{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AKDJ3NL6MTR7OJBQVLN6I3TEA7","short_pith_number":"pith:AKDJ3NL6","canonical_record":{"source":{"id":"2507.09615","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-13T12:38:38Z","cross_cats_sorted":[],"title_canon_sha256":"1461f9f454cb86915de870b953ee4167429a7c77065596631cbc139ebf6816a7","abstract_canon_sha256":"ff3f249ff049c95d968e1f3a168bbc9b6979e26a42fb6b7ebb2f1ae0ffff0d9f"},"schema_version":"1.0"},"canonical_sha256":"02869db57e64e3f72430aadbe46e6407c8d77778959cb6548f82203ac0eccb0f","source":{"kind":"arxiv","id":"2507.09615","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.09615","created_at":"2026-07-05T11:36:36Z"},{"alias_kind":"arxiv_version","alias_value":"2507.09615v1","created_at":"2026-07-05T11:36:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09615","created_at":"2026-07-05T11:36:36Z"},{"alias_kind":"pith_short_12","alias_value":"AKDJ3NL6MTR7","created_at":"2026-07-05T11:36:36Z"},{"alias_kind":"pith_short_16","alias_value":"AKDJ3NL6MTR7OJBQ","created_at":"2026-07-05T11:36:36Z"},{"alias_kind":"pith_short_8","alias_value":"AKDJ3NL6","created_at":"2026-07-05T11:36:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AKDJ3NL6MTR7OJBQVLN6I3TEA7","target":"record","payload":{"canonical_record":{"source":{"id":"2507.09615","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-13T12:38:38Z","cross_cats_sorted":[],"title_canon_sha256":"1461f9f454cb86915de870b953ee4167429a7c77065596631cbc139ebf6816a7","abstract_canon_sha256":"ff3f249ff049c95d968e1f3a168bbc9b6979e26a42fb6b7ebb2f1ae0ffff0d9f"},"schema_version":"1.0"},"canonical_sha256":"02869db57e64e3f72430aadbe46e6407c8d77778959cb6548f82203ac0eccb0f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:36.788301Z","signature_b64":"3MQyGhSsW8oVEmKZzwUwGGqPiizxnFikuo8ezfhN0+KvHCZHcMErsEAv5EqFF+VIIIkwM5lPm5X9XFs82TMCCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02869db57e64e3f72430aadbe46e6407c8d77778959cb6548f82203ac0eccb0f","last_reissued_at":"2026-07-05T11:36:36.787871Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:36.787871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.09615","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":"2026-07-05T11:36:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"isgpbaPSVt/hR7DlrWKO9QX7t8WvIx4E03SzLZ8c7ZOOZ6MMNdAgpbeOgCsgGGg6jsncbe/iecgho3rf4tV/Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T04:29:06.324404Z"},"content_sha256":"f89f3cb7c27a58fcf738527c6db20f53d0bef8827b308638ea0ecbf4e2e60fe2","schema_version":"1.0","event_id":"sha256:f89f3cb7c27a58fcf738527c6db20f53d0bef8827b308638ea0ecbf4e2e60fe2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AKDJ3NL6MTR7OJBQVLN6I3TEA7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Fine-Grained Adaptation of CLIP via a Self-Trained Alignment Score","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chetan Arora, Eman Ali, Muhammad Haris Khan, Sathira Silva","submitted_at":"2025-07-13T12:38:38Z","abstract_excerpt":"Vision-language models (VLMs) like CLIP excel in zero-shot learning by aligning image and text representations through contrastive pretraining. Existing approaches to unsupervised adaptation (UA) for fine-grained classification with VLMs either rely on fixed alignment scores that cannot capture evolving, subtle class distinctions or use computationally expensive pseudo-labeling strategies that limit scalability. In contrast, we show that modeling fine-grained cross-modal interactions during adaptation produces more accurate, class-discriminative pseudo-labels and substantially improves perform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09615","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/2507.09615/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":"2026-07-05T11:36:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qg7rNDzD+MI1b8UF6RcWQEGWiI+lP1EAbd/5pEjFtW7n3CZ6Y4vRqMeS5VGnrHRGVsCePwJoJZqDEekD2NucAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T04:29:06.324891Z"},"content_sha256":"e5ce1574683432b799c933749ab986676f8d47dd7ef072292c72e74051fed61b","schema_version":"1.0","event_id":"sha256:e5ce1574683432b799c933749ab986676f8d47dd7ef072292c72e74051fed61b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AKDJ3NL6MTR7OJBQVLN6I3TEA7/bundle.json","state_url":