{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:PYLWXLGRJC44LGNGJ4SIF3BCOP","short_pith_number":"pith:PYLWXLGR","canonical_record":{"source":{"id":"2608.02124","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-03T12:15:33Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d41769abedb5e8e8879bc98acaf5f226a72391524b86f3f4240c60ebf5dd2841","abstract_canon_sha256":"5f68aeb288307df8fa36e4c2586528c549a8d65d00cd514d67e896adad2db28c"},"schema_version":"1.0"},"canonical_sha256":"7e176bacd148b9c599a64f2482ec2273d80331e453d15724bcb5f5c6502397e8","source":{"kind":"arxiv","id":"2608.02124","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02124","created_at":"2026-08-04T02:11:03Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02124v1","created_at":"2026-08-04T02:11:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02124","created_at":"2026-08-04T02:11:03Z"},{"alias_kind":"pith_short_12","alias_value":"PYLWXLGRJC44","created_at":"2026-08-04T02:11:03Z"},{"alias_kind":"pith_short_16","alias_value":"PYLWXLGRJC44LGNG","created_at":"2026-08-04T02:11:03Z"},{"alias_kind":"pith_short_8","alias_value":"PYLWXLGR","created_at":"2026-08-04T02:11:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:PYLWXLGRJC44LGNGJ4SIF3BCOP","target":"record","payload":{"canonical_record":{"source":{"id":"2608.02124","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-03T12:15:33Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d41769abedb5e8e8879bc98acaf5f226a72391524b86f3f4240c60ebf5dd2841","abstract_canon_sha256":"5f68aeb288307df8fa36e4c2586528c549a8d65d00cd514d67e896adad2db28c"},"schema_version":"1.0"},"canonical_sha256":"7e176bacd148b9c599a64f2482ec2273d80331e453d15724bcb5f5c6502397e8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:11:03.659537Z","signature_b64":"jn+NI4AJNTn5xUCs4Im6vbxCv5Cj9ksueE9insC77xxiixDCkrLxxl8AvXJ/u5nY71nt+VtuY4xY5SyS8Lt1AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e176bacd148b9c599a64f2482ec2273d80331e453d15724bcb5f5c6502397e8","last_reissued_at":"2026-08-04T02:11:03.657954Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:11:03.657954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.02124","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":"2026-08-04T02:11:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7u3NVsT0RVgdW6HHNSTV+4B71DdtjWQsMleAH6kwJqhtjPu5uttSo+swBGiGHcJ2eriVH+LT6zSeemdyp1iFCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:22:15.819049Z"},"content_sha256":"b420311070faeb2318895527787167d89d60b1df54e6dccc06a5bc75210d0048","schema_version":"1.0","event_id":"sha256:b420311070faeb2318895527787167d89d60b1df54e6dccc06a5bc75210d0048"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:PYLWXLGRJC44LGNGJ4SIF3BCOP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HAFI-VLM: A Frequency Perspective for Diagnosing and Enhancing Visual Perception in Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Boran Zhao, Chuanchang Su, Jiayi Lu, Jin Cui, Pengju Ren, Xinyue Long","submitted_at":"2026-08-03T12:15:33Z","abstract_excerpt":"Vision-language models (VLMs) remain unreliable when predictions require fine-grained visual evidence. We identify a previously overlooked cause: spectral response rigidity. Despite substantial frequency variation across images and tasks, pretrained vision encoders exhibit persistent, encoder-specific layerwise spectral profiles that change only marginally under downstream fine-tuning. Since pretrained vision encoders only receive images, they cannot adapt spectral extraction to the evidence required by the current query. We therefore propose HAFI-VLM, which introduces a task-conditioned frequ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02124","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/2608.02124/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":"2026-08-04T02:11:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o34zRF7p6qkV7QrJlYNgVclv8fsLDjc+3LW7vy+OljtTUgXI+EtLRHlYBjI1Dl126TewtGFhmQ4SM0m6u2FbDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T14:22:15.820015Z"},"content_sha256":"7a7e8bf32af9e304eb6f5dff3aaedf51ef7d4c7f1cf382ec104faddf6d878a90","schema_version":"1.0","event_id":"sha256:7a7e8bf32af9e304eb6f5dff3aaedf51ef7d4c7f1cf382ec104faddf6d878a90"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PYLWXLGRJC44LGNGJ4SIF3BCOP/bundle.json","state_url