{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:7P66B7MY7OJ3L7OIXBL2FRKNKW","short_pith_number":"pith:7P66B7MY","canonical_record":{"source":{"id":"2604.02327","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-02T17:59:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b940763bb9d5a0ea3e53be657b942f62c314988e99ceab1d62aab2810685e154","abstract_canon_sha256":"26f000de02dec66b5c68612376b1ed0eaea07292a3441ab6c73ad318a4701f6b"},"schema_version":"1.0"},"canonical_sha256":"fbfde0fd98fb93b5fdc8b857a2c54d55b6d86cec7988d43185abacd564374464","source":{"kind":"arxiv","id":"2604.02327","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.02327","created_at":"2026-06-30T02:17:19Z"},{"alias_kind":"arxiv_version","alias_value":"2604.02327v2","created_at":"2026-06-30T02:17:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.02327","created_at":"2026-06-30T02:17:19Z"},{"alias_kind":"pith_short_12","alias_value":"7P66B7MY7OJ3","created_at":"2026-06-30T02:17:19Z"},{"alias_kind":"pith_short_16","alias_value":"7P66B7MY7OJ3L7OI","created_at":"2026-06-30T02:17:19Z"},{"alias_kind":"pith_short_8","alias_value":"7P66B7MY","created_at":"2026-06-30T02:17:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:7P66B7MY7OJ3L7OIXBL2FRKNKW","target":"record","payload":{"canonical_record":{"source":{"id":"2604.02327","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-02T17:59:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b940763bb9d5a0ea3e53be657b942f62c314988e99ceab1d62aab2810685e154","abstract_canon_sha256":"26f000de02dec66b5c68612376b1ed0eaea07292a3441ab6c73ad318a4701f6b"},"schema_version":"1.0"},"canonical_sha256":"fbfde0fd98fb93b5fdc8b857a2c54d55b6d86cec7988d43185abacd564374464","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:19.976959Z","signature_b64":"D39588tQCr/cO8qr/yVEDpCQmHSLaH23GXUuA4VV3rJ6sgGU9RuMqfcCVAj384igf8yeEkzyLWnWAqhWZJCpDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbfde0fd98fb93b5fdc8b857a2c54d55b6d86cec7988d43185abacd564374464","last_reissued_at":"2026-06-30T02:17:19.976354Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:19.976354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.02327","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":"2026-06-30T02:17:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ArLs4kv+wk/FZ5BApdruXUn5jHHYlnfRx7yb7JmrOfZD3didkpZ/tSJPOun4aWApDiEEiDrFq4iC5CuWU/FiCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T12:47:52.112354Z"},"content_sha256":"485901fc6b3fae2550078f75204b0b5ba83a22382d234ddbf622c761d1874324","schema_version":"1.0","event_id":"sha256:485901fc6b3fae2550078f75204b0b5ba83a22382d234ddbf622c761d1874324"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:7P66B7MY7OJ3L7OIXBL2FRKNKW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Steerable Visual Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Deva Ramanan, Jona Ruthardt, Makarand Tapaswi, Manu Gaur, Yuki M. Asano","submitted_at":"2026-04-02T17:59:49Z","abstract_excerpt":"Pretrained Vision Transformers (ViTs) such as DINOv2 and MAE provide generic image features that can be applied to a variety of downstream tasks such as retrieval, classification, and segmentation. However, such representations tend to focus on the most salient visual cues in the image, with no way to direct them toward less prominent concepts of interest. In contrast, Multimodal LLMs can be guided with textual prompts, but the resulting representations tend to be language-centric and lose their effectiveness for generic visual tasks. To address this, we introduce Steerable Visual Representati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.02327","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/2604.02327/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":"2026-06-30T02:17:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OeyFKYGhWPIP0nMq4PbOvAWeDBPVEzhICKQuEZ0dxmoIKlI4wvjApW4jKEXHcPutfjz4mLgYR5o7oFXKKdtwBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T12:47:52.112951Z"},"content_sha256":"cb69952a8796efbd79a49eb0f06c3157a996828a921c885b1b02f49c83afabbc","schema_version":"1.0","event_id":"sha256:cb69952a8796efbd79a49eb0f06c3157a996828a921c885b1b02f49c83afabbc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7P66B7MY7OJ3L7OIXBL2FRKNKW/bundle.json","state_url":"https://pith.science