{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YPD2V4WXEEGGLZJ5UUWP3KNPIM","short_pith_number":"pith:YPD2V4WX","canonical_record":{"source":{"id":"2606.01825","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T07:41:44Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"b44cbd63e96f254050d6bd1c0a4698e5bb5a85aa46db741f9064c783bcf27723","abstract_canon_sha256":"515622d812ced0583c3e39dba95ac25a7040a8d6f2141e1e504ce54481cf2612"},"schema_version":"1.0"},"canonical_sha256":"c3c7aaf2d7210c65e53da52cfda9af433ddb270d6282600a1ce7cf80d63df162","source":{"kind":"arxiv","id":"2606.01825","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01825","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01825v1","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01825","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"YPD2V4WXEEGG","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"pith_short_16","alias_value":"YPD2V4WXEEGGLZJ5","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"pith_short_8","alias_value":"YPD2V4WX","created_at":"2026-06-02T02:04:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YPD2V4WXEEGGLZJ5UUWP3KNPIM","target":"record","payload":{"canonical_record":{"source":{"id":"2606.01825","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T07:41:44Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"b44cbd63e96f254050d6bd1c0a4698e5bb5a85aa46db741f9064c783bcf27723","abstract_canon_sha256":"515622d812ced0583c3e39dba95ac25a7040a8d6f2141e1e504ce54481cf2612"},"schema_version":"1.0"},"canonical_sha256":"c3c7aaf2d7210c65e53da52cfda9af433ddb270d6282600a1ce7cf80d63df162","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:57.900677Z","signature_b64":"+kVTbtKdBu/QCDLAQ/vsYHkbPtmLWoCkGyPvz0E7lCrxF6XeIY1PdQ3jvAupsjH0t0R8xlZFYnISGhO/b3e9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3c7aaf2d7210c65e53da52cfda9af433ddb270d6282600a1ce7cf80d63df162","last_reissued_at":"2026-06-02T02:04:57.900347Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:57.900347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.01825","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":"2026-06-02T02:04:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JaZQ1AwFzxFeaiFanxPJcure1P6L5x5pUr3W1ocFvN2bZvM6SuSj+2/4QzCWXCcO/22l4yw6TViTF5NBt0DIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T00:40:04.141976Z"},"content_sha256":"e277a816ce84a2b8e4e14ffe087f492f9e1b997b70d68aff2193f6b1c126a37b","schema_version":"1.0","event_id":"sha256:e277a816ce84a2b8e4e14ffe087f492f9e1b997b70d68aff2193f6b1c126a37b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YPD2V4WXEEGGLZJ5UUWP3KNPIM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ROGLE: Robust Global-Local Alignment with Automated Region Supervision for Text-Based Person Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Shulei Wang, Sihang Cai, Tao Jin, Xibei Jia, Zequn Xie","submitted_at":"2026-06-01T07:41:44Z","abstract_excerpt":"Text-Based Person Search (TBPS) aims to retrieve pedestrian images using natural language queries. However, existing TBPS models, especially those based on CLIP, struggle with fine-grained understanding due to global representational bias and semantic sparsity inherited from training on short captions. This results in weak fine-grained alignment, exacerbated by the scarcity of region-level annotations. To address this, we propose ROGLE (Robust Global-Local Embedding), a unified framework that overcomes reliance on costly manual annotations through an automated Region-to-Sentence Matching (RSM)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01825","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/2606.01825/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":"2026-06-02T02:04:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+R7NQsgLAVqFjMKdpOgMKK7nylTgPkQ5TCyw1YYpKvOdsL50eUNbgUmn9abFyluWviG6NgFtsLUqJc+OwZvmDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T00:40:04.142796Z"},"content_sha256":"c5ffb8df76d98eb8fb855ce2b13166f52afc0f12d5d41730a2cfbb0005a8b4b9","schema_version":"1.0","event_id":"sha256:c5ffb8df76d98eb8fb855ce2b13166f52afc0f12d5d41730a2cfbb0005a8b4b9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YPD2V4WXEEGGLZJ5UUWP3KNPIM/bundle.json","state_url":"https