{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3RZMMID6WLAAXMLIH3A7TBPEM6","short_pith_number":"pith:3RZMMID6","canonical_record":{"source":{"id":"2412.18303","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T09:15:00Z","cross_cats_sorted":[],"title_canon_sha256":"68b8cd2cdc3229a68ddf40a5fa2e1f09313fe0eb1fe4884125a50165f71cb51e","abstract_canon_sha256":"656c3d016817e915a4a259efd729b7890a78f5cf54034d05e963e917f2c558ab"},"schema_version":"1.0"},"canonical_sha256":"dc72c6207eb2c00bb1683ec1f985e467971a3bf8ea461b997a921399068cf8cf","source":{"kind":"arxiv","id":"2412.18303","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18303","created_at":"2026-07-05T10:21:52Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18303v2","created_at":"2026-07-05T10:21:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18303","created_at":"2026-07-05T10:21:52Z"},{"alias_kind":"pith_short_12","alias_value":"3RZMMID6WLAA","created_at":"2026-07-05T10:21:52Z"},{"alias_kind":"pith_short_16","alias_value":"3RZMMID6WLAAXMLI","created_at":"2026-07-05T10:21:52Z"},{"alias_kind":"pith_short_8","alias_value":"3RZMMID6","created_at":"2026-07-05T10:21:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3RZMMID6WLAAXMLIH3A7TBPEM6","target":"record","payload":{"canonical_record":{"source":{"id":"2412.18303","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T09:15:00Z","cross_cats_sorted":[],"title_canon_sha256":"68b8cd2cdc3229a68ddf40a5fa2e1f09313fe0eb1fe4884125a50165f71cb51e","abstract_canon_sha256":"656c3d016817e915a4a259efd729b7890a78f5cf54034d05e963e917f2c558ab"},"schema_version":"1.0"},"canonical_sha256":"dc72c6207eb2c00bb1683ec1f985e467971a3bf8ea461b997a921399068cf8cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:52.191766Z","signature_b64":"P4UqFRiIvOT1/tobWROIQqjlq8nCKgu7KJX4R8Nr964dEsYcT3ShMqpnzdcQsI91oeimsYSakhH8LHIYtnbWAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc72c6207eb2c00bb1683ec1f985e467971a3bf8ea461b997a921399068cf8cf","last_reissued_at":"2026-07-05T10:21:52.191262Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:52.191262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.18303","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:21:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k0QLkd+xmZorVZKTm+qZx+4IvDqpzkJXMSTda2uZ5e580nlxzt1qWSTpMGmF6rexroOJvBOvYfp7jrcbjtRIDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:39:27.695339Z"},"content_sha256":"c42b72ec11f18dd0ea92f89f47695159cfe58f5db5669c56ef1c0843446c433d","schema_version":"1.0","event_id":"sha256:c42b72ec11f18dd0ea92f89f47695159cfe58f5db5669c56ef1c0843446c433d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3RZMMID6WLAAXMLIH3A7TBPEM6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adam Goodge, Kui Jia, Xun Xu, Yongyi Su, Yushu Li","submitted_at":"2024-12-24T09:15:00Z","abstract_excerpt":"Vision-language models (VLMs) have revolutionized machine learning by leveraging large pre-trained models to tackle various downstream tasks. Although label, training, and data efficiency have improved, many state-of-the-art VLMs still require task-specific hyperparameter tuning and fail to fully exploit test samples. To overcome these challenges, we propose a graph-based approach for label-efficient adaptation and inference. Our method dynamically constructs a graph over text prompts, few-shot examples, and test samples, using label propagation for inference without task-specific tuning. Unli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18303","kind":"arxiv","version":2},"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/2412.18303/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":"2026-07-05T10:21:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hXUxR7Qsv75Z+Bwu3bnKf4eBmy7cz7bdcueBpGJkKCDQE+pGhRrZYnxAcBcSGOFEyawtdAgo+CcLOSukp6ISDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:39:27.695850Z"},"content_sha256":"3243e8fc3b5df22ffa82ad05c1a3b03b319f09c0e1d47da86f443962f7a5eb28","schema_version":"1.0","event_id":"sha256:3243e8fc3b5df22ffa82ad05c1a3b03b319f09c0e1d47da86f443962f7a5eb28"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3RZMMID6WLAAXMLIH3A7TBPEM6/bundle.json","state_url":"https://pith.science/pith/3RZMMID6WLAAXMLIH3A7TBPEM6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3RZMMID6WLAAXMLIH3A7TBPEM6/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":"2026-08-09T00:39:27Z","links":{"resolver":"https://pith.science/pith/3RZMMID6WLAAXMLIH3A7TBPEM6","bundle":"https://pith.science/pith/3RZMMID6WLAAXMLIH3A7TBPEM6/bundle.json","state":"https://pith.science/pith/3RZMMID6WLAAXMLIH3A7TBPEM6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3RZMMID6WLAAXMLIH3A7TBPEM6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3RZMMID6WLAAXMLIH3A7TBPEM6","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":"656c3d016817e915a4a259efd729b7890a78f5cf54034d05e963e917f2c558ab","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T09:15:00Z","title_canon_sha256":"68b8cd2cdc3229a68ddf40a5fa2e1f09313fe0eb1fe4884125a50165f71cb51e"},"schema_version":"1.0","source":{"id":"2412.18303","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18303","created_at":"2026-07-05T10:21:52Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18303v2","created_at":"2026-07-05T10:21:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18303","created_at":"2026-07-05T10:21:52Z"},{"alias_kind":"pith_short_12","alias_value":"3RZMMID6WLAA","created_at":"2026-07-05T10:21:52Z"},{"alias_kind":"pith_short_16","alias_value":"3RZMMID6WLAAXMLI","created_at":"2026-07-05T10:21:52Z"},{"alias_kind":"pith_short_8","alias_value":"3RZMMID6","created_at":"2026-07-05T10:21:52Z"}],"graph_snapshots":[{"event_id":"sha256:3243e8fc3b5df22ffa82ad05c1a3b03b319f09c0e1d47da86f443962f7a5eb28","target":"graph","created_at":"2026-07-05T10:21:52Z","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/2412.18303/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) have revolutionized machine learning by leveraging large pre-trained models to tackle various downstream tasks. Although label, training, and data efficiency have improved, many state-of-the-art VLMs still require task-specific hyperparameter tuning and fail to fully exploit test samples. To overcome these challenges, we propose a graph-based approach for label-efficient adaptation and inference. Our method dynamically constructs a graph over text prompts, few-shot examples, and test samples, using label propagation for inference without task-specific tuning. Unli","authors_text":"Adam Goodge, Kui Jia, Xun Xu, Yongyi Su, Yushu Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T09:15:00Z","title":"Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18303","kind":"arxiv","version":2},"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:c42b72ec11f18dd0ea92f89f47695159cfe58f5db5669c56ef1c0843446c433d","target":"record","created_at":"2026-07-05T10:21:52Z","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":"656c3d016817e915a4a259efd729b7890a78f5cf54034d05e963e917f2c558ab","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T09:15:00Z","title_canon_sha256":"68b8cd2cdc3229a68ddf40a5fa2e1f09313fe0eb1fe4884125a50165f71cb51e"},"schema_version":"1.0","source":{"id":"2412.18303","kind":"arxiv","version":2}},"canonical_sha256":"dc72c6207eb2c00bb1683ec1f985e467971a3bf8ea461b997a921399068cf8cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc72c6207eb2c00bb1683ec1f985e467971a3bf8ea461b997a921399068cf8cf","first_computed_at":"2026-07-05T10:21:52.191262Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:52.191262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P4UqFRiIvOT1/tobWROIQqjlq8nCKgu7KJX4R8Nr964dEsYcT3ShMqpnzdcQsI91oeimsYSakhH8LHIYtnbWAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:52.191766Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.18303","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c42b72ec11f18dd0ea92f89f47695159cfe58f5db5669c56ef1c0843446c433d","sha256:3243e8fc3b5df22ffa82ad05c1a3b03b319f09c0e1d47da86f443962f7a5eb28"],"state_sha256":"cce1e0af7306ccef0d10faae13ebad577a246bf7d8460ccde5b7b084d993ab02"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fgn1CKHtPfrT7iade2z5JquSYSGFAl/F6l4VVoo394Z8wFwiKXqnjZZh6aDJIwuZI2pYlRE02jAtFTD6eI/gBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:39:27.701109Z","bundle_sha256":"52957ba2f595bb27a91b7dceaf4f8a6f104a7902969a17b5b93fbd8fd35ae57a"}}