{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:AZRI2CG4W2PVRHSR2XPKRGJWKA","short_pith_number":"pith:AZRI2CG4","canonical_record":{"source":{"id":"2607.13661","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-15T10:06:39Z","cross_cats_sorted":[],"title_canon_sha256":"2cc62e0f46690d8d845c4d4236b5e6ac9cf62ae82e8702bb9a3aa4b4f11411b0","abstract_canon_sha256":"c46954ad30958875061065724cd0b8f25ad44df553285772ae549cc2a691ef03"},"schema_version":"1.0"},"canonical_sha256":"06628d08dcb69f589e51d5dea899365007ff96792498ccdce9fa2cbf793015ce","source":{"kind":"arxiv","id":"2607.13661","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.13661","created_at":"2026-07-16T01:22:59Z"},{"alias_kind":"arxiv_version","alias_value":"2607.13661v1","created_at":"2026-07-16T01:22:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13661","created_at":"2026-07-16T01:22:59Z"},{"alias_kind":"pith_short_12","alias_value":"AZRI2CG4W2PV","created_at":"2026-07-16T01:22:59Z"},{"alias_kind":"pith_short_16","alias_value":"AZRI2CG4W2PVRHSR","created_at":"2026-07-16T01:22:59Z"},{"alias_kind":"pith_short_8","alias_value":"AZRI2CG4","created_at":"2026-07-16T01:22:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:AZRI2CG4W2PVRHSR2XPKRGJWKA","target":"record","payload":{"canonical_record":{"source":{"id":"2607.13661","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-15T10:06:39Z","cross_cats_sorted":[],"title_canon_sha256":"2cc62e0f46690d8d845c4d4236b5e6ac9cf62ae82e8702bb9a3aa4b4f11411b0","abstract_canon_sha256":"c46954ad30958875061065724cd0b8f25ad44df553285772ae549cc2a691ef03"},"schema_version":"1.0"},"canonical_sha256":"06628d08dcb69f589e51d5dea899365007ff96792498ccdce9fa2cbf793015ce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T01:22:59.470890Z","signature_b64":"SNozX5D6okPrIFKD7NcJBT+0QdbJ6JzwxON2VpQVCSjear2Gj8+ZLXItvW1l9VfBu5zMg9S1beVFd83i3ooECw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06628d08dcb69f589e51d5dea899365007ff96792498ccdce9fa2cbf793015ce","last_reissued_at":"2026-07-16T01:22:59.470002Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T01:22:59.470002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.13661","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":"2026-07-16T01:22:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3M95s+xdh3ocMOcbYggEOxoLeBc08r1WkMOhdm4l6YPH94TKOj/3X1xGvHjlQAr19u/UlYbjkKJLh3Y68a6XDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:49:47.252795Z"},"content_sha256":"85ae28408a8bb62602ef82d510edd193713b618294870b0244c94ab565847872","schema_version":"1.0","event_id":"sha256:85ae28408a8bb62602ef82d510edd193713b618294870b0244c94ab565847872"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:AZRI2CG4W2PVRHSR2XPKRGJWKA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fine-grained CLIP fine-tuning with self-annotated region alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antoni B. Chan, Chenyang Zhao, Janet H. Hsiao, Wei Lin","submitted_at":"2026-07-15T10:06:39Z","abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) has been shown to have limitations in its fine-grained dense feature representation, due to its pre-training focusing on matching the whole image to a text description. Considering the large data and computational burden in pre-training a vision-language model from scratch, a series of works aim to enhance the fine-grained ability of CLIP through a fine-tuning scheme. However, existing works suffer from a variety of limitations: additional region annotations are usually required, which limits the semantic diversity due to the predefined categories"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13661","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/2607.13661/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":"2026-07-16T01:22:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cZBKyHOGh+itEsWCxPTx9DYrnTiBqIW3wlAjt9BiNFJ2U1NEAzAlHlyPXBoo+XMmxCTx5VNkGcsCegYS5vjLBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:49:47.253285Z"},"content_sha256":"05622705b4420d273a80f2687c21b0a14b290f7f9a500edb99de08fb833e7124","schema_version":"1.0","event_id":"sha256:05622705b4420d273a80f2687c21b0a14b290f7f9a500edb99de08fb833e7124"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AZRI2CG4W2PVRHSR2XPKRGJWKA/bundle.json","state_url":"https://pith.science/