://pith.science/pith/YPD2V4WXEEGGLZJ5UUWP3KNPIM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YPD2V4WXEEGGLZJ5UUWP3KNPIM/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":"2026-06-11T00:40:04Z","links":{"resolver":"https://pith.science/pith/YPD2V4WXEEGGLZJ5UUWP3KNPIM","bundle":"https://pith.science/pith/YPD2V4WXEEGGLZJ5UUWP3KNPIM/bundle.json","state":"https://pith.science/pith/YPD2V4WXEEGGLZJ5UUWP3KNPIM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YPD2V4WXEEGGLZJ5UUWP3KNPIM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YPD2V4WXEEGGLZJ5UUWP3KNPIM","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":"515622d812ced0583c3e39dba95ac25a7040a8d6f2141e1e504ce54481cf2612","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T07:41:44Z","title_canon_sha256":"b44cbd63e96f254050d6bd1c0a4698e5bb5a85aa46db741f9064c783bcf27723"},"schema_version":"1.0","source":{"id":"2606.01825","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01825","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01825v1","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01825","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"YPD2V4WXEEGG","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"pith_short_16","alias_value":"YPD2V4WXEEGGLZJ5","created_at":"2026-06-02T02:04:57Z"},{"alias_kind":"pith_short_8","alias_value":"YPD2V4WX","created_at":"2026-06-02T02:04:57Z"}],"graph_snapshots":[{"event_id":"sha256:c5ffb8df76d98eb8fb855ce2b13166f52afc0f12d5d41730a2cfbb0005a8b4b9","target":"graph","created_at":"2026-06-02T02:04:57Z","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/2606.01825/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-Based Person Search (TBPS) aims to retrieve pedestrian images using natural language queries. However, existing TBPS models, especially those based on CLIP, struggle with fine-grained understanding due to global representational bias and semantic sparsity inherited from training on short captions. This results in weak fine-grained alignment, exacerbated by the scarcity of region-level annotations. To address this, we propose ROGLE (Robust Global-Local Embedding), a unified framework that overcomes reliance on costly manual annotations through an automated Region-to-Sentence Matching (RSM)","authors_text":"Shulei Wang, Sihang Cai, Tao Jin, Xibei Jia, Zequn Xie","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T07:41:44Z","title":"ROGLE: Robust Global-Local Alignment with Automated Region Supervision for Text-Based Person Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01825","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:e277a816ce84a2b8e4e14ffe087f492f9e1b997b70d68aff2193f6b1c126a37b","target":"record","created_at":"2026-06-02T02:04:57Z","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":"515622d812ced0583c3e39dba95ac25a7040a8d6f2141e1e504ce54481cf2612","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T07:41:44Z","title_canon_sha256":"b44cbd63e96f254050d6bd1c0a4698e5bb5a85aa46db741f9064c783bcf27723"},"schema_version":"1.0","source":{"id":"2606.01825","kind":"arxiv","version":1}},"canonical_sha256":"c3c7aaf2d7210c65e53da52cfda9af433ddb270d6282600a1ce7cf80d63df162","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3c7aaf2d7210c65e53da52cfda9af433ddb270d6282600a1ce7cf80d63df162","first_computed_at":"2026-06-02T02:04:57.900347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:57.900347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+kVTbtKdBu/QCDLAQ/vsYHkbPtmLWoCkGyPvz0E7lCrxF6XeIY1PdQ3jvAupsjH0t0R8xlZFYnISGhO/b3e9CQ==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:57.900677Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01825","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e277a816ce84a2b8e4e14ffe087f492f9e1b997b70d68aff2193f6b1c126a37b","sha256:c5ffb8df76d98eb8fb855ce2b13166f52afc0f12d5d41730a2cfbb0005a8b4b9"],"state_sha256":"b635a1cfef04e13ead35f0e897bed2d59f6795acd9df9da4f622ceb107544cd5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VHS6/bvvK+PaoTaDlxZifNDZYMcaYI9xoM6kmJ5VqGbfOt/Y0SaLptYLqx37xk3rsxxNoRMDtc0xwaQ8c0eLAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T00:40:04.146924Z","bundle_sha256":"6cfecc7bf4619f5ace09eec281d3d662b8cb0531b7dfa71fcce9288be61ae6e0"}}