{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZF243VS5V4CRJDGW75EAL43RCU","short_pith_number":"pith:ZF243VS5","canonical_record":{"source":{"id":"2310.05916","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-09T17:59:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ab1913706ab914fe9faebcc6cee3d7c54bc3c15013f9ae40a7cbdd59e10389de","abstract_canon_sha256":"19aa51614a9d27616360d978a16618c4d9dd930b1bf560bc4721860ad204fda9"},"schema_version":"1.0"},"canonical_sha256":"c975cdd65daf05148cd6ff4805f371151cc87aa537f2097fe6f358a830baae98","source":{"kind":"arxiv","id":"2310.05916","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.05916","created_at":"2026-07-05T08:02:02Z"},{"alias_kind":"arxiv_version","alias_value":"2310.05916v4","created_at":"2026-07-05T08:02:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05916","created_at":"2026-07-05T08:02:02Z"},{"alias_kind":"pith_short_12","alias_value":"ZF243VS5V4CR","created_at":"2026-07-05T08:02:02Z"},{"alias_kind":"pith_short_16","alias_value":"ZF243VS5V4CRJDGW","created_at":"2026-07-05T08:02:02Z"},{"alias_kind":"pith_short_8","alias_value":"ZF243VS5","created_at":"2026-07-05T08:02:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZF243VS5V4CRJDGW75EAL43RCU","target":"record","payload":{"canonical_record":{"source":{"id":"2310.05916","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-09T17:59:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ab1913706ab914fe9faebcc6cee3d7c54bc3c15013f9ae40a7cbdd59e10389de","abstract_canon_sha256":"19aa51614a9d27616360d978a16618c4d9dd930b1bf560bc4721860ad204fda9"},"schema_version":"1.0"},"canonical_sha256":"c975cdd65daf05148cd6ff4805f371151cc87aa537f2097fe6f358a830baae98","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:02.235247Z","signature_b64":"ArHHhLTOEj0UA7msRZ1YSNrleGghGStQ+c3NQFE5YibjFZ5g+3kfU6NFDhU4cXY7ff8jJSw4FnVqIeKvaxkxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c975cdd65daf05148cd6ff4805f371151cc87aa537f2097fe6f358a830baae98","last_reissued_at":"2026-07-05T08:02:02.234778Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:02.234778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.05916","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:02:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"STkV9VcJoSZDE96gineGT36mzYiZybaALCrUbYZ4Yct2MPbSEBDJQrF7/s38/UABtGTWo2Q0d8umMqSlkPCTAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:23:48.322086Z"},"content_sha256":"e72fdbc688e8c795c098d632cec08ed71a3ffaf4e783ede9c668c4fdff36d18a","schema_version":"1.0","event_id":"sha256:e72fdbc688e8c795c098d632cec08ed71a3ffaf4e783ede9c668c4fdff36d18a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZF243VS5V4CRJDGW75EAL43RCU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Interpreting CLIP's Image Representation via Text-Based Decomposition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Alexei A. Efros, Jacob Steinhardt, Yossi Gandelsman","submitted_at":"2023-10-09T17:59:04Z","abstract_excerpt":"We investigate the CLIP image encoder by analyzing how individual model components affect the final representation. We decompose the image representation as a sum across individual image patches, model layers, and attention heads, and use CLIP's text representation to interpret the summands. Interpreting the attention heads, we characterize each head's role by automatically finding text representations that span its output space, which reveals property-specific roles for many heads (e.g. location or shape). Next, interpreting the image patches, we uncover an emergent spatial localization withi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05916","kind":"arxiv","version":4},"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/2310.05916/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":"2026-07-05T08:02:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c5vzhWQnFX8OVNdL3ptiOav2a4WvM25cFWYnf3dERRz1Tf/QbpTWAi2zbFeVvBpD8qcRIgitbzRkI4XP7DxbBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:23:48.322509Z"},"content_sha256":"dc5cc4ee196c3f0cb1aa907570e5bd74789222b26b4df6457c1733515e9128d3","schema_version":"1.0","event_id":"sha256:dc5cc4ee196c3f0cb1aa907570e5bd74789222b26b4df6457c1733515e9128d3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZF243VS5V4CRJDGW75EAL43RCU/bundle.json","state_url":"https://pith