{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:7VG4E5TKRPWELSGDA5YGFQOSUS","short_pith_number":"pith:7VG4E5TK","canonical_record":{"source":{"id":"2607.09488","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-10T15:05:21Z","cross_cats_sorted":[],"title_canon_sha256":"74ff2740c048952482b3cac75cbe9eb89126b25c1614f248f2de06bea182a0e8","abstract_canon_sha256":"75588693657a7edf758b3e94e19a63cf3d92ab9df6362f0f659044d339b061bf"},"schema_version":"1.0"},"canonical_sha256":"fd4dc2766a8bec45c8c3077062c1d2a4ac9a623afaca829f65d035ece15f8d3d","source":{"kind":"arxiv","id":"2607.09488","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.09488","created_at":"2026-07-13T01:20:13Z"},{"alias_kind":"arxiv_version","alias_value":"2607.09488v1","created_at":"2026-07-13T01:20:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09488","created_at":"2026-07-13T01:20:13Z"},{"alias_kind":"pith_short_12","alias_value":"7VG4E5TKRPWE","created_at":"2026-07-13T01:20:13Z"},{"alias_kind":"pith_short_16","alias_value":"7VG4E5TKRPWELSGD","created_at":"2026-07-13T01:20:13Z"},{"alias_kind":"pith_short_8","alias_value":"7VG4E5TK","created_at":"2026-07-13T01:20:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:7VG4E5TKRPWELSGDA5YGFQOSUS","target":"record","payload":{"canonical_record":{"source":{"id":"2607.09488","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-10T15:05:21Z","cross_cats_sorted":[],"title_canon_sha256":"74ff2740c048952482b3cac75cbe9eb89126b25c1614f248f2de06bea182a0e8","abstract_canon_sha256":"75588693657a7edf758b3e94e19a63cf3d92ab9df6362f0f659044d339b061bf"},"schema_version":"1.0"},"canonical_sha256":"fd4dc2766a8bec45c8c3077062c1d2a4ac9a623afaca829f65d035ece15f8d3d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T01:20:13.409804Z","signature_b64":"1b17hQ+rwJLk/V7jhuPSAHZrNoHKI90g9xbMlteYJPf2tq+9A/ntUu5g/HvE3em588A3cNbVYcx0uDUw6SHWBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd4dc2766a8bec45c8c3077062c1d2a4ac9a623afaca829f65d035ece15f8d3d","last_reissued_at":"2026-07-13T01:20:13.408815Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T01:20:13.408815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.09488","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":"2026-07-13T01:20:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iP/VQqtEsb1H4tdnLYBPDiwI3CjVylVMa9NHYeuknWPn4v9tNfmPGjaWn/cpT5KRfI+lriQx+k8CTiH5+a8GDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:12:10.534624Z"},"content_sha256":"52d831ae464d36edcc3b6e97dde05f5d8d59349f8bfe2f6b2c55040178b6ea6d","schema_version":"1.0","event_id":"sha256:52d831ae464d36edcc3b6e97dde05f5d8d59349f8bfe2f6b2c55040178b6ea6d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:7VG4E5TKRPWELSGDA5YGFQOSUS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SigLIP-HD by Fine-to-Coarse Supervision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hengshuang Zhao, Lihe Yang, Zhen Zhao","submitted_at":"2026-07-10T15:05:21Z","abstract_excerpt":"High-quality visual representation is a long-standing pursuit in computer vision. In the context of multimodal LLMs (MLLMs), feeding higher-resolution images can produce more fine-grained visual tokens. However, it introduces additional computational and design complexity, due to multiple forward passes and post-processing of increased tokens. Before simply adopting a higher resolution, have we truly unlocked the model's full perception capability at a standard resolution? Therefore, we study an interesting problem: how to achieve fine visual perception under lower cost without larger images. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09488","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/2607.09488/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":"2026-07-13T01:20:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4IYH0rBiqzqC92xRV9G4JPPNu2jwP/zGMYAws2p8wHkw+lKZkfnxZF0UeHbb1meWt3ReqV1CFUbHikuPjRBdBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:12:10.535239Z"},"content_sha256":"2d3fa69f8071aaf582a116e4cab9bf8a5e7d93b7eb1984937081e5e2d346ade5","schema_version":"1.0","event_id":"sha256:2d3fa69f8071aaf582a116e4cab9bf8a5e7d93b7eb1984937081e5e2d346ade5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7VG4E5TKRPWELSGDA5YGFQOSUS/bundle.json","state_url":"https://pith