pith/AZRI2CG4W2PVRHSR2XPKRGJWKA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AZRI2CG4W2PVRHSR2XPKRGJWKA/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":"2026-08-06T18:49:47Z","links":{"resolver":"https://pith.science/pith/AZRI2CG4W2PVRHSR2XPKRGJWKA","bundle":"https://pith.science/pith/AZRI2CG4W2PVRHSR2XPKRGJWKA/bundle.json","state":"https://pith.science/pith/AZRI2CG4W2PVRHSR2XPKRGJWKA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AZRI2CG4W2PVRHSR2XPKRGJWKA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AZRI2CG4W2PVRHSR2XPKRGJWKA","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":"c46954ad30958875061065724cd0b8f25ad44df553285772ae549cc2a691ef03","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-15T10:06:39Z","title_canon_sha256":"2cc62e0f46690d8d845c4d4236b5e6ac9cf62ae82e8702bb9a3aa4b4f11411b0"},"schema_version":"1.0","source":{"id":"2607.13661","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.13661","created_at":"2026-07-16T01:22:59Z"},{"alias_kind":"arxiv_version","alias_value":"2607.13661v1","created_at":"2026-07-16T01:22:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13661","created_at":"2026-07-16T01:22:59Z"},{"alias_kind":"pith_short_12","alias_value":"AZRI2CG4W2PV","created_at":"2026-07-16T01:22:59Z"},{"alias_kind":"pith_short_16","alias_value":"AZRI2CG4W2PVRHSR","created_at":"2026-07-16T01:22:59Z"},{"alias_kind":"pith_short_8","alias_value":"AZRI2CG4","created_at":"2026-07-16T01:22:59Z"}],"graph_snapshots":[{"event_id":"sha256:05622705b4420d273a80f2687c21b0a14b290f7f9a500edb99de08fb833e7124","target":"graph","created_at":"2026-07-16T01:22:59Z","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/2607.13661/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Contrastive Language-Image Pre-training (CLIP) has been shown to have limitations in its fine-grained dense feature representation, due to its pre-training focusing on matching the whole image to a text description. Considering the large data and computational burden in pre-training a vision-language model from scratch, a series of works aim to enhance the fine-grained ability of CLIP through a fine-tuning scheme. However, existing works suffer from a variety of limitations: additional region annotations are usually required, which limits the semantic diversity due to the predefined categories","authors_text":"Antoni B. Chan, Chenyang Zhao, Janet H. Hsiao, Wei Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-15T10:06:39Z","title":"Fine-grained CLIP fine-tuning with self-annotated region alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13661","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":"sha256:85ae28408a8bb62602ef82d510edd193713b618294870b0244c94ab565847872","target":"record","created_at":"2026-07-16T01:22:59Z","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":"c46954ad30958875061065724cd0b8f25ad44df553285772ae549cc2a691ef03","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-15T10:06:39Z","title_canon_sha256":"2cc62e0f46690d8d845c4d4236b5e6ac9cf62ae82e8702bb9a3aa4b4f11411b0"},"schema_version":"1.0","source":{"id":"2607.13661","kind":"arxiv","version":1}},"canonical_sha256":"06628d08dcb69f589e51d5dea899365007ff96792498ccdce9fa2cbf793015ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06628d08dcb69f589e51d5dea899365007ff96792498ccdce9fa2cbf793015ce","first_computed_at":"2026-07-16T01:22:59.470002Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-16T01:22:59.470002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SNozX5D6okPrIFKD7NcJBT+0QdbJ6JzwxON2VpQVCSjear2Gj8+ZLXItvW1l9VfBu5zMg9S1beVFd83i3ooECw==","signature_status":"signed_v1","signed_at":"2026-07-16T01:22:59.470890Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.13661","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85ae28408a8bb62602ef82d510edd193713b618294870b0244c94ab565847872","sha256:05622705b4420d273a80f2687c21b0a14b290f7f9a500edb99de08fb833e7124"],"state_sha256":"81241b84aaf6f6da91ddf495277dfd1fab40393134093f4de59c48d100753b05"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/K9meDyzr9yFkgjO/0AqmD5Bz2htxcw6M/De8diF/F+OrtELogqNI7jrO7vclk/fbXFgkPVWF5w4UhlsFZ7sDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T18:49:47.257696Z","bundle_sha256":"19609687bf901c2e7be8805bfed39a79a60fd1f6356d149ff2df9f0924a26258"}}