{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7UEJE4HLQOZDCTVE6EY6VX4GDV","short_pith_number":"pith:7UEJE4HL","canonical_record":{"source":{"id":"2412.07802","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-08T20:46:23Z","cross_cats_sorted":[],"title_canon_sha256":"a5e4798d2a5fe5cfd773a4d53bb77d8533e80e8578d31eb94739bab2262850af","abstract_canon_sha256":"8a7490c0c42ec3ea5488248144b8b47be0dc7223a858fb7a6539336c5b2f3bc9"},"schema_version":"1.0"},"canonical_sha256":"fd089270eb83b2314ea4f131eadf861d4c6a6617cd6ab461f2dbca836ac46a4b","source":{"kind":"arxiv","id":"2412.07802","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.07802","created_at":"2026-07-05T09:47:39Z"},{"alias_kind":"arxiv_version","alias_value":"2412.07802v1","created_at":"2026-07-05T09:47:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07802","created_at":"2026-07-05T09:47:39Z"},{"alias_kind":"pith_short_12","alias_value":"7UEJE4HLQOZD","created_at":"2026-07-05T09:47:39Z"},{"alias_kind":"pith_short_16","alias_value":"7UEJE4HLQOZDCTVE","created_at":"2026-07-05T09:47:39Z"},{"alias_kind":"pith_short_8","alias_value":"7UEJE4HL","created_at":"2026-07-05T09:47:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7UEJE4HLQOZDCTVE6EY6VX4GDV","target":"record","payload":{"canonical_record":{"source":{"id":"2412.07802","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-08T20:46:23Z","cross_cats_sorted":[],"title_canon_sha256":"a5e4798d2a5fe5cfd773a4d53bb77d8533e80e8578d31eb94739bab2262850af","abstract_canon_sha256":"8a7490c0c42ec3ea5488248144b8b47be0dc7223a858fb7a6539336c5b2f3bc9"},"schema_version":"1.0"},"canonical_sha256":"fd089270eb83b2314ea4f131eadf861d4c6a6617cd6ab461f2dbca836ac46a4b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:39.371769Z","signature_b64":"fwglKZVSljtVZzo9mGojZtOKnMTs8vtJUPV553bleCJXVzeJEcDOD9s6V9A60E9axRdNYiBg1awZC+0VQAwyBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd089270eb83b2314ea4f131eadf861d4c6a6617cd6ab461f2dbca836ac46a4b","last_reissued_at":"2026-07-05T09:47:39.369048Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:39.369048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.07802","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":"2026-07-05T09:47:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OhTePDu8BQAPjOjTpfyxlBSC3XEGVXIhPKufTeWyGCTQHoLkulmqc7MjkfhoGvtdzVaviBp4tpPova98tDZADw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:38:25.446889Z"},"content_sha256":"194f5529db2fc13fe69846a0a44f56e0b7c1dbf7ae1465ab699130e3f2eff340","schema_version":"1.0","event_id":"sha256:194f5529db2fc13fe69846a0a44f56e0b7c1dbf7ae1465ab699130e3f2eff340"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7UEJE4HLQOZDCTVE6EY6VX4GDV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Language Model as Visual Explainer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Xinchao Wang, Xingyi Yang","submitted_at":"2024-12-08T20:46:23Z","abstract_excerpt":"In this paper, we present Language Model as Visual Explainer LVX, a systematic approach for interpreting the internal workings of vision models using a tree-structured linguistic explanation, without the need for model training. Central to our strategy is the collaboration between vision models and LLM to craft explanations. On one hand, the LLM is harnessed to delineate hierarchical visual attributes, while concurrently, a text-to-image API retrieves images that are most aligned with these textual concepts. By mapping the collected texts and images to the vision model's embedding space, we co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07802","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/2412.07802/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":"2026-07-05T09:47:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ohD7mXBgguZJUhNFvQoNC3ZlPhyI8Fxr8AOnfFUkJxWT3T+FBIGDVJNLPE0vLk/beALFNorXVHNZ/w4EEALnBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:38:25.447373Z"},"content_sha256":"7fe6df368ce6128ac848e2fc5b3c07a501ef255fb19b3a92cc1c52beaad94153","schema_version":"1.0","event_id":"sha256:7fe6df368ce6128ac848e2fc5b3c07a501ef255fb19b3a92cc1c52beaad94153"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7UEJE4HLQOZDCTVE6EY6VX4GDV/bundle.json","state_url":"https://