{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:7X4ZMEQETPL5VWORH5FIZITS76","short_pith_number":"pith:7X4ZMEQE","canonical_record":{"source":{"id":"2607.05727","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-07T01:21:33Z","cross_cats_sorted":[],"title_canon_sha256":"255a055b9012911c028779f28c39cc1cee37cdfb27475a75b7951b1804f32107","abstract_canon_sha256":"55410df05aaae309c858a8c701c8b7af45bc2c65040865362cc8f5ef88e411ab"},"schema_version":"1.0"},"canonical_sha256":"fdf99612049bd7dad9d13f4a8ca272ff85c856a87eef759c06012cb99e58d8c5","source":{"kind":"arxiv","id":"2607.05727","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.05727","created_at":"2026-07-08T01:18:42Z"},{"alias_kind":"arxiv_version","alias_value":"2607.05727v1","created_at":"2026-07-08T01:18:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05727","created_at":"2026-07-08T01:18:42Z"},{"alias_kind":"pith_short_12","alias_value":"7X4ZMEQETPL5","created_at":"2026-07-08T01:18:42Z"},{"alias_kind":"pith_short_16","alias_value":"7X4ZMEQETPL5VWOR","created_at":"2026-07-08T01:18:42Z"},{"alias_kind":"pith_short_8","alias_value":"7X4ZMEQE","created_at":"2026-07-08T01:18:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:7X4ZMEQETPL5VWORH5FIZITS76","target":"record","payload":{"canonical_record":{"source":{"id":"2607.05727","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-07T01:21:33Z","cross_cats_sorted":[],"title_canon_sha256":"255a055b9012911c028779f28c39cc1cee37cdfb27475a75b7951b1804f32107","abstract_canon_sha256":"55410df05aaae309c858a8c701c8b7af45bc2c65040865362cc8f5ef88e411ab"},"schema_version":"1.0"},"canonical_sha256":"fdf99612049bd7dad9d13f4a8ca272ff85c856a87eef759c06012cb99e58d8c5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:18:42.662857Z","signature_b64":"ucMrCWOY1oKCDsojkrTYthhEKbov4Il3SzpySPcsr52Rg2gDTNyoijFI309LSoUyI5uknFf0VC7iBFCMfVpvAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdf99612049bd7dad9d13f4a8ca272ff85c856a87eef759c06012cb99e58d8c5","last_reissued_at":"2026-07-08T01:18:42.662390Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:18:42.662390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.05727","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":"2026-07-08T01:18:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T+nFU0mRnVMZjcGdzuPIBKzmckvjyZNG+HlScYpy1SPJgF8ZA47cN+xDb9GwkjN1cQbJCnls+dDVbmtuVPCLCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T04:32:00.007646Z"},"content_sha256":"ff283ffb51d0525f90d3488f736be2e02a1579d682164e2039a7cf3887c99122","schema_version":"1.0","event_id":"sha256:ff283ffb51d0525f90d3488f736be2e02a1579d682164e2039a7cf3887c99122"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:7X4ZMEQETPL5VWORH5FIZITS76","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SAMPLe: SAM-based Optimizer for Prompt Learning in VLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fatemeh Afghah, Fatemeh Lotfi, Hossein Kashiani, Hossein Rajoli, Niloufar Alipour Talemi, Xiaolong Ma","submitted_at":"2026-07-07T01:21:33Z","abstract_excerpt":"Pre-trained Vision-Language Models (VLMs) like CLIP have proven highly effective as foundation models for various downstream applications. However, prompt learning in VLMs encounters a performance-generalization dilemma: while prompts can be tuned to achieve high accuracy on seen distributions, this tuning process often undermines their generalizability to unseen data. The limited set of learnable prompts, which contextualize and condition the input to steer it toward the task within the pretrained VLM, tends to overfit the training data, leading to a trade-off between task-specific performanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05727","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/2607.05727/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":"2026-07-08T01:18:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uUUFEBa0ZO7iO1rEhVfYW0PFid4Yv55BPJSCD8eiE9f9/78+O8XY5VgDaw3X6Y1V6mtUWdqlhdGIEw3zg+zxDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T04:32:00.008508Z"},"content_sha256":"567554755e8aa802996451a4d7652a5dcc3d04b148d3d95d50d455036e5c8e61","schema_version":"1.0","event_id":"sha256:567554755e8aa802996451a4d7652a5dcc3d04b148d3d95d50d455036e5c8e61"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7X4ZMEQETPL5VWORH5FIZITS76/bundle.json","state_url":"https://pith