{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SAOT6P6ZSF3A5GJ7A5E3UQWZ2B","short_pith_number":"pith:SAOT6P6Z","canonical_record":{"source":{"id":"2608.07435","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-07T17:21:04Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"66dd2e97f35d39c1b88311544b7f31d9bb8b94d4bddb70495d31b421914a5065","abstract_canon_sha256":"4d825d641e25f0ddaaefd36be87a3ab6b7836a13ec2bb3ef1b4da5693f58fe04"},"schema_version":"1.0"},"canonical_sha256":"901d3f3fd991760e993f0749ba42d9d0640408f60d2864cf090f0763ec0fa536","source":{"kind":"arxiv","id":"2608.07435","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.07435","created_at":"2026-08-10T01:15:23Z"},{"alias_kind":"arxiv_version","alias_value":"2608.07435v1","created_at":"2026-08-10T01:15:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07435","created_at":"2026-08-10T01:15:23Z"},{"alias_kind":"pith_short_12","alias_value":"SAOT6P6ZSF3A","created_at":"2026-08-10T01:15:23Z"},{"alias_kind":"pith_short_16","alias_value":"SAOT6P6ZSF3A5GJ7","created_at":"2026-08-10T01:15:23Z"},{"alias_kind":"pith_short_8","alias_value":"SAOT6P6Z","created_at":"2026-08-10T01:15:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SAOT6P6ZSF3A5GJ7A5E3UQWZ2B","target":"record","payload":{"canonical_record":{"source":{"id":"2608.07435","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-07T17:21:04Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"66dd2e97f35d39c1b88311544b7f31d9bb8b94d4bddb70495d31b421914a5065","abstract_canon_sha256":"4d825d641e25f0ddaaefd36be87a3ab6b7836a13ec2bb3ef1b4da5693f58fe04"},"schema_version":"1.0"},"canonical_sha256":"901d3f3fd991760e993f0749ba42d9d0640408f60d2864cf090f0763ec0fa536","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:15:23.314441Z","signature_b64":"xamfYwKCp39hCMAXotXN3yt7Cw9MhqeqliJdGfQB8GFNXpXLGkhQu2Mk2/srPgb+KfI/4MxQGMN5F/aeAvuSCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"901d3f3fd991760e993f0749ba42d9d0640408f60d2864cf090f0763ec0fa536","last_reissued_at":"2026-08-10T01:15:23.311904Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:15:23.311904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.07435","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":"2026-08-10T01:15:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9tSGiruurrmqmHNXX23twXFAFChQLZewNxHlwBfu8gkft+cUf9M7cEYKsFjxYkIWqEvBcQ6GvkmqAXmtkfTVAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T06:56:38.991511Z"},"content_sha256":"7a18ed22f5076bde8ccefe134c1465c1ea9eea6157ca68934fa14c55c14ad415","schema_version":"1.0","event_id":"sha256:7a18ed22f5076bde8ccefe134c1465c1ea9eea6157ca68934fa14c55c14ad415"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SAOT6P6ZSF3A5GJ7A5E3UQWZ2B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SABRE: Scalable and Automated Benchmarking of VLMs under Stress","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jiawei Zhou, Luzhe Sun, Matthew R. Walter, Zixuan Lan","submitted_at":"2026-08-07T17:21:04Z","abstract_excerpt":"Vision-language models (VLMs) are improving rapidly, but benchmark development lags behind, making weaknesses hard to identify. Building stress tests is costly: samples must satisfy controlled conditions, remain answerable, and challenge current models. We present SABRE, a scalable, automated pipeline that converts a Test Primer (a Markdown Task Design with Data Schema) into structured specifications, generated or edited images, and question-answer pairs. Automated filtering removes candidates solved by a Filtering VLM, while human review verifies candidate validity and supports annotation cor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07435","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/2608.07435/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":"2026-08-10T01:15:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sH4kHv777Kgv32xAsRiiQ5dpzzKhxtRhMEP0Ei4RWOR9EqHzXbwFLOJH/Rt8zDAa1BgEvo+4uEmFdiKj4w/XBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T06:56:38.992027Z"},"content_sha256":"7482025ec612806a4b40be8a2ff72565ea7f5fa12894ffadbd38bda623e70708","schema_version":"1.0","event_id":"sha256:7482025ec612806a4b40be8a2ff72565ea7f5fa12894ffadbd38bda623e70708"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SAOT6P6ZSF3A5GJ7A5E3UQWZ2B/bundle.json","state_url":"https