{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:36R35NS7WFKQR5RE5APQJ5QMOJ","short_pith_number":"pith:36R35NS7","canonical_record":{"source":{"id":"2605.24946","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-24T08:47:36Z","cross_cats_sorted":[],"title_canon_sha256":"189676d0397fa4d144bceec8dd897344ad78f9608d4810d9833696b971b653be","abstract_canon_sha256":"3c8526ce6cabac31b7b889346249cd5b276912d9879b4042ccafa5e40b124f09"},"schema_version":"1.0"},"canonical_sha256":"dfa3beb65fb15508f624e81f04f60c727fa0365256bbd0dcfa54272ff9d709a0","source":{"kind":"arxiv","id":"2605.24946","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24946","created_at":"2026-05-26T01:04:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24946v1","created_at":"2026-05-26T01:04:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24946","created_at":"2026-05-26T01:04:07Z"},{"alias_kind":"pith_short_12","alias_value":"36R35NS7WFKQ","created_at":"2026-05-26T01:04:07Z"},{"alias_kind":"pith_short_16","alias_value":"36R35NS7WFKQR5RE","created_at":"2026-05-26T01:04:07Z"},{"alias_kind":"pith_short_8","alias_value":"36R35NS7","created_at":"2026-05-26T01:04:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:36R35NS7WFKQR5RE5APQJ5QMOJ","target":"record","payload":{"canonical_record":{"source":{"id":"2605.24946","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-24T08:47:36Z","cross_cats_sorted":[],"title_canon_sha256":"189676d0397fa4d144bceec8dd897344ad78f9608d4810d9833696b971b653be","abstract_canon_sha256":"3c8526ce6cabac31b7b889346249cd5b276912d9879b4042ccafa5e40b124f09"},"schema_version":"1.0"},"canonical_sha256":"dfa3beb65fb15508f624e81f04f60c727fa0365256bbd0dcfa54272ff9d709a0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:04:07.099224Z","signature_b64":"aqd8Pa50l++ppjRv31kp0+kYjVGzeU2EZ7RnBju9pBbeP6FxRUKJPh6kKG/v/a7RLSy9WfQ9BFjM6aEnoT8PDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfa3beb65fb15508f624e81f04f60c727fa0365256bbd0dcfa54272ff9d709a0","last_reissued_at":"2026-05-26T01:04:07.098578Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:04:07.098578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.24946","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":"2026-05-26T01:04:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gjNmqeAT6lcD5QeusMAJj3kwNx5sejlt8X5ESt8liCPxUKwqSOE57uPA1puFX/7V9CUVVJg9LLGRCWyH57A0Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T14:41:20.867721Z"},"content_sha256":"97c26065e3f26253462439cbfae8419034c461ee1673b75bd9614c3292f9d7e7","schema_version":"1.0","event_id":"sha256:97c26065e3f26253462439cbfae8419034c461ee1673b75bd9614c3292f9d7e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:36R35NS7WFKQR5RE5APQJ5QMOJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Interpretability Transfer from Language to Vision via Sparse Autoencoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexey Kravets, Chuan Li, Da Chen, Da Li, Vinay P. Namboodiri","submitted_at":"2026-05-24T08:47:36Z","abstract_excerpt":"Recent advances in language model interpretability using sparse autoencoders (SAEs) have yet to effectively translate to the visual domain, mainly due to the difficulty and ambiguity of labeling visual concepts. In this paper, we introduce Visual Interpretability via SAE Transfer Alignment (VISTA), a framework that transfers interpretability from language to vision in a LLaVA-style vision-language model by constraining a visual projector to map visual tokens into an LLM's pre-existing, labeled textual SAE space. This approach enables visual interpretability without training dedicated vision SA"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24946","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/2605.24946/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":"2026-05-26T01:04:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kRjo/w1FNGHIxTYpDEDF5qooJpxWH2jDaze4v24SUMVPAYufDIZjSlLGPkyk77Dubu/y+XaVNYLflaHNLNtiAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T14:41:20.868104Z"},"content_sha256":"1e3c3bece2be6d4728b8f82dbf96611f05cd53c72ae1a689798b20ee4e389b35","schema_version":"1.0","event_id":"sha256:1e3c3bece2be6d4728b8f82dbf96611f05cd53c72ae1a689798b20ee4e389b35"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/36R35NS7WFKQR5RE5APQJ5QMOJ/bundle.json","state_url":"https://pith.