Resurrecting the Salmon: Rethinking Mechanistic Interpretability with Domain-Specific Sparse Autoencoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Charles O'Neill, Max Kirkby, Mudith Jayasekara","submitted_at":"2025-08-12T21:45:10Z","abstract_excerpt":"Sparse autoencoders (SAEs) decompose large language model (LLM) activations into latent features that reveal mechanistic structure. Conventional SAEs train on broad data distributions, forcing a fixed latent budget to capture only high-frequency, generic patterns. This often results in significant linear ``dark matter'' in reconstruction error and produces latents that fragment or absorb each other, complicating interpretation. We show that restricting SAE training to a well-defined domain (medical text) reallocates capacity to domain-specific features, improving both reconstruction fidelity a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09363","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/2508.09363/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":"2026-07-05T11:53:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d88Xm13I1BekBVYe5zF1/EnNcSIvjTBqnUoIaq0EqPC8iCkCtsDSdU1lhF6MVg94D/eh0dQAgLbLkHnv5Ar2Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:14:39.676883Z"},"content_sha256":"6ed726da9b09670fbdcd0c86f30e6801340bfbed2f4f282c0b2febdfd15e0ddf","schema_version":"1.0","event_id":"sha256:6ed726da9b09670fbdcd0c86f30e6801340bfbed2f4f282c0b2febdfd15e0ddf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CG3PZN22PGSOM5C3SAWTASJPPF/bundle.json","state_url":"https://pith.science/pith/CG3PZN22PGSOM5C3SAWTASJPPF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CG3PZN22PGSOM5C3SAWTASJPPF/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":"2026-08-04T09:14:39Z","links":{"resolver":"https://pith.science/pith/CG3PZN22PGSOM5C3SAWTASJPPF","bundle":"https://pith.science/pith/CG3PZN22PGSOM5C3SAWTASJPPF/bundle.json","state":"https://pith.science/pith/CG3PZN22PGSOM5C3SAWTASJPPF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CG3PZN22PGSOM5C3SAWTASJPPF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CG3PZN22PGSOM5C3SAWTASJPPF","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":"783c6f1693168e5c09fd241c490163e373097ac97367b31778e15e33583e338c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-12T21:45:10Z","title_canon_sha256":"c4b0e805da3314571bc8bb4f362e40ffb6843657002dd2844eedd94d483c6723"},"schema_version":"1.0","source":{"id":"2508.09363","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.09363","created_at":"2026-07-05T11:53:13Z"},{"alias_kind":"arxiv_version","alias_value":"2508.09363v1","created_at":"2026-07-05T11:53:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.09363","created_at":"2026-07-05T11:53:13Z"},{"alias_kind":"pith_short_12","alias_value":"CG3PZN22PGSO","created_at":"2026-07-05T11:53:13Z"},{"alias_kind":"pith_short_16","alias_value":"CG3PZN22PGSOM5C3","created_at":"2026-07-05T11:53:13Z"},{"alias_kind":"pith_short_8","alias_value":"CG3PZN22","created_at":"2026-07-05T11:53:13Z"}],"graph_snapshots":[{"event_id":"sha256:6ed726da9b09670fbdcd0c86f30e6801340bfbed2f4f282c0b2febdfd15e0ddf","target":"graph","created_at":"2026-07-05T11:53:13Z","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/2508.09363/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sparse autoencoders (SAEs) decompose large language model (LLM) activations into latent features that reveal mechanistic structure. Conventional SAEs train on broad data distributions, forcing a fixed latent budget to capture only high-frequency, generic patterns. This often results in significant linear ``dark matter'' in reconstruction error and produces latents that fragment or absorb each other, complicating interpretation. We show that restricting SAE training to a well-defined domain (medical text) reallocates capacity to domain-specific features, improving both reconstruction fidelity a","authors_text":"Charles O'Neill, Max Kirkby, Mudith Jayasekara","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-12T21:45:10Z","title":"Resurrecting the Salmon: Rethinking Mechanistic Interpretability with Domain-Specific Sparse Autoencoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.09363","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":"sha256:1f5146124f0f127f223670b6a681e6bd695b815c96c0eae3f73f56911f1a4bee","target":"record","created_at":"2026-07-05T11:53:13Z","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":"783c6f1693168e5c09fd241c490163e373097ac97367b31778e15e33583e338c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-12T21:45:10Z","title_canon_sha256":"c4b0e805da3314571bc8bb4f362e40ffb6843657002dd2844eedd94d483c6723"},"schema_version":"1.0","source":{"id":"2508.09363","kind":"arxiv","version":1}},"canonical_sha256":"11b6fcb75a79a4e6745b902d30492f7968f3ff6ee5d112ac42a8dc21737a4f2f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11b6fcb75a79a4e6745b902d30492f7968f3ff6ee5d112ac42a8dc21737a4f2f","first_computed_at":"2026-07-05T11:53:13.444811Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:53:13.444811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+2sE22aGFQxwTrgUvIDhUtfqz9oPYwSVvSIi54LaUUFJpZTAJFYRHLLwdEaUpQEca/9NZ0MVJvrExTDXeQ+gDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:53:13.445263Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.09363","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f5146124f0f127f223670b6a681e6bd695b815c96c0eae3f73f56911f1a4bee","sha256:6ed726da9b09670fbdcd0c86f30e6801340bfbed2f4f282c0b2febdfd15e0ddf"],"state_sha256":"ae69f44e411aaeebd5fd870583f1843d011053ac9ffbcb86b617dec4ba4027cd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7E1Kp3u0AA/t/3XSwjhbW2587r8WwW0GOfbCdB8gnjo2aceubLKS5weQ/sTEV66uWnF/uSJLQOYwnGqmM+XbCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T09:14:39.681865Z","bundle_sha256":"3d24b69f6cf31f5f8e24f0cdba63c8c0f9f4e635b14172efb3092e921010f82a"}}