":"https://pith.science/pith/PYLWXLGRJC44LGNGJ4SIF3BCOP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PYLWXLGRJC44LGNGJ4SIF3BCOP/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":"2026-08-05T14:22:15Z","links":{"resolver":"https://pith.science/pith/PYLWXLGRJC44LGNGJ4SIF3BCOP","bundle":"https://pith.science/pith/PYLWXLGRJC44LGNGJ4SIF3BCOP/bundle.json","state":"https://pith.science/pith/PYLWXLGRJC44LGNGJ4SIF3BCOP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PYLWXLGRJC44LGNGJ4SIF3BCOP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PYLWXLGRJC44LGNGJ4SIF3BCOP","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":"5f68aeb288307df8fa36e4c2586528c549a8d65d00cd514d67e896adad2db28c","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-03T12:15:33Z","title_canon_sha256":"d41769abedb5e8e8879bc98acaf5f226a72391524b86f3f4240c60ebf5dd2841"},"schema_version":"1.0","source":{"id":"2608.02124","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02124","created_at":"2026-08-04T02:11:03Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02124v1","created_at":"2026-08-04T02:11:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02124","created_at":"2026-08-04T02:11:03Z"},{"alias_kind":"pith_short_12","alias_value":"PYLWXLGRJC44","created_at":"2026-08-04T02:11:03Z"},{"alias_kind":"pith_short_16","alias_value":"PYLWXLGRJC44LGNG","created_at":"2026-08-04T02:11:03Z"},{"alias_kind":"pith_short_8","alias_value":"PYLWXLGR","created_at":"2026-08-04T02:11:03Z"}],"graph_snapshots":[{"event_id":"sha256:7a7e8bf32af9e304eb6f5dff3aaedf51ef7d4c7f1cf382ec104faddf6d878a90","target":"graph","created_at":"2026-08-04T02:11:03Z","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/2608.02124/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) remain unreliable when predictions require fine-grained visual evidence. We identify a previously overlooked cause: spectral response rigidity. Despite substantial frequency variation across images and tasks, pretrained vision encoders exhibit persistent, encoder-specific layerwise spectral profiles that change only marginally under downstream fine-tuning. Since pretrained vision encoders only receive images, they cannot adapt spectral extraction to the evidence required by the current query. We therefore propose HAFI-VLM, which introduces a task-conditioned frequ","authors_text":"Boran Zhao, Chuanchang Su, Jiayi Lu, Jin Cui, Pengju Ren, Xinyue Long","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-03T12:15:33Z","title":"HAFI-VLM: A Frequency Perspective for Diagnosing and Enhancing Visual Perception in Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02124","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:b420311070faeb2318895527787167d89d60b1df54e6dccc06a5bc75210d0048","target":"record","created_at":"2026-08-04T02:11:03Z","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":"5f68aeb288307df8fa36e4c2586528c549a8d65d00cd514d67e896adad2db28c","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-03T12:15:33Z","title_canon_sha256":"d41769abedb5e8e8879bc98acaf5f226a72391524b86f3f4240c60ebf5dd2841"},"schema_version":"1.0","source":{"id":"2608.02124","kind":"arxiv","version":1}},"canonical_sha256":"7e176bacd148b9c599a64f2482ec2273d80331e453d15724bcb5f5c6502397e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e176bacd148b9c599a64f2482ec2273d80331e453d15724bcb5f5c6502397e8","first_computed_at":"2026-08-04T02:11:03.657954Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:11:03.657954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jn+NI4AJNTn5xUCs4Im6vbxCv5Cj9ksueE9insC77xxiixDCkrLxxl8AvXJ/u5nY71nt+VtuY4xY5SyS8Lt1AQ==","signature_status":"signed_v1","signed_at":"2026-08-04T02:11:03.659537Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.02124","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b420311070faeb2318895527787167d89d60b1df54e6dccc06a5bc75210d0048","sha256:7a7e8bf32af9e304eb6f5dff3aaedf51ef7d4c7f1cf382ec104faddf6d878a90"],"state_sha256":"284fa0a2fb1be53b7d42eb93c098f02cd613344c481147982e559a5c371c9755"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G0kIlMO92l3EG9sx+zYC3gV3hUwXE55ahe7KOCjWo7QsVqK0UxKoPGVaU9TuE4C1uWl2tVOLI9PrPlHEYa2sAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T14:22:15.848255Z","bundle_sha256":"4204726623c292ccec024925234cfb1657067c9e5536f5ba2702ce69e3b2dae9"}}