.science/pith/7X4ZMEQETPL5VWORH5FIZITS76/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7X4ZMEQETPL5VWORH5FIZITS76/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":"2026-08-01T04:32:00Z","links":{"resolver":"https://pith.science/pith/7X4ZMEQETPL5VWORH5FIZITS76","bundle":"https://pith.science/pith/7X4ZMEQETPL5VWORH5FIZITS76/bundle.json","state":"https://pith.science/pith/7X4ZMEQETPL5VWORH5FIZITS76/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7X4ZMEQETPL5VWORH5FIZITS76/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7X4ZMEQETPL5VWORH5FIZITS76","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":"55410df05aaae309c858a8c701c8b7af45bc2c65040865362cc8f5ef88e411ab","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-07T01:21:33Z","title_canon_sha256":"255a055b9012911c028779f28c39cc1cee37cdfb27475a75b7951b1804f32107"},"schema_version":"1.0","source":{"id":"2607.05727","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.05727","created_at":"2026-07-08T01:18:42Z"},{"alias_kind":"arxiv_version","alias_value":"2607.05727v1","created_at":"2026-07-08T01:18:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05727","created_at":"2026-07-08T01:18:42Z"},{"alias_kind":"pith_short_12","alias_value":"7X4ZMEQETPL5","created_at":"2026-07-08T01:18:42Z"},{"alias_kind":"pith_short_16","alias_value":"7X4ZMEQETPL5VWOR","created_at":"2026-07-08T01:18:42Z"},{"alias_kind":"pith_short_8","alias_value":"7X4ZMEQE","created_at":"2026-07-08T01:18:42Z"}],"graph_snapshots":[{"event_id":"sha256:567554755e8aa802996451a4d7652a5dcc3d04b148d3d95d50d455036e5c8e61","target":"graph","created_at":"2026-07-08T01:18:42Z","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/2607.05727/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained Vision-Language Models (VLMs) like CLIP have proven highly effective as foundation models for various downstream applications. However, prompt learning in VLMs encounters a performance-generalization dilemma: while prompts can be tuned to achieve high accuracy on seen distributions, this tuning process often undermines their generalizability to unseen data. The limited set of learnable prompts, which contextualize and condition the input to steer it toward the task within the pretrained VLM, tends to overfit the training data, leading to a trade-off between task-specific performanc","authors_text":"Fatemeh Afghah, Fatemeh Lotfi, Hossein Kashiani, Hossein Rajoli, Niloufar Alipour Talemi, Xiaolong Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-07T01:21:33Z","title":"SAMPLe: SAM-based Optimizer for Prompt Learning in VLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05727","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:ff283ffb51d0525f90d3488f736be2e02a1579d682164e2039a7cf3887c99122","target":"record","created_at":"2026-07-08T01:18:42Z","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":"55410df05aaae309c858a8c701c8b7af45bc2c65040865362cc8f5ef88e411ab","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-07T01:21:33Z","title_canon_sha256":"255a055b9012911c028779f28c39cc1cee37cdfb27475a75b7951b1804f32107"},"schema_version":"1.0","source":{"id":"2607.05727","kind":"arxiv","version":1}},"canonical_sha256":"fdf99612049bd7dad9d13f4a8ca272ff85c856a87eef759c06012cb99e58d8c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fdf99612049bd7dad9d13f4a8ca272ff85c856a87eef759c06012cb99e58d8c5","first_computed_at":"2026-07-08T01:18:42.662390Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-08T01:18:42.662390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ucMrCWOY1oKCDsojkrTYthhEKbov4Il3SzpySPcsr52Rg2gDTNyoijFI309LSoUyI5uknFf0VC7iBFCMfVpvAQ==","signature_status":"signed_v1","signed_at":"2026-07-08T01:18:42.662857Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.05727","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff283ffb51d0525f90d3488f736be2e02a1579d682164e2039a7cf3887c99122","sha256:567554755e8aa802996451a4d7652a5dcc3d04b148d3d95d50d455036e5c8e61"],"state_sha256":"665934466b73eac65f960ab54ab84253e729354294c002669104fc1b00c0f100"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6hLn35MhZk33Ktes2sSV0xNmgPftAUiMfQTPeVdzTvG9fiARnbBtzFL+vz9ORcEwc/YOWmc1vSp2PQGHRg7uAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T04:32:00.015073Z","bundle_sha256":"aab7d912ff2bf2c3d373062a120ca7735edd15c51bc4f11b240f82675e426548"}}