science/pith/36R35NS7WFKQR5RE5APQJ5QMOJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/36R35NS7WFKQR5RE5APQJ5QMOJ/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":"2026-06-05T14:41:20Z","links":{"resolver":"https://pith.science/pith/36R35NS7WFKQR5RE5APQJ5QMOJ","bundle":"https://pith.science/pith/36R35NS7WFKQR5RE5APQJ5QMOJ/bundle.json","state":"https://pith.science/pith/36R35NS7WFKQR5RE5APQJ5QMOJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/36R35NS7WFKQR5RE5APQJ5QMOJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:36R35NS7WFKQR5RE5APQJ5QMOJ","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":"3c8526ce6cabac31b7b889346249cd5b276912d9879b4042ccafa5e40b124f09","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-24T08:47:36Z","title_canon_sha256":"189676d0397fa4d144bceec8dd897344ad78f9608d4810d9833696b971b653be"},"schema_version":"1.0","source":{"id":"2605.24946","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24946","created_at":"2026-05-26T01:04:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24946v1","created_at":"2026-05-26T01:04:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24946","created_at":"2026-05-26T01:04:07Z"},{"alias_kind":"pith_short_12","alias_value":"36R35NS7WFKQ","created_at":"2026-05-26T01:04:07Z"},{"alias_kind":"pith_short_16","alias_value":"36R35NS7WFKQR5RE","created_at":"2026-05-26T01:04:07Z"},{"alias_kind":"pith_short_8","alias_value":"36R35NS7","created_at":"2026-05-26T01:04:07Z"}],"graph_snapshots":[{"event_id":"sha256:1e3c3bece2be6d4728b8f82dbf96611f05cd53c72ae1a689798b20ee4e389b35","target":"graph","created_at":"2026-05-26T01:04:07Z","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/2605.24946/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in language model interpretability using sparse autoencoders (SAEs) have yet to effectively translate to the visual domain, mainly due to the difficulty and ambiguity of labeling visual concepts. In this paper, we introduce Visual Interpretability via SAE Transfer Alignment (VISTA), a framework that transfers interpretability from language to vision in a LLaVA-style vision-language model by constraining a visual projector to map visual tokens into an LLM's pre-existing, labeled textual SAE space. This approach enables visual interpretability without training dedicated vision SA","authors_text":"Alexey Kravets, Chuan Li, Da Chen, Da Li, Vinay P. Namboodiri","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-24T08:47:36Z","title":"Interpretability Transfer from Language to Vision via Sparse Autoencoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24946","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":"sha256:97c26065e3f26253462439cbfae8419034c461ee1673b75bd9614c3292f9d7e7","target":"record","created_at":"2026-05-26T01:04:07Z","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":"3c8526ce6cabac31b7b889346249cd5b276912d9879b4042ccafa5e40b124f09","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-24T08:47:36Z","title_canon_sha256":"189676d0397fa4d144bceec8dd897344ad78f9608d4810d9833696b971b653be"},"schema_version":"1.0","source":{"id":"2605.24946","kind":"arxiv","version":1}},"canonical_sha256":"dfa3beb65fb15508f624e81f04f60c727fa0365256bbd0dcfa54272ff9d709a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dfa3beb65fb15508f624e81f04f60c727fa0365256bbd0dcfa54272ff9d709a0","first_computed_at":"2026-05-26T01:04:07.098578Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:04:07.098578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aqd8Pa50l++ppjRv31kp0+kYjVGzeU2EZ7RnBju9pBbeP6FxRUKJPh6kKG/v/a7RLSy9WfQ9BFjM6aEnoT8PDw==","signature_status":"signed_v1","signed_at":"2026-05-26T01:04:07.099224Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24946","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:97c26065e3f26253462439cbfae8419034c461ee1673b75bd9614c3292f9d7e7","sha256:1e3c3bece2be6d4728b8f82dbf96611f05cd53c72ae1a689798b20ee4e389b35"],"state_sha256":"0a3fa510d9f8ccea854af077e8d8504f58506a1eef070b8fcf8cbf2766c1979c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vlAzSslxkyjXTeg26J7EbeX1ZllTsF0DgKjO2UogtBjJB8asJSCz7JJRga9W0V7svHOo917uVApKXhCOgSE1Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T14:41:20.870182Z","bundle_sha256":"8ae648806494996ff1b6a3e05cf4c217fbc80fac46dfd31c1ce5ce26b13ab13e"}}