{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:33O6OSZLFMUKJOH4ZZ7E6LNA4U","short_pith_number":"pith:33O6OSZL","canonical_record":{"source":{"id":"2608.12748","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-13T02:57:21Z","cross_cats_sorted":[],"title_canon_sha256":"a5276bc9df514fba09cb513e4e859db47a76d3ff4068f37ad8cc524bd34af3ad","abstract_canon_sha256":"e311e080ec7044d0eb8686df20171564cfc14a0f80f1fa9c65164adae741ba5b"},"schema_version":"1.0"},"canonical_sha256":"dedde74b2b2b28a4b8fcce7e4f2da0e506a9b3b84d0560ef62ccde798bac4136","source":{"kind":"arxiv","id":"2608.12748","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.12748","created_at":"2026-08-14T00:47:26Z"},{"alias_kind":"arxiv_version","alias_value":"2608.12748v1","created_at":"2026-08-14T00:47:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12748","created_at":"2026-08-14T00:47:26Z"},{"alias_kind":"pith_short_12","alias_value":"33O6OSZLFMUK","created_at":"2026-08-14T00:47:26Z"},{"alias_kind":"pith_short_16","alias_value":"33O6OSZLFMUKJOH4","created_at":"2026-08-14T00:47:26Z"},{"alias_kind":"pith_short_8","alias_value":"33O6OSZL","created_at":"2026-08-14T00:47:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:33O6OSZLFMUKJOH4ZZ7E6LNA4U","target":"record","payload":{"canonical_record":{"source":{"id":"2608.12748","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-13T02:57:21Z","cross_cats_sorted":[],"title_canon_sha256":"a5276bc9df514fba09cb513e4e859db47a76d3ff4068f37ad8cc524bd34af3ad","abstract_canon_sha256":"e311e080ec7044d0eb8686df20171564cfc14a0f80f1fa9c65164adae741ba5b"},"schema_version":"1.0"},"canonical_sha256":"dedde74b2b2b28a4b8fcce7e4f2da0e506a9b3b84d0560ef62ccde798bac4136","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-14T00:47:26.565556Z","signature_b64":"Q1kybx+ZaVLIVhL+oNB8wXgLOjMZ0yypk1as536iFANa7HIEsVZjaCZYkmwhHLoPtEpcNTuIglfAZR2Bg/uiAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dedde74b2b2b28a4b8fcce7e4f2da0e506a9b3b84d0560ef62ccde798bac4136","last_reissued_at":"2026-08-14T00:47:26.537194Z","signature_status":"signed_v1","first_computed_at":"2026-08-14T00:47:26.537194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.12748","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":"2026-08-14T00:47:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pwUWR4OYchh8Xb2A2VoFa3OR4r3ZYZlB5bjSfQBjaXDupndErv1D72RuTB+V5f31s9hR5NQzlPo/MJGxfAayAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T10:42:48.673518Z"},"content_sha256":"0c3dce28bf717583c60992daa72e5197643b5406200ef992b1b1e5cc3ebd6d9e","schema_version":"1.0","event_id":"sha256:0c3dce28bf717583c60992daa72e5197643b5406200ef992b1b1e5cc3ebd6d9e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:33O6OSZLFMUKJOH4ZZ7E6LNA4U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling Representation Diversity: Modulated Attention and Reconstructive Regularization for Visual Grounding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fengyi Wu, Junli Lin, Junyi Hu, Tian Bai, Wei Wen, Xingchen Li, Yian Huang, Yi Zhang, Zaoli Li, Zhenming Peng","submitted_at":"2026-08-13T02:57:21Z","abstract_excerpt":"Referring Expression Comprehension (REC) is commonly studied under dataset-specific fine-tuning, resulting in specialist models with limited cross-dataset generalization. In this work, we revisit REC from the perspective of unified open-vocabulary grounding and identify representation degeneration as a key obstacle to scaling a single generalist model. To preserve representation diversity, we propose a holistic data-model co-design framework. Architecturally, we introduce the Modulated Attention-Contrastive Head (mACH) for efficient token-level vision-language alignment and a text-conditioned "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12748","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/2608.12748/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":"2026-08-14T00:47:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"masUaSgf12yHKjk1EQC+pmqIprrXe0cOd3Bb1peOxI2Z6ZdqYZVDtySXJ0y33CdmtwxAdLKgMzm0iNklXp9tBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T10:42:48.674030Z"},"content_sha256":"fcabeeb4aa4d983641974d4ca7f250109d74d80533ebf07680b5de9a36d7af43","schema_version":"1.0","event_id":"sha256:fcabeeb4aa4d983641974d4ca7f250109d74d80533ebf07680b5de9a36d7af43"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/33O6OSZLFMUKJOH4ZZ7E6LNA4U/bundle.json","state_url":"https://pith.science/pith/33O6OSZLFMUKJOH4ZZ7E6LNA4U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/33O6OSZLFMUKJOH4ZZ7E6LNA4U/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":"2026-08-19T10:42:48Z","links":{"resolver":"https://pith.science/pith/33O6OSZLFMUKJOH4ZZ7E6LNA4U","bundle":"https://pith.science/pith/33O6OSZLFMUKJOH4ZZ7E6LNA4U/bundle.json","state":"https://pith.science/pith/33O6OSZLFMUKJOH4ZZ7E6LNA4U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/33O6OSZLFMUKJOH4ZZ7E6LNA4U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:33O6OSZLFMUKJOH4ZZ7E6LNA4U","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":"e311e080ec7044d0eb8686df20171564cfc14a0f80f1fa9c65164adae741ba5b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-13T02:57:21Z","title_canon_sha256":"a5276bc9df514fba09cb513e4e859db47a76d3ff4068f37ad8cc524bd34af3ad"},"schema_version":"1.0","source":{"id":"2608.12748","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.12748","created_at":"2026-08-14T00:47:26Z"},{"alias_kind":"arxiv_version","alias_value