{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OZHUOGCXSXV4VS43SZV3YOJYDC","short_pith_number":"pith:OZHUOGCX","canonical_record":{"source":{"id":"2607.04605","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-06T02:19:11Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"987a9660447e5e19b3ebc49ba4cf6bfe1ed1d4991f7a24f89dbc61ca4474f745","abstract_canon_sha256":"14e9b16ebda1b70a9206f839b03ddde627c7781485580da16219f1b00460dda6"},"schema_version":"1.0"},"canonical_sha256":"764f47185795ebcacb9b966bbc393818be782edea7e72e04f8eee684ae8ceee5","source":{"kind":"arxiv","id":"2607.04605","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04605","created_at":"2026-07-07T02:19:27Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04605v1","created_at":"2026-07-07T02:19:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04605","created_at":"2026-07-07T02:19:27Z"},{"alias_kind":"pith_short_12","alias_value":"OZHUOGCXSXV4","created_at":"2026-07-07T02:19:27Z"},{"alias_kind":"pith_short_16","alias_value":"OZHUOGCXSXV4VS43","created_at":"2026-07-07T02:19:27Z"},{"alias_kind":"pith_short_8","alias_value":"OZHUOGCX","created_at":"2026-07-07T02:19:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OZHUOGCXSXV4VS43SZV3YOJYDC","target":"record","payload":{"canonical_record":{"source":{"id":"2607.04605","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-06T02:19:11Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"987a9660447e5e19b3ebc49ba4cf6bfe1ed1d4991f7a24f89dbc61ca4474f745","abstract_canon_sha256":"14e9b16ebda1b70a9206f839b03ddde627c7781485580da16219f1b00460dda6"},"schema_version":"1.0"},"canonical_sha256":"764f47185795ebcacb9b966bbc393818be782edea7e72e04f8eee684ae8ceee5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:19:27.117170Z","signature_b64":"WajAM3d2A4KebVjlmGD0FyVusvJrv0RdWOpsdmu+Qs8LTLXAmjnLa8RCkZJSv01U6dmWB8OGE7fadG5/RebgBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"764f47185795ebcacb9b966bbc393818be782edea7e72e04f8eee684ae8ceee5","last_reissued_at":"2026-07-07T02:19:27.116378Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:19:27.116378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.04605","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":"2026-07-07T02:19:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GmcMlutqMUw1e/AeIqe8ks0gQKWTLAxEpG/BdEMLRoavPEcY1MgAouaYrEW2l3S08CdAQyWmRwbfBn3b+BbGBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T12:28:50.144613Z"},"content_sha256":"e98e76a977207106ad8855f8c0941455a2a0944329501737f6e4201ec229e90b","schema_version":"1.0","event_id":"sha256:e98e76a977207106ad8855f8c0941455a2a0944329501737f6e4201ec229e90b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OZHUOGCXSXV4VS43SZV3YOJYDC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.IR","authors_text":"Jaewoo Kang, Jungwoo Park, Junha Jung, Suhyeong Park","submitted_at":"2026-07-06T02:19:11Z","abstract_excerpt":"Multi-vector vision-language retrieval preserves fine-grained visual evidence through maximum-similarity late interaction, but dense image-side tokens make storage and scoring expensive. Existing token compression methods reduce this cost, yet they can remove or collapse object- and region-level evidence that future query tokens may need to select. We propose SaMer, an object-aware token merging framework that compresses image-side post-projector tokens into $K$ representative centroids while preserving the original late-interaction interface. SaMer uses object annotations only during training"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04605","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/2607.04605/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":"2026-07-07T02:19:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s2M5xOeNF4kkIQGJW6XRiXzPHtRTUQsV3za5nHHqR34p8URYrHTwhg6z2p4Nh57r3dQ1RDW6+eVHs29bodg8CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T12:28:50.145135Z"},"content_sha256":"a79fd0bb5de364bc20eb916a375b89fbfa517ed435ea9f5131ba4c453d0868fb","schema_version":"1.0","event_id":"sha256:a79fd0bb5de364bc20eb916a375b89fbfa517ed435ea9f5131ba4c453d0868fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OZHUOGCXSXV4VS43SZV3YOJYDC/bundle.json","state_url":"https://pith.science/pith/OZHUOGCXSXV4VS43SZV3YOJYDC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OZHUOGCXSXV4VS43SZV3YOJYDC/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":"2026-08-19T12:28:50Z","links":{"resolver":"https://pith.science/pith/OZHUOGCXSXV4VS43SZV3YOJYDC","bundle":"https://pith.science/pith/OZHUOGCXSXV4VS43SZV3YOJYDC/bundle.json","state":"https://pith.science/pith/OZHUOGCXSXV4VS43SZV3YOJYDC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OZHUOGCXSXV4VS43SZV3YOJYDC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OZHUOGCXSXV4VS43SZV3YOJYDC","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":"14e9b16ebda1b70a9206f839b03ddde627c7781485580da16219f1b00460dda6","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-06T02:19:11Z","title_canon_sha256":"987a9660447e5e19b3ebc49ba4cf6bfe1ed1d4991f7a24f89dbc61ca4474f745"},"schema_version":"1.0","source":{"id":"2607.04605","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04605","created_at":"2026-07-07T02:19:27Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04605v1","created_at":"2026-07-07T02:19:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04605","created_at":"2026-07-07T02:19:27Z"},{"alias_kind":"pith_short_12","alias_value":"OZHUOGCXSXV4","created_at":"2026-07-07T02:19:27Z"},{"alias_kind":"pith_short_16","alias_value":"OZHUOGCXSXV4VS43","created_at":"2026-07-07T02:19:27Z"},{"alias_kind":"pith_short_8","alias_value":"OZHUOGCX","created_at":"2026-07-07T02:19:27Z"}],"graph_snapshots":[{"event_id":"sha256:a79fd0bb5de364bc20eb916a375b89fbfa517ed435ea9f5131ba4c453d0868fb","target":"graph","created_at":"2026-07-07T02:19:27Z","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/2607.04605/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-vector vision-language retrieval preserves fine-grained visual evidence through maximum-similarity late interaction, but dense image-side tokens make storage and scoring expensive. Existing token compression methods reduce this cost, yet they can remove or collapse object- and region-level evidence that future query tokens may need to select. We propose SaMer, an object-aware token merging framework that compresses image-side post-projector tokens into $K$ representative centroids while preserving the original late-interaction interface. SaMer uses object annotations only during training","authors_text":"Jaewoo Kang, Jungwoo Park, Junha Jung, Suhyeong Park","cross_cats":["cs.AI","cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-06T02:19:11Z","title":"Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04605","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:e98e76a977207106ad8855f8c0941455a2a0944329501737f6e4201ec229e90b","target":"record","created_at":"2026-07-07T02:19:27Z","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":"14e9b16ebda1b70a9206f839b03ddde627c7781485580da16219f1b00460dda6","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-06T02:19:11Z","title_canon_sha256":"987a9660447e5e19b3ebc49ba4cf6bfe1ed1d4991f7a24f89dbc61ca4474f745"},"schema_version":"1.0","source":{"id":"2607.04605","kind":"arxiv","version":1}},"canonical_sha256":"764f47185795ebcacb9b966bbc393818be782edea7e72e04f8eee684ae8ceee5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"764f47185795ebcacb9b966bbc393818be782edea7e72e04f8eee684ae8ceee5","first_computed_at":"2026-07-07T02:19:27.116378Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:19:27.116378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WajAM3d2A4KebVjlmGD0FyVusvJrv0RdWOpsdmu+Qs8LTLXAmjnLa8RCkZJSv01U6dmWB8OGE7fadG5/RebgBw==","signature_status":"signed_v1","signed_at":"2026-07-07T02:19:27.117170Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.04605","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e98e76a977207106ad8855f8c0941455a2a0944329501737f6e4201ec229e90b","sha256:a79fd0bb5de364bc20eb916a375b89fbfa517ed435ea9f5131ba4c453d0868fb"],"state_sha256":"4bcb06faf161e188cfa7c7f914f109c4e6a4d68fd0539383ae81a3b502902f8d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QLdFu3RLqsfcGO/srZ304VHrRa6xNqB5cAWmWoGxkyxcTGs4sq8s3OcRIppqln+Pu6SRCufLNUlSsRfYhIpFCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T12:28:50.150418Z","bundle_sha256":"c14172de86ae479c120c41f31e75bd8adb8e4199561959d27efac64d96669979"}}