{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QUUU6NTVQPVSSJXXIZTZOAFYDE","short_pith_number":"pith:QUUU6NTV","canonical_record":{"source":{"id":"2506.23822","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T13:14:46Z","cross_cats_sorted":[],"title_canon_sha256":"d033fbc5d922d6c4f8c4d74f07b63efe20bab6bea36bf502f238dcc15e656974","abstract_canon_sha256":"53e9864c047d7be1a5e5dca4cb77c4b002e5ecae4b303adf5bebd9256130f789"},"schema_version":"1.0"},"canonical_sha256":"85294f367583eb2926f746679700b819384b0762b32f7a12eb77dc0b44566264","source":{"kind":"arxiv","id":"2506.23822","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23822","created_at":"2026-07-05T11:29:28Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23822v1","created_at":"2026-07-05T11:29:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23822","created_at":"2026-07-05T11:29:28Z"},{"alias_kind":"pith_short_12","alias_value":"QUUU6NTVQPVS","created_at":"2026-07-05T11:29:28Z"},{"alias_kind":"pith_short_16","alias_value":"QUUU6NTVQPVSSJXX","created_at":"2026-07-05T11:29:28Z"},{"alias_kind":"pith_short_8","alias_value":"QUUU6NTV","created_at":"2026-07-05T11:29:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QUUU6NTVQPVSSJXXIZTZOAFYDE","target":"record","payload":{"canonical_record":{"source":{"id":"2506.23822","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T13:14:46Z","cross_cats_sorted":[],"title_canon_sha256":"d033fbc5d922d6c4f8c4d74f07b63efe20bab6bea36bf502f238dcc15e656974","abstract_canon_sha256":"53e9864c047d7be1a5e5dca4cb77c4b002e5ecae4b303adf5bebd9256130f789"},"schema_version":"1.0"},"canonical_sha256":"85294f367583eb2926f746679700b819384b0762b32f7a12eb77dc0b44566264","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:28.377888Z","signature_b64":"R3Ks58nIQIaE8uLtjWcqt1lx7pTuq3lQMTnPqvgWttNlV79f3remgv7MKiysbPS9u6CtNT0wIG0RV+EqwvuUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85294f367583eb2926f746679700b819384b0762b32f7a12eb77dc0b44566264","last_reissued_at":"2026-07-05T11:29:28.377395Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:28.377395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.23822","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":"2026-07-05T11:29:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dNTWyNFoxiu7SwDHIAg5owQuZqdLN9MgbxpNROGZLoc8V8oa9JQ3WRibF3ci5zVCSsBCouELk/Jmx6SrKgTvDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T06:36:18.640405Z"},"content_sha256":"0d5bf711ecdca7327e4f4e5128e39b5e980465907b87d1ac40d8b57c71268ead","schema_version":"1.0","event_id":"sha256:0d5bf711ecdca7327e4f4e5128e39b5e980465907b87d1ac40d8b57c71268ead"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QUUU6NTVQPVSSJXXIZTZOAFYDE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Interpretable Zero-Shot Learning with Locally-Aligned Vision-Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bowen Duan, Fahad Shahbaz Khan, Salman Khan, Shiming Chen","submitted_at":"2025-06-30T13:14:46Z","abstract_excerpt":"Large-scale vision-language models (VLMs), such as CLIP, have achieved remarkable success in zero-shot learning (ZSL) by leveraging large-scale visual-text pair datasets. However, these methods often lack interpretability, as they compute the similarity between an entire query image and the embedded category words, making it difficult to explain their predictions. One approach to address this issue is to develop interpretable models by integrating language, where classifiers are built using discrete attributes, similar to human perception. This introduces a new challenge: how to effectively al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23822","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/2506.23822/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":"2026-07-05T11:29:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5IYm4kn78nM++SyEnFH0o7A2w+YIe2kUlGFQF69Vta90R+/vtwciXykKz7lrvpP6dNksHSXs0apGTZ5gd/+NDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T06:36:18.640784Z"},"content_sha256":"fa7b094f0e4de6905ac1a221f69ee4142048e8377bbfdc08ce3c5a1a36260948","schema_version":"1.0","event_id":"sha256:fa7b094f0e4de6905ac1a221f69ee4142048e8377bbfdc08ce3c5a1a36260948"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QUUU6NTVQPVSSJXXIZTZOAFYDE/bundle.json","state_url":"https://pith.