"https://pith.science/pith/AKDJ3NL6MTR7OJBQVLN6I3TEA7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AKDJ3NL6MTR7OJBQVLN6I3TEA7/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":"2026-08-20T04:29:06Z","links":{"resolver":"https://pith.science/pith/AKDJ3NL6MTR7OJBQVLN6I3TEA7","bundle":"https://pith.science/pith/AKDJ3NL6MTR7OJBQVLN6I3TEA7/bundle.json","state":"https://pith.science/pith/AKDJ3NL6MTR7OJBQVLN6I3TEA7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AKDJ3NL6MTR7OJBQVLN6I3TEA7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AKDJ3NL6MTR7OJBQVLN6I3TEA7","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":"ff3f249ff049c95d968e1f3a168bbc9b6979e26a42fb6b7ebb2f1ae0ffff0d9f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-13T12:38:38Z","title_canon_sha256":"1461f9f454cb86915de870b953ee4167429a7c77065596631cbc139ebf6816a7"},"schema_version":"1.0","source":{"id":"2507.09615","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.09615","created_at":"2026-07-05T11:36:36Z"},{"alias_kind":"arxiv_version","alias_value":"2507.09615v1","created_at":"2026-07-05T11:36:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09615","created_at":"2026-07-05T11:36:36Z"},{"alias_kind":"pith_short_12","alias_value":"AKDJ3NL6MTR7","created_at":"2026-07-05T11:36:36Z"},{"alias_kind":"pith_short_16","alias_value":"AKDJ3NL6MTR7OJBQ","created_at":"2026-07-05T11:36:36Z"},{"alias_kind":"pith_short_8","alias_value":"AKDJ3NL6","created_at":"2026-07-05T11:36:36Z"}],"graph_snapshots":[{"event_id":"sha256:e5ce1574683432b799c933749ab986676f8d47dd7ef072292c72e74051fed61b","target":"graph","created_at":"2026-07-05T11:36:36Z","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/2507.09615/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) like CLIP excel in zero-shot learning by aligning image and text representations through contrastive pretraining. Existing approaches to unsupervised adaptation (UA) for fine-grained classification with VLMs either rely on fixed alignment scores that cannot capture evolving, subtle class distinctions or use computationally expensive pseudo-labeling strategies that limit scalability. In contrast, we show that modeling fine-grained cross-modal interactions during adaptation produces more accurate, class-discriminative pseudo-labels and substantially improves perform","authors_text":"Chetan Arora, Eman Ali, Muhammad Haris Khan, Sathira Silva","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-13T12:38:38Z","title":"Towards Fine-Grained Adaptation of CLIP via a Self-Trained Alignment Score"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09615","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:f89f3cb7c27a58fcf738527c6db20f53d0bef8827b308638ea0ecbf4e2e60fe2","target":"record","created_at":"2026-07-05T11:36:36Z","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":"ff3f249ff049c95d968e1f3a168bbc9b6979e26a42fb6b7ebb2f1ae0ffff0d9f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-13T12:38:38Z","title_canon_sha256":"1461f9f454cb86915de870b953ee4167429a7c77065596631cbc139ebf6816a7"},"schema_version":"1.0","source":{"id":"2507.09615","kind":"arxiv","version":1}},"canonical_sha256":"02869db57e64e3f72430aadbe46e6407c8d77778959cb6548f82203ac0eccb0f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"02869db57e64e3f72430aadbe46e6407c8d77778959cb6548f82203ac0eccb0f","first_computed_at":"2026-07-05T11:36:36.787871Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:36.787871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3MQyGhSsW8oVEmKZzwUwGGqPiizxnFikuo8ezfhN0+KvHCZHcMErsEAv5EqFF+VIIIkwM5lPm5X9XFs82TMCCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:36.788301Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.09615","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f89f3cb7c27a58fcf738527c6db20f53d0bef8827b308638ea0ecbf4e2e60fe2","sha256:e5ce1574683432b799c933749ab986676f8d47dd7ef072292c72e74051fed61b"],"state_sha256":"6a5e5056919ac92c98bb015c6aaf8be727e57cc26cec15206eae8276af3455a9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"djvF6bBNTPYgG8OowXrQqIrQa0rKZHzO+v00Dmut2TlCt/6CItxok9n5bD6nkpFsBw5zTZWO+NRGTSAq9uJKBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T04:29:06.328468Z","bundle_sha256":"94799f9b67ec9ad35126790417f1e363e4b6cfc33e2b6a7984512c85274f7b4c"}}