{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WCTPKLEPVYO2EKNPE2U57Y7T7T","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":"4819410bd4129b183ad0100412882565bfeb8fdfe081e39749f1712376bf1212","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T14:54:58Z","title_canon_sha256":"2e17122db56ddbf6224db644a95f5fcb8a7d4f42aae8ae7fd6c3e1a22c3cd08d"},"schema_version":"1.0","source":{"id":"2605.28567","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28567","created_at":"2026-05-28T02:04:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28567v1","created_at":"2026-05-28T02:04:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28567","created_at":"2026-05-28T02:04:56Z"},{"alias_kind":"pith_short_12","alias_value":"WCTPKLEPVYO2","created_at":"2026-05-28T02:04:56Z"},{"alias_kind":"pith_short_16","alias_value":"WCTPKLEPVYO2EKNP","created_at":"2026-05-28T02:04:56Z"},{"alias_kind":"pith_short_8","alias_value":"WCTPKLEP","created_at":"2026-05-28T02:04:56Z"}],"graph_snapshots":[{"event_id":"sha256:88ccb45337bf34739b88f51e91822c2300902abe9691cf20dd0873df8ad9cd92","target":"graph","created_at":"2026-05-28T02:04:56Z","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/2605.28567/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sparse autoencoders (SAEs) have become a central tool for interpreting language models. However, two key SAE analyses that remain difficult to scale are (1) matching semantically similar features across multi-layers and (2) compressing large feature circuits into interpretable supernodes. Although these have been treated as separate problems, we show that both are instances of a more fundamental challenge, which we frame as the estimation of semantic distances between SAE features that lie on different activation manifolds. We introduce a distributional framework for this problem, in which eac","authors_text":"My T. Thai, Nguyen Do, Tue M. Cao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T14:54:58Z","title":"Semantic Optimal Transport for Sparse Autoencoder Feature Matching and Circuit Compression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28567","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":"sha256:0d9e462843cced9786bcc0fe9e806f404e325c481bf4f0efb64726e2fa6edb8d","target":"record","created_at":"2026-05-28T02:04:56Z","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":"4819410bd4129b183ad0100412882565bfeb8fdfe081e39749f1712376bf1212","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T14:54:58Z","title_canon_sha256":"2e17122db56ddbf6224db644a95f5fcb8a7d4f42aae8ae7fd6c3e1a22c3cd08d"},"schema_version":"1.0","source":{"id":"2605.28567","kind":"arxiv","version":1}},"canonical_sha256":"b0a6f52c8fae1da229af26a9dfe3f3fce01b323038dbc7f7f474dff65c60d716","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0a6f52c8fae1da229af26a9dfe3f3fce01b323038dbc7f7f474dff65c60d716","first_computed_at":"2026-05-28T02:04:56.587026Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T02:04:56.587026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xcDwoESGOSE5jp2yHOf/vQHJiOBIm03jAATMBm1WK1Cjc6i/MwG7ugF6jT4GHxdee4MidZfmOi0Ru8JWwRacDA==","signature_status":"signed_v1","signed_at":"2026-05-28T02:04:56.587540Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28567","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d9e462843cced9786bcc0fe9e806f404e325c481bf4f0efb64726e2fa6edb8d","sha256:88ccb45337bf34739b88f51e91822c2300902abe9691cf20dd0873df8ad9cd92"],"state_sha256":"041591430c5b7f668019d58f0339fe13a974c6f6f038ce740d8c527884e285f9"}