/pith/7P66B7MY7OJ3L7OIXBL2FRKNKW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7P66B7MY7OJ3L7OIXBL2FRKNKW/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":"2026-08-06T12:47:52Z","links":{"resolver":"https://pith.science/pith/7P66B7MY7OJ3L7OIXBL2FRKNKW","bundle":"https://pith.science/pith/7P66B7MY7OJ3L7OIXBL2FRKNKW/bundle.json","state":"https://pith.science/pith/7P66B7MY7OJ3L7OIXBL2FRKNKW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7P66B7MY7OJ3L7OIXBL2FRKNKW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7P66B7MY7OJ3L7OIXBL2FRKNKW","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":"26f000de02dec66b5c68612376b1ed0eaea07292a3441ab6c73ad318a4701f6b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-02T17:59:49Z","title_canon_sha256":"b940763bb9d5a0ea3e53be657b942f62c314988e99ceab1d62aab2810685e154"},"schema_version":"1.0","source":{"id":"2604.02327","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.02327","created_at":"2026-06-30T02:17:19Z"},{"alias_kind":"arxiv_version","alias_value":"2604.02327v2","created_at":"2026-06-30T02:17:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.02327","created_at":"2026-06-30T02:17:19Z"},{"alias_kind":"pith_short_12","alias_value":"7P66B7MY7OJ3","created_at":"2026-06-30T02:17:19Z"},{"alias_kind":"pith_short_16","alias_value":"7P66B7MY7OJ3L7OI","created_at":"2026-06-30T02:17:19Z"},{"alias_kind":"pith_short_8","alias_value":"7P66B7MY","created_at":"2026-06-30T02:17:19Z"}],"graph_snapshots":[{"event_id":"sha256:cb69952a8796efbd79a49eb0f06c3157a996828a921c885b1b02f49c83afabbc","target":"graph","created_at":"2026-06-30T02:17:19Z","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/2604.02327/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretrained Vision Transformers (ViTs) such as DINOv2 and MAE provide generic image features that can be applied to a variety of downstream tasks such as retrieval, classification, and segmentation. However, such representations tend to focus on the most salient visual cues in the image, with no way to direct them toward less prominent concepts of interest. In contrast, Multimodal LLMs can be guided with textual prompts, but the resulting representations tend to be language-centric and lose their effectiveness for generic visual tasks. To address this, we introduce Steerable Visual Representati","authors_text":"Deva Ramanan, Jona Ruthardt, Makarand Tapaswi, Manu Gaur, Yuki M. Asano","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-02T17:59:49Z","title":"Steerable Visual Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.02327","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":"sha256:485901fc6b3fae2550078f75204b0b5ba83a22382d234ddbf622c761d1874324","target":"record","created_at":"2026-06-30T02:17:19Z","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":"26f000de02dec66b5c68612376b1ed0eaea07292a3441ab6c73ad318a4701f6b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-02T17:59:49Z","title_canon_sha256":"b940763bb9d5a0ea3e53be657b942f62c314988e99ceab1d62aab2810685e154"},"schema_version":"1.0","source":{"id":"2604.02327","kind":"arxiv","version":2}},"canonical_sha256":"fbfde0fd98fb93b5fdc8b857a2c54d55b6d86cec7988d43185abacd564374464","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fbfde0fd98fb93b5fdc8b857a2c54d55b6d86cec7988d43185abacd564374464","first_computed_at":"2026-06-30T02:17:19.976354Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:17:19.976354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D39588tQCr/cO8qr/yVEDpCQmHSLaH23GXUuA4VV3rJ6sgGU9RuMqfcCVAj384igf8yeEkzyLWnWAqhWZJCpDg==","signature_status":"signed_v1","signed_at":"2026-06-30T02:17:19.976959Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.02327","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:485901fc6b3fae2550078f75204b0b5ba83a22382d234ddbf622c761d1874324","sha256:cb69952a8796efbd79a49eb0f06c3157a996828a921c885b1b02f49c83afabbc"],"state_sha256":"4867827a39c0813612914bc3f5d3c3165f67b53e35025cbd7d615f1431ca1c49"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"efj/3/0eTwbfRYvzntQWmapdyaZAoD0nYbXLeWGgtFPsQBJPfBPzySSWFDaY93j0y4ziC5f+nCDkn2ebjN02Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T12:47:52.116732Z","bundle_sha256":"77517496211b61882b0d4278e3ff432b6225b692fa1a4c58af87a469fb83e818"}}