science/pith/QUUU6NTVQPVSSJXXIZTZOAFYDE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QUUU6NTVQPVSSJXXIZTZOAFYDE/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":"2026-07-08T06:36:18Z","links":{"resolver":"https://pith.science/pith/QUUU6NTVQPVSSJXXIZTZOAFYDE","bundle":"https://pith.science/pith/QUUU6NTVQPVSSJXXIZTZOAFYDE/bundle.json","state":"https://pith.science/pith/QUUU6NTVQPVSSJXXIZTZOAFYDE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QUUU6NTVQPVSSJXXIZTZOAFYDE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QUUU6NTVQPVSSJXXIZTZOAFYDE","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":"53e9864c047d7be1a5e5dca4cb77c4b002e5ecae4b303adf5bebd9256130f789","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T13:14:46Z","title_canon_sha256":"d033fbc5d922d6c4f8c4d74f07b63efe20bab6bea36bf502f238dcc15e656974"},"schema_version":"1.0","source":{"id":"2506.23822","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.23822","created_at":"2026-07-05T11:29:28Z"},{"alias_kind":"arxiv_version","alias_value":"2506.23822v1","created_at":"2026-07-05T11:29:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23822","created_at":"2026-07-05T11:29:28Z"},{"alias_kind":"pith_short_12","alias_value":"QUUU6NTVQPVS","created_at":"2026-07-05T11:29:28Z"},{"alias_kind":"pith_short_16","alias_value":"QUUU6NTVQPVSSJXX","created_at":"2026-07-05T11:29:28Z"},{"alias_kind":"pith_short_8","alias_value":"QUUU6NTV","created_at":"2026-07-05T11:29:28Z"}],"graph_snapshots":[{"event_id":"sha256:fa7b094f0e4de6905ac1a221f69ee4142048e8377bbfdc08ce3c5a1a36260948","target":"graph","created_at":"2026-07-05T11:29:28Z","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/2506.23822/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large-scale vision-language models (VLMs), such as CLIP, have achieved remarkable success in zero-shot learning (ZSL) by leveraging large-scale visual-text pair datasets. However, these methods often lack interpretability, as they compute the similarity between an entire query image and the embedded category words, making it difficult to explain their predictions. One approach to address this issue is to develop interpretable models by integrating language, where classifiers are built using discrete attributes, similar to human perception. This introduces a new challenge: how to effectively al","authors_text":"Bowen Duan, Fahad Shahbaz Khan, Salman Khan, Shiming Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T13:14:46Z","title":"Interpretable Zero-Shot Learning with Locally-Aligned Vision-Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23822","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":"sha256:0d5bf711ecdca7327e4f4e5128e39b5e980465907b87d1ac40d8b57c71268ead","target":"record","created_at":"2026-07-05T11:29:28Z","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":"53e9864c047d7be1a5e5dca4cb77c4b002e5ecae4b303adf5bebd9256130f789","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-30T13:14:46Z","title_canon_sha256":"d033fbc5d922d6c4f8c4d74f07b63efe20bab6bea36bf502f238dcc15e656974"},"schema_version":"1.0","source":{"id":"2506.23822","kind":"arxiv","version":1}},"canonical_sha256":"85294f367583eb2926f746679700b819384b0762b32f7a12eb77dc0b44566264","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85294f367583eb2926f746679700b819384b0762b32f7a12eb77dc0b44566264","first_computed_at":"2026-07-05T11:29:28.377395Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:28.377395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R3Ks58nIQIaE8uLtjWcqt1lx7pTuq3lQMTnPqvgWttNlV79f3remgv7MKiysbPS9u6CtNT0wIG0RV+EqwvuUBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:28.377888Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.23822","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d5bf711ecdca7327e4f4e5128e39b5e980465907b87d1ac40d8b57c71268ead","sha256:fa7b094f0e4de6905ac1a221f69ee4142048e8377bbfdc08ce3c5a1a36260948"],"state_sha256":"635115a735bb553a98eec019377a7a748df37e3d09bd242caa15c34f08395d62"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tvIKLiGnUaFcOPi4xFszxlM35wYgLREnANrtnfYTKoHrPmFPUMYJWE64oninKM+rqvp+EK8lMBoCEcjZKtGjAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T06:36:18.642979Z","bundle_sha256":"5bf7f1ead11eb4fa4bca6cece557bc0fff0ddffc52b6a214e5546fd956652413"}}