{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2TESRFOUKDUPRW6HHNFECRXTIZ","short_pith_number":"pith:2TESRFOU","canonical_record":{"source":{"id":"2406.01583","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-03T17:58:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d5db6b181ecf17c0bbb7d6070658c417f27fdc63b2ee806184a59e3967eaacf7","abstract_canon_sha256":"d12a65e426fd7780c4b858a8b4c8113d1f2e823a463ebeb13f073850195f1696"},"schema_version":"1.0"},"canonical_sha256":"d4c92895d450e8f8dbc73b4a4146f346797b89a53dd8b1fdccb2c2423d482387","source":{"kind":"arxiv","id":"2406.01583","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01583","created_at":"2026-07-05T09:23:06Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01583v2","created_at":"2026-07-05T09:23:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01583","created_at":"2026-07-05T09:23:06Z"},{"alias_kind":"pith_short_12","alias_value":"2TESRFOUKDUP","created_at":"2026-07-05T09:23:06Z"},{"alias_kind":"pith_short_16","alias_value":"2TESRFOUKDUPRW6H","created_at":"2026-07-05T09:23:06Z"},{"alias_kind":"pith_short_8","alias_value":"2TESRFOU","created_at":"2026-07-05T09:23:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2TESRFOUKDUPRW6HHNFECRXTIZ","target":"record","payload":{"canonical_record":{"source":{"id":"2406.01583","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-03T17:58:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d5db6b181ecf17c0bbb7d6070658c417f27fdc63b2ee806184a59e3967eaacf7","abstract_canon_sha256":"d12a65e426fd7780c4b858a8b4c8113d1f2e823a463ebeb13f073850195f1696"},"schema_version":"1.0"},"canonical_sha256":"d4c92895d450e8f8dbc73b4a4146f346797b89a53dd8b1fdccb2c2423d482387","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:06.537963Z","signature_b64":"eDpB8TG/3SHDQHKoNZw3kz3iFDSUhGmLi54wcjo/SUV6CRGRdAy7dEHuilT9r3WASnAvZ7HX6cvt8i1OFQgdDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4c92895d450e8f8dbc73b4a4146f346797b89a53dd8b1fdccb2c2423d482387","last_reissued_at":"2026-07-05T09:23:06.537557Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:06.537557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.01583","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":"2026-07-05T09:23:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Sp08aRavBdwSu4BqajZ1nILiOGUmLYTnl7ofNw/rd805E0BiwgyZwhEo8DdzzyMCzRfsUf4AmzHKxlx1dj2CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T15:12:52.312676Z"},"content_sha256":"98c664cc11291053accd927a4063dcb6b4a7fa5a11f1edde44dd6ab7a347fce6","schema_version":"1.0","event_id":"sha256:98c664cc11291053accd927a4063dcb6b4a7fa5a11f1edde44dd6ab7a347fce6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2TESRFOUKDUPRW6HHNFECRXTIZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Samyadeep Basu, Soheil Feizi, Sriram Balasubramanian","submitted_at":"2024-06-03T17:58:43Z","abstract_excerpt":"Recent work has explored how individual components of the CLIP-ViT model contribute to the final representation by leveraging the shared image-text representation space of CLIP. These components, such as attention heads and MLPs, have been shown to capture distinct image features like shape, color or texture. However, understanding the role of these components in arbitrary vision transformers (ViTs) is challenging. To this end, we introduce a general framework which can identify the roles of various components in ViTs beyond CLIP. Specifically, we (a) automate the decomposition of the final re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01583","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/2406.01583/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":"2026-07-05T09:23:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sjamkqni88BDX7i/bSUhbEw9bv/IS4pevgzHgzrLX8GPGr8WENW8WNPgGgI34pXIdVxL0CKSn8IbJQkMwV7YDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T15:12:52.313197Z"},"content_sha256":"62e9ccb6a57f1a2a3f869cbebf2b7e3f7ee2579a39d654678f758ccdde5f974a","schema_version":"1.0","event_id":"sha256:62e9ccb6a57f1a2a3f869cbebf2b7e3f7ee2579a39d654678f758ccdde5f974a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2TESRFOUKDUPRW6HHNFECRXTIZ/bundle.json","state_url":"https://pith.science/pith/2TESRFOUKDUPRW6HHNFECRXTIZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2TESRFOUKDUPRW6HHNFECRXTIZ/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":"2026-08-10T15:12:52Z","links":{"resolver":"https://pith.science/pith/2TESRFOUKDUPRW6HHNFECRXTIZ","bundle":"https://pith.science/pith/2TESRFOUKDUPRW6HHNFECRXTIZ/bundle.json","state":"https://pith.science/pith/2TESRFOUKDUPRW6HHNFECRXTIZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2TESRFOUKDUPRW6HHNFECRXTIZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2TESRFOUKDUPRW6HHNFECRXTIZ","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":"d12a65e426fd7780c4b858a8b4c8113d1f2e823a463ebeb13f073850195f1696","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-03T17:58:43Z","title_canon_sha256":"d5db6b181ecf17c0bbb7d6070658c417f27fdc63b2ee806184a59e3967eaacf7"},"schema_version":"1.0","source":{"id":"2406.01583","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01583","created_at":"2026-07-05T09:23:06Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01583v2","created_at":"2026-07-05T09:23:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01583","created_at":"2026-07-05T09:23:06Z"},{"alias_kind":"pith_short_12","alias_value":"2TESRFOUKDUP","created_at":"2026-07-05T09:23:06Z"},{"alias_kind":"pith_short_16","alias_value":"2TESRFOUKDUPRW6H","created_at":"2026-07-05T09:23:06Z"},{"alias_kind":"pith_short_8","alias_value":"2TESRFOU","created_at":"2026-07-05T09:23:06Z"}],"graph_snapshots":[{"event_id":"sha256:62e9ccb6a57f1a2a3f869cbebf2b7e3f7ee2579a39d654678f758ccdde5f974a","target":"graph","created_at":"2026-07-05T09:23:06Z","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/2406.01583/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work has explored how individual components of the CLIP-ViT model contribute to the final representation by leveraging the shared image-text representation space of CLIP. These components, such as attention heads and MLPs, have been shown to capture distinct image features like shape, color or texture. However, understanding the role of these components in arbitrary vision transformers (ViTs) is challenging. To this end, we introduce a general framework which can identify the roles of various components in ViTs beyond CLIP. Specifically, we (a) automate the decomposition of the final re","authors_text":"Samyadeep Basu, Soheil Feizi, Sriram Balasubramanian","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-03T17:58:43Z","title":"Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01583","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":"sha256:98c664cc11291053accd927a4063dcb6b4a7fa5a11f1edde44dd6ab7a347fce6","target":"record","created_at":"2026-07-05T09:23:06Z","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":"d12a65e426fd7780c4b858a8b4c8113d1f2e823a463ebeb13f073850195f1696","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-03T17:58:43Z","title_canon_sha256":"d5db6b181ecf17c0bbb7d6070658c417f27fdc63b2ee806184a59e3967eaacf7"},"schema_version":"1.0","source":{"id":"2406.01583","kind":"arxiv","version":2}},"canonical_sha256":"d4c92895d450e8f8dbc73b4a4146f346797b89a53dd8b1fdccb2c2423d482387","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d4c92895d450e8f8dbc73b4a4146f346797b89a53dd8b1fdccb2c2423d482387","first_computed_at":"2026-07-05T09:23:06.537557Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:23:06.537557Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eDpB8TG/3SHDQHKoNZw3kz3iFDSUhGmLi54wcjo/SUV6CRGRdAy7dEHuilT9r3WASnAvZ7HX6cvt8i1OFQgdDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:23:06.537963Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.01583","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98c664cc11291053accd927a4063dcb6b4a7fa5a11f1edde44dd6ab7a347fce6","sha256:62e9ccb6a57f1a2a3f869cbebf2b7e3f7ee2579a39d654678f758ccdde5f974a"],"state_sha256":"b0abd6d539dcda50c956ba3b0f5affbf894c9efdace06d21ec47bda14eeeeae3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rYYuns1oM5SSowWyQgtRDHFT7w/BIceHCQIgFMqvlPvPb3aqEmWQTbdYLB6zQ8Ro4FFIfx6+L59TtaObjkweDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T15:12:52.317554Z","bundle_sha256":"3d51ca5d162342c1959c81cf6d20015db39f4663adcaf72e44359798b454749d"}}