{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:Y5237MN4WW45A44UCDGIZ3SVU7","short_pith_number":"pith:Y5237MN4","canonical_record":{"source":{"id":"2606.25657","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-24T10:11:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"94b2fb8af466b30ae1ef3b00ee16c7c96abfde85938df3873a58d4d066c558f7","abstract_canon_sha256":"117c369bc8f8dfbc7d6fee55661ff5eb05233b432a12fc4489e5a72fb4d9b128"},"schema_version":"1.0"},"canonical_sha256":"c775bfb1bcb5b9d0739410cc8cee55a7c2eba58187ad0949004c8e1f61f00b31","source":{"kind":"arxiv","id":"2606.25657","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.25657","created_at":"2026-06-25T01:18:11Z"},{"alias_kind":"arxiv_version","alias_value":"2606.25657v1","created_at":"2026-06-25T01:18:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25657","created_at":"2026-06-25T01:18:11Z"},{"alias_kind":"pith_short_12","alias_value":"Y5237MN4WW45","created_at":"2026-06-25T01:18:11Z"},{"alias_kind":"pith_short_16","alias_value":"Y5237MN4WW45A44U","created_at":"2026-06-25T01:18:11Z"},{"alias_kind":"pith_short_8","alias_value":"Y5237MN4","created_at":"2026-06-25T01:18:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:Y5237MN4WW45A44UCDGIZ3SVU7","target":"record","payload":{"canonical_record":{"source":{"id":"2606.25657","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-24T10:11:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"94b2fb8af466b30ae1ef3b00ee16c7c96abfde85938df3873a58d4d066c558f7","abstract_canon_sha256":"117c369bc8f8dfbc7d6fee55661ff5eb05233b432a12fc4489e5a72fb4d9b128"},"schema_version":"1.0"},"canonical_sha256":"c775bfb1bcb5b9d0739410cc8cee55a7c2eba58187ad0949004c8e1f61f00b31","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:18:11.964997Z","signature_b64":"qWfp+yZrY6EIFgTAYIBBOQAff6mevEIqUCnO3VfIpm7tZBAAizs6EAQI0hiTOAKOGweZyZslpb42A5YJBojpAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c775bfb1bcb5b9d0739410cc8cee55a7c2eba58187ad0949004c8e1f61f00b31","last_reissued_at":"2026-06-25T01:18:11.964543Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:18:11.964543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.25657","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":"2026-06-25T01:18:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mpsEaZ4ej2U53Z4MaOlgWJFTFW215zxSC6wd9tMInUTTozfogJs30rPRpmzWEfYtUBnlTIT5lEHqomOcUGWJCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T17:56:54.379085Z"},"content_sha256":"9f07cdbb2e0c5696f60ae90b1d9724728e139e9de4606eaf30dc78d33d852304","schema_version":"1.0","event_id":"sha256:9f07cdbb2e0c5696f60ae90b1d9724728e139e9de4606eaf30dc78d33d852304"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:Y5237MN4WW45A44UCDGIZ3SVU7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Steering Vision-Language Models with Joint Sparse Autoencoders","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hongxu Lin, Hui Li, Huizhen Shu, Wenjie Sun, Xuying Li","submitted_at":"2026-06-24T10:11:04Z","abstract_excerpt":"Sparse Autoencoders (SAEs) have shown promise for analyzing language models, but applying them to vision-language models (VLMs) often yields representations that are difficult to use as controllable cross-modal steering directions. We introduce the Joint Sparse Autoencoder (JSAE), which uses an explicit alignment constraint to jointly factorize sequence-pooled vision and language activations into shared, interpretable image/caption-level features. Applied to LLaVA, JSAE recovers cross-modal features for recognizable concepts (e.g., food and animals). Through bidirectional interventions (additi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25657","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/2606.25657/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":"2026-06-25T01:18:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/Or/tWMgqi9TvabPPDLKr9SG3bCs0lru5IrtEgLlxNUClJOAcaGnbHwpRMYlQ16FxyqKaAow8rQyl8A2S6DtCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T17:56:54.379475Z"},"content_sha256":"fe133889bf0327a263f80863f814144b0d596920358680fb4d3849b7ff8cb8b9","schema_version":"1.0","event_id":"sha256:fe133889bf0327a263f80863f814144b0d596920358680fb4d3849b7ff8cb8b9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y5237MN4WW45A44UCDGIZ3SVU7/bundle.json","state_url":"https://pith