{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VXAW5Y57RGQJABL3KNJNK3XPFB","short_pith_number":"pith:VXAW5Y57","canonical_record":{"source":{"id":"2412.09442","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T16:57:20Z","cross_cats_sorted":[],"title_canon_sha256":"089c8a621c59470cd5352e87c9f20bbb57c7ef1d8c959c67ac86326ef086dc57","abstract_canon_sha256":"c67048ae0348693236601269c715da1d650788e16a97428d7c1505f1a652b70c"},"schema_version":"1.0"},"canonical_sha256":"adc16ee3bf89a090057b5352d56eef28586fd6ab6c08928a7221887ea49611e1","source":{"kind":"arxiv","id":"2412.09442","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09442","created_at":"2026-07-05T11:39:46Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09442v4","created_at":"2026-07-05T11:39:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09442","created_at":"2026-07-05T11:39:46Z"},{"alias_kind":"pith_short_12","alias_value":"VXAW5Y57RGQJ","created_at":"2026-07-05T11:39:46Z"},{"alias_kind":"pith_short_16","alias_value":"VXAW5Y57RGQJABL3","created_at":"2026-07-05T11:39:46Z"},{"alias_kind":"pith_short_8","alias_value":"VXAW5Y57","created_at":"2026-07-05T11:39:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VXAW5Y57RGQJABL3KNJNK3XPFB","target":"record","payload":{"canonical_record":{"source":{"id":"2412.09442","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T16:57:20Z","cross_cats_sorted":[],"title_canon_sha256":"089c8a621c59470cd5352e87c9f20bbb57c7ef1d8c959c67ac86326ef086dc57","abstract_canon_sha256":"c67048ae0348693236601269c715da1d650788e16a97428d7c1505f1a652b70c"},"schema_version":"1.0"},"canonical_sha256":"adc16ee3bf89a090057b5352d56eef28586fd6ab6c08928a7221887ea49611e1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:46.450161Z","signature_b64":"58S0mvTR06gO/kT1bC3qy108f4tp/ELfXm1El1sRtViQn3xYBuwzm0DAEt0DI42UUHayB8UoFWItsVKg3yzmCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"adc16ee3bf89a090057b5352d56eef28586fd6ab6c08928a7221887ea49611e1","last_reissued_at":"2026-07-05T11:39:46.449623Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:46.449623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.09442","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":"2026-07-05T11:39:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VtnPgFqOU1JXcGe8RN9FOz+QJ4+iUsjJVTlp8Nv/56MyjcZY66g/HUdtR3SK3FmGtQLG1nISbCSmtGZ2s6tJBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T05:29:00.158922Z"},"content_sha256":"e3e3d7d7c2aa3ea2f7e5889a1019277c27a5a2a6154d2afab9177d41ac62c316","schema_version":"1.0","event_id":"sha256:e3e3d7d7c2aa3ea2f7e5889a1019277c27a5a2a6154d2afab9177d41ac62c316"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VXAW5Y57RGQJABL3KNJNK3XPFB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Advancing Textual Prompt Learning with Anchored Attributes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Yang, Ming-Ming Cheng, Xiang Li, Yibing Song, Zheng Li","submitted_at":"2024-12-12T16:57:20Z","abstract_excerpt":"Textual-based prompt learning methods primarily employ multiple learnable soft prompts and hard class tokens in a cascading manner as text inputs, aiming to align image and text (category) spaces for downstream tasks. However, current training is restricted to aligning images with predefined known categories and cannot be associated with unknown categories. In this work, we propose utilizing universal attributes as a bridge to enhance the alignment between images and unknown categories. Specifically, we introduce an Attribute-anchored Textual Prompt learning method for vision-language models, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09442","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/2412.09442/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":"2026-07-05T11:39:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gXLb6MHbFOljyCmRhusqz5OFxo/Zl/CsmdxYDwoj0D1noY4EkUMezl3QMQQHiP2aKBIl3SidDfLjkZo/ehUUBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T05:29:00.159515Z"},"content_sha256":"4bed48e6c736958d234657362c1f98f3d54e5d1ba5dc12065f50ca5b0cd84998","schema_version":"1.0","event_id":"sha256:4bed48e6c736958d234657362c1f98f3d54e5d1ba5dc12065f50ca5b0cd84998"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VXAW5Y57RGQJABL3KNJNK3XPFB/bundle.json","state_url":"https://