.science/pith/ZF243VS5V4CRJDGW75EAL43RCU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZF243VS5V4CRJDGW75EAL43RCU/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":"2026-08-06T00:23:48Z","links":{"resolver":"https://pith.science/pith/ZF243VS5V4CRJDGW75EAL43RCU","bundle":"https://pith.science/pith/ZF243VS5V4CRJDGW75EAL43RCU/bundle.json","state":"https://pith.science/pith/ZF243VS5V4CRJDGW75EAL43RCU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZF243VS5V4CRJDGW75EAL43RCU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZF243VS5V4CRJDGW75EAL43RCU","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":"19aa51614a9d27616360d978a16618c4d9dd930b1bf560bc4721860ad204fda9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-09T17:59:04Z","title_canon_sha256":"ab1913706ab914fe9faebcc6cee3d7c54bc3c15013f9ae40a7cbdd59e10389de"},"schema_version":"1.0","source":{"id":"2310.05916","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.05916","created_at":"2026-07-05T08:02:02Z"},{"alias_kind":"arxiv_version","alias_value":"2310.05916v4","created_at":"2026-07-05T08:02:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05916","created_at":"2026-07-05T08:02:02Z"},{"alias_kind":"pith_short_12","alias_value":"ZF243VS5V4CR","created_at":"2026-07-05T08:02:02Z"},{"alias_kind":"pith_short_16","alias_value":"ZF243VS5V4CRJDGW","created_at":"2026-07-05T08:02:02Z"},{"alias_kind":"pith_short_8","alias_value":"ZF243VS5","created_at":"2026-07-05T08:02:02Z"}],"graph_snapshots":[{"event_id":"sha256:dc5cc4ee196c3f0cb1aa907570e5bd74789222b26b4df6457c1733515e9128d3","target":"graph","created_at":"2026-07-05T08:02:02Z","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/2310.05916/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate the CLIP image encoder by analyzing how individual model components affect the final representation. We decompose the image representation as a sum across individual image patches, model layers, and attention heads, and use CLIP's text representation to interpret the summands. Interpreting the attention heads, we characterize each head's role by automatically finding text representations that span its output space, which reveals property-specific roles for many heads (e.g. location or shape). Next, interpreting the image patches, we uncover an emergent spatial localization withi","authors_text":"Alexei A. Efros, Jacob Steinhardt, Yossi Gandelsman","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-09T17:59:04Z","title":"Interpreting CLIP's Image Representation via Text-Based Decomposition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05916","kind":"arxiv","version":4},"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:e72fdbc688e8c795c098d632cec08ed71a3ffaf4e783ede9c668c4fdff36d18a","target":"record","created_at":"2026-07-05T08:02:02Z","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":"19aa51614a9d27616360d978a16618c4d9dd930b1bf560bc4721860ad204fda9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-09T17:59:04Z","title_canon_sha256":"ab1913706ab914fe9faebcc6cee3d7c54bc3c15013f9ae40a7cbdd59e10389de"},"schema_version":"1.0","source":{"id":"2310.05916","kind":"arxiv","version":4}},"canonical_sha256":"c975cdd65daf05148cd6ff4805f371151cc87aa537f2097fe6f358a830baae98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c975cdd65daf05148cd6ff4805f371151cc87aa537f2097fe6f358a830baae98","first_computed_at":"2026-07-05T08:02:02.234778Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:02.234778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ArHHhLTOEj0UA7msRZ1YSNrleGghGStQ+c3NQFE5YibjFZ5g+3kfU6NFDhU4cXY7ff8jJSw4FnVqIeKvaxkxCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:02.235247Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.05916","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e72fdbc688e8c795c098d632cec08ed71a3ffaf4e783ede9c668c4fdff36d18a","sha256:dc5cc4ee196c3f0cb1aa907570e5bd74789222b26b4df6457c1733515e9128d3"],"state_sha256":"1a54179def364a34b969a2e05746a29624235a808362314bdcdc09afc8c2e1db"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+NhPtZK+Hchzd9AA5HkuWplVxPIfXFbiggb8eoAdh+hn8BgNCskXWD1QdpmgWoSSeJozAsjo6FNdgXC6/HXPAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T00:23:48.325262Z","bundle_sha256":"4cbe90615073195e953c5a56c19865a0a5d01fd8a732e76e8f9f72d5439719ab"}}