.science/pith/Y5237MN4WW45A44UCDGIZ3SVU7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y5237MN4WW45A44UCDGIZ3SVU7/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":"2026-06-27T17:56:54Z","links":{"resolver":"https://pith.science/pith/Y5237MN4WW45A44UCDGIZ3SVU7","bundle":"https://pith.science/pith/Y5237MN4WW45A44UCDGIZ3SVU7/bundle.json","state":"https://pith.science/pith/Y5237MN4WW45A44UCDGIZ3SVU7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y5237MN4WW45A44UCDGIZ3SVU7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Y5237MN4WW45A44UCDGIZ3SVU7","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":"117c369bc8f8dfbc7d6fee55661ff5eb05233b432a12fc4489e5a72fb4d9b128","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-24T10:11:04Z","title_canon_sha256":"94b2fb8af466b30ae1ef3b00ee16c7c96abfde85938df3873a58d4d066c558f7"},"schema_version":"1.0","source":{"id":"2606.25657","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.25657","created_at":"2026-06-25T01:18:11Z"},{"alias_kind":"arxiv_version","alias_value":"2606.25657v1","created_at":"2026-06-25T01:18:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25657","created_at":"2026-06-25T01:18:11Z"},{"alias_kind":"pith_short_12","alias_value":"Y5237MN4WW45","created_at":"2026-06-25T01:18:11Z"},{"alias_kind":"pith_short_16","alias_value":"Y5237MN4WW45A44U","created_at":"2026-06-25T01:18:11Z"},{"alias_kind":"pith_short_8","alias_value":"Y5237MN4","created_at":"2026-06-25T01:18:11Z"}],"graph_snapshots":[{"event_id":"sha256:fe133889bf0327a263f80863f814144b0d596920358680fb4d3849b7ff8cb8b9","target":"graph","created_at":"2026-06-25T01:18:11Z","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/2606.25657/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sparse Autoencoders (SAEs) have shown promise for analyzing language models, but applying them to vision-language models (VLMs) often yields representations that are difficult to use as controllable cross-modal steering directions. We introduce the Joint Sparse Autoencoder (JSAE), which uses an explicit alignment constraint to jointly factorize sequence-pooled vision and language activations into shared, interpretable image/caption-level features. Applied to LLaVA, JSAE recovers cross-modal features for recognizable concepts (e.g., food and animals). Through bidirectional interventions (additi","authors_text":"Hongxu Lin, Hui Li, Huizhen Shu, Wenjie Sun, Xuying Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-24T10:11:04Z","title":"Steering Vision-Language Models with Joint Sparse Autoencoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25657","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":"sha256:9f07cdbb2e0c5696f60ae90b1d9724728e139e9de4606eaf30dc78d33d852304","target":"record","created_at":"2026-06-25T01:18:11Z","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":"117c369bc8f8dfbc7d6fee55661ff5eb05233b432a12fc4489e5a72fb4d9b128","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-24T10:11:04Z","title_canon_sha256":"94b2fb8af466b30ae1ef3b00ee16c7c96abfde85938df3873a58d4d066c558f7"},"schema_version":"1.0","source":{"id":"2606.25657","kind":"arxiv","version":1}},"canonical_sha256":"c775bfb1bcb5b9d0739410cc8cee55a7c2eba58187ad0949004c8e1f61f00b31","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c775bfb1bcb5b9d0739410cc8cee55a7c2eba58187ad0949004c8e1f61f00b31","first_computed_at":"2026-06-25T01:18:11.964543Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T01:18:11.964543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qWfp+yZrY6EIFgTAYIBBOQAff6mevEIqUCnO3VfIpm7tZBAAizs6EAQI0hiTOAKOGweZyZslpb42A5YJBojpAQ==","signature_status":"signed_v1","signed_at":"2026-06-25T01:18:11.964997Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.25657","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9f07cdbb2e0c5696f60ae90b1d9724728e139e9de4606eaf30dc78d33d852304","sha256:fe133889bf0327a263f80863f814144b0d596920358680fb4d3849b7ff8cb8b9"],"state_sha256":"cdbe813f38387a54b7938b621c7b17ee53eadeb4a18769d91a7dee7ba2cb4444"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2GzfCs0Vj69N7Huu/D+ylXLopZzf2i9jWbYQfcCwgSk+pZabbRHakipJxjIXCCtmNmsxOjziitMdgjnEnPIqCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T17:56:54.381438Z","bundle_sha256":"d38b5a6d5ed6d351aba3d8c089cfb8c0738bb1f6a33557cf752fe81445b9e65d"}}