://pith.science/pith/SAOT6P6ZSF3A5GJ7A5E3UQWZ2B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SAOT6P6ZSF3A5GJ7A5E3UQWZ2B/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":"2026-08-11T06:56:38Z","links":{"resolver":"https://pith.science/pith/SAOT6P6ZSF3A5GJ7A5E3UQWZ2B","bundle":"https://pith.science/pith/SAOT6P6ZSF3A5GJ7A5E3UQWZ2B/bundle.json","state":"https://pith.science/pith/SAOT6P6ZSF3A5GJ7A5E3UQWZ2B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SAOT6P6ZSF3A5GJ7A5E3UQWZ2B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SAOT6P6ZSF3A5GJ7A5E3UQWZ2B","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":"4d825d641e25f0ddaaefd36be87a3ab6b7836a13ec2bb3ef1b4da5693f58fe04","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-07T17:21:04Z","title_canon_sha256":"66dd2e97f35d39c1b88311544b7f31d9bb8b94d4bddb70495d31b421914a5065"},"schema_version":"1.0","source":{"id":"2608.07435","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.07435","created_at":"2026-08-10T01:15:23Z"},{"alias_kind":"arxiv_version","alias_value":"2608.07435v1","created_at":"2026-08-10T01:15:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07435","created_at":"2026-08-10T01:15:23Z"},{"alias_kind":"pith_short_12","alias_value":"SAOT6P6ZSF3A","created_at":"2026-08-10T01:15:23Z"},{"alias_kind":"pith_short_16","alias_value":"SAOT6P6ZSF3A5GJ7","created_at":"2026-08-10T01:15:23Z"},{"alias_kind":"pith_short_8","alias_value":"SAOT6P6Z","created_at":"2026-08-10T01:15:23Z"}],"graph_snapshots":[{"event_id":"sha256:7482025ec612806a4b40be8a2ff72565ea7f5fa12894ffadbd38bda623e70708","target":"graph","created_at":"2026-08-10T01:15:23Z","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/2608.07435/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) are improving rapidly, but benchmark development lags behind, making weaknesses hard to identify. Building stress tests is costly: samples must satisfy controlled conditions, remain answerable, and challenge current models. We present SABRE, a scalable, automated pipeline that converts a Test Primer (a Markdown Task Design with Data Schema) into structured specifications, generated or edited images, and question-answer pairs. Automated filtering removes candidates solved by a Filtering VLM, while human review verifies candidate validity and supports annotation cor","authors_text":"Jiawei Zhou, Luzhe Sun, Matthew R. Walter, Zixuan Lan","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-07T17:21:04Z","title":"SABRE: Scalable and Automated Benchmarking of VLMs under Stress"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07435","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":"sha256:7a18ed22f5076bde8ccefe134c1465c1ea9eea6157ca68934fa14c55c14ad415","target":"record","created_at":"2026-08-10T01:15:23Z","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":"4d825d641e25f0ddaaefd36be87a3ab6b7836a13ec2bb3ef1b4da5693f58fe04","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-07T17:21:04Z","title_canon_sha256":"66dd2e97f35d39c1b88311544b7f31d9bb8b94d4bddb70495d31b421914a5065"},"schema_version":"1.0","source":{"id":"2608.07435","kind":"arxiv","version":1}},"canonical_sha256":"901d3f3fd991760e993f0749ba42d9d0640408f60d2864cf090f0763ec0fa536","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"901d3f3fd991760e993f0749ba42d9d0640408f60d2864cf090f0763ec0fa536","first_computed_at":"2026-08-10T01:15:23.311904Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-10T01:15:23.311904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xamfYwKCp39hCMAXotXN3yt7Cw9MhqeqliJdGfQB8GFNXpXLGkhQu2Mk2/srPgb+KfI/4MxQGMN5F/aeAvuSCQ==","signature_status":"signed_v1","signed_at":"2026-08-10T01:15:23.314441Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.07435","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a18ed22f5076bde8ccefe134c1465c1ea9eea6157ca68934fa14c55c14ad415","sha256:7482025ec612806a4b40be8a2ff72565ea7f5fa12894ffadbd38bda623e70708"],"state_sha256":"7b66389df1f1c12c255ebbc11a4bc3dedb7aaa2d5967c35c1e041d4d75342089"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZZQLKR7xYNEuYrgnbMX3U1b2Kw+8fFtr+6yYWYLMpbzWs9Xj5eu5HMobKpQrJ9WIDvXJAgoRjK03r23dlcnFAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T06:56:38.996401Z","bundle_sha256":"733550d712fe6468060e92f71cac381ff75107251fc12e227f415b2f6a8ac719"}}