pith.science/pith/7UEJE4HLQOZDCTVE6EY6VX4GDV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7UEJE4HLQOZDCTVE6EY6VX4GDV/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":"2026-08-06T18:38:25Z","links":{"resolver":"https://pith.science/pith/7UEJE4HLQOZDCTVE6EY6VX4GDV","bundle":"https://pith.science/pith/7UEJE4HLQOZDCTVE6EY6VX4GDV/bundle.json","state":"https://pith.science/pith/7UEJE4HLQOZDCTVE6EY6VX4GDV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7UEJE4HLQOZDCTVE6EY6VX4GDV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7UEJE4HLQOZDCTVE6EY6VX4GDV","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":"8a7490c0c42ec3ea5488248144b8b47be0dc7223a858fb7a6539336c5b2f3bc9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-08T20:46:23Z","title_canon_sha256":"a5e4798d2a5fe5cfd773a4d53bb77d8533e80e8578d31eb94739bab2262850af"},"schema_version":"1.0","source":{"id":"2412.07802","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.07802","created_at":"2026-07-05T09:47:39Z"},{"alias_kind":"arxiv_version","alias_value":"2412.07802v1","created_at":"2026-07-05T09:47:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07802","created_at":"2026-07-05T09:47:39Z"},{"alias_kind":"pith_short_12","alias_value":"7UEJE4HLQOZD","created_at":"2026-07-05T09:47:39Z"},{"alias_kind":"pith_short_16","alias_value":"7UEJE4HLQOZDCTVE","created_at":"2026-07-05T09:47:39Z"},{"alias_kind":"pith_short_8","alias_value":"7UEJE4HL","created_at":"2026-07-05T09:47:39Z"}],"graph_snapshots":[{"event_id":"sha256:7fe6df368ce6128ac848e2fc5b3c07a501ef255fb19b3a92cc1c52beaad94153","target":"graph","created_at":"2026-07-05T09:47:39Z","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/2412.07802/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present Language Model as Visual Explainer LVX, a systematic approach for interpreting the internal workings of vision models using a tree-structured linguistic explanation, without the need for model training. Central to our strategy is the collaboration between vision models and LLM to craft explanations. On one hand, the LLM is harnessed to delineate hierarchical visual attributes, while concurrently, a text-to-image API retrieves images that are most aligned with these textual concepts. By mapping the collected texts and images to the vision model's embedding space, we co","authors_text":"Xinchao Wang, Xingyi Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-08T20:46:23Z","title":"Language Model as Visual Explainer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07802","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":"sha256:194f5529db2fc13fe69846a0a44f56e0b7c1dbf7ae1465ab699130e3f2eff340","target":"record","created_at":"2026-07-05T09:47:39Z","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":"8a7490c0c42ec3ea5488248144b8b47be0dc7223a858fb7a6539336c5b2f3bc9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-08T20:46:23Z","title_canon_sha256":"a5e4798d2a5fe5cfd773a4d53bb77d8533e80e8578d31eb94739bab2262850af"},"schema_version":"1.0","source":{"id":"2412.07802","kind":"arxiv","version":1}},"canonical_sha256":"fd089270eb83b2314ea4f131eadf861d4c6a6617cd6ab461f2dbca836ac46a4b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd089270eb83b2314ea4f131eadf861d4c6a6617cd6ab461f2dbca836ac46a4b","first_computed_at":"2026-07-05T09:47:39.369048Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:47:39.369048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fwglKZVSljtVZzo9mGojZtOKnMTs8vtJUPV553bleCJXVzeJEcDOD9s6V9A60E9axRdNYiBg1awZC+0VQAwyBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:47:39.371769Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.07802","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:194f5529db2fc13fe69846a0a44f56e0b7c1dbf7ae1465ab699130e3f2eff340","sha256:7fe6df368ce6128ac848e2fc5b3c07a501ef255fb19b3a92cc1c52beaad94153"],"state_sha256":"4876c67b6850a6e3f245ddef4d2da066a72a9adf89c452bc1114565bfd14d574"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3se2Yop8kn95BMOoU9y39pjF+Pb3OivV9hkFPdy1Em+Rhy6CRDX8r3+ubXKIwcSczGWQrRbIcYVJsdIe/uELBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T18:38:25.452514Z","bundle_sha256":"1aef684bf08eea16a3cca836fffdcab8f5e247b03383fb7cf12d95ba7760526c"}}