.science/pith/7VG4E5TKRPWELSGDA5YGFQOSUS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7VG4E5TKRPWELSGDA5YGFQOSUS/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":"2026-08-06T07:12:10Z","links":{"resolver":"https://pith.science/pith/7VG4E5TKRPWELSGDA5YGFQOSUS","bundle":"https://pith.science/pith/7VG4E5TKRPWELSGDA5YGFQOSUS/bundle.json","state":"https://pith.science/pith/7VG4E5TKRPWELSGDA5YGFQOSUS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7VG4E5TKRPWELSGDA5YGFQOSUS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7VG4E5TKRPWELSGDA5YGFQOSUS","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":"75588693657a7edf758b3e94e19a63cf3d92ab9df6362f0f659044d339b061bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-10T15:05:21Z","title_canon_sha256":"74ff2740c048952482b3cac75cbe9eb89126b25c1614f248f2de06bea182a0e8"},"schema_version":"1.0","source":{"id":"2607.09488","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.09488","created_at":"2026-07-13T01:20:13Z"},{"alias_kind":"arxiv_version","alias_value":"2607.09488v1","created_at":"2026-07-13T01:20:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09488","created_at":"2026-07-13T01:20:13Z"},{"alias_kind":"pith_short_12","alias_value":"7VG4E5TKRPWE","created_at":"2026-07-13T01:20:13Z"},{"alias_kind":"pith_short_16","alias_value":"7VG4E5TKRPWELSGD","created_at":"2026-07-13T01:20:13Z"},{"alias_kind":"pith_short_8","alias_value":"7VG4E5TK","created_at":"2026-07-13T01:20:13Z"}],"graph_snapshots":[{"event_id":"sha256:2d3fa69f8071aaf582a116e4cab9bf8a5e7d93b7eb1984937081e5e2d346ade5","target":"graph","created_at":"2026-07-13T01:20:13Z","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/2607.09488/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"High-quality visual representation is a long-standing pursuit in computer vision. In the context of multimodal LLMs (MLLMs), feeding higher-resolution images can produce more fine-grained visual tokens. However, it introduces additional computational and design complexity, due to multiple forward passes and post-processing of increased tokens. Before simply adopting a higher resolution, have we truly unlocked the model's full perception capability at a standard resolution? Therefore, we study an interesting problem: how to achieve fine visual perception under lower cost without larger images. ","authors_text":"Hengshuang Zhao, Lihe Yang, Zhen Zhao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-10T15:05:21Z","title":"SigLIP-HD by Fine-to-Coarse Supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09488","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":"sha256:52d831ae464d36edcc3b6e97dde05f5d8d59349f8bfe2f6b2c55040178b6ea6d","target":"record","created_at":"2026-07-13T01:20:13Z","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":"75588693657a7edf758b3e94e19a63cf3d92ab9df6362f0f659044d339b061bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-10T15:05:21Z","title_canon_sha256":"74ff2740c048952482b3cac75cbe9eb89126b25c1614f248f2de06bea182a0e8"},"schema_version":"1.0","source":{"id":"2607.09488","kind":"arxiv","version":1}},"canonical_sha256":"fd4dc2766a8bec45c8c3077062c1d2a4ac9a623afaca829f65d035ece15f8d3d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd4dc2766a8bec45c8c3077062c1d2a4ac9a623afaca829f65d035ece15f8d3d","first_computed_at":"2026-07-13T01:20:13.408815Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-13T01:20:13.408815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1b17hQ+rwJLk/V7jhuPSAHZrNoHKI90g9xbMlteYJPf2tq+9A/ntUu5g/HvE3em588A3cNbVYcx0uDUw6SHWBA==","signature_status":"signed_v1","signed_at":"2026-07-13T01:20:13.409804Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.09488","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52d831ae464d36edcc3b6e97dde05f5d8d59349f8bfe2f6b2c55040178b6ea6d","sha256:2d3fa69f8071aaf582a116e4cab9bf8a5e7d93b7eb1984937081e5e2d346ade5"],"state_sha256":"7970f1ae039d3ebfc0b053ced63048591a2c57d8cfcf991898c26cd1c2da8aa3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qvutArnnWhxAgIMZQDtUE5fytifPWi457gVpvZSGEmpN9WUSHsGOZ4J3ohf+ZzvT881Ot3mQ+EIcF+T/OzlNDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:12:10.539366Z","bundle_sha256":"42661062e1a0ac739c8d769c21ef23f4bb3503f6106938fbc428ab712e1056ce"}}