pith.science/pith/VXAW5Y57RGQJABL3KNJNK3XPFB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VXAW5Y57RGQJABL3KNJNK3XPFB/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":"2026-08-16T05:29:00Z","links":{"resolver":"https://pith.science/pith/VXAW5Y57RGQJABL3KNJNK3XPFB","bundle":"https://pith.science/pith/VXAW5Y57RGQJABL3KNJNK3XPFB/bundle.json","state":"https://pith.science/pith/VXAW5Y57RGQJABL3KNJNK3XPFB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VXAW5Y57RGQJABL3KNJNK3XPFB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VXAW5Y57RGQJABL3KNJNK3XPFB","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":"c67048ae0348693236601269c715da1d650788e16a97428d7c1505f1a652b70c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T16:57:20Z","title_canon_sha256":"089c8a621c59470cd5352e87c9f20bbb57c7ef1d8c959c67ac86326ef086dc57"},"schema_version":"1.0","source":{"id":"2412.09442","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09442","created_at":"2026-07-05T11:39:46Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09442v4","created_at":"2026-07-05T11:39:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09442","created_at":"2026-07-05T11:39:46Z"},{"alias_kind":"pith_short_12","alias_value":"VXAW5Y57RGQJ","created_at":"2026-07-05T11:39:46Z"},{"alias_kind":"pith_short_16","alias_value":"VXAW5Y57RGQJABL3","created_at":"2026-07-05T11:39:46Z"},{"alias_kind":"pith_short_8","alias_value":"VXAW5Y57","created_at":"2026-07-05T11:39:46Z"}],"graph_snapshots":[{"event_id":"sha256:4bed48e6c736958d234657362c1f98f3d54e5d1ba5dc12065f50ca5b0cd84998","target":"graph","created_at":"2026-07-05T11:39:46Z","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/2412.09442/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Textual-based prompt learning methods primarily employ multiple learnable soft prompts and hard class tokens in a cascading manner as text inputs, aiming to align image and text (category) spaces for downstream tasks. However, current training is restricted to aligning images with predefined known categories and cannot be associated with unknown categories. In this work, we propose utilizing universal attributes as a bridge to enhance the alignment between images and unknown categories. Specifically, we introduce an Attribute-anchored Textual Prompt learning method for vision-language models, ","authors_text":"Jian Yang, Ming-Ming Cheng, Xiang Li, Yibing Song, Zheng Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T16:57:20Z","title":"Advancing Textual Prompt Learning with Anchored Attributes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09442","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:e3e3d7d7c2aa3ea2f7e5889a1019277c27a5a2a6154d2afab9177d41ac62c316","target":"record","created_at":"2026-07-05T11:39:46Z","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":"c67048ae0348693236601269c715da1d650788e16a97428d7c1505f1a652b70c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-12T16:57:20Z","title_canon_sha256":"089c8a621c59470cd5352e87c9f20bbb57c7ef1d8c959c67ac86326ef086dc57"},"schema_version":"1.0","source":{"id":"2412.09442","kind":"arxiv","version":4}},"canonical_sha256":"adc16ee3bf89a090057b5352d56eef28586fd6ab6c08928a7221887ea49611e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"adc16ee3bf89a090057b5352d56eef28586fd6ab6c08928a7221887ea49611e1","first_computed_at":"2026-07-05T11:39:46.449623Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:46.449623Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"58S0mvTR06gO/kT1bC3qy108f4tp/ELfXm1El1sRtViQn3xYBuwzm0DAEt0DI42UUHayB8UoFWItsVKg3yzmCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:46.450161Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.09442","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3e3d7d7c2aa3ea2f7e5889a1019277c27a5a2a6154d2afab9177d41ac62c316","sha256:4bed48e6c736958d234657362c1f98f3d54e5d1ba5dc12065f50ca5b0cd84998"],"state_sha256":"326bd37ed2bb524e9719cc7c9c8896a77b4de7717a1bf7aa47e181f999b3cb32"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7Z5jCJ3qlqrSzvP9IYtEEsYpgDYAhLuRC8QIUNQf2wtuWgMYEx8bUxYHQC1VO9EZinxJ/6krfiW1CJN88KeDAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T05:29:00.163048Z","bundle_sha256":"1a8b5bf1b9ffaaf761a6fe1430a6d2d278f7ca4dbba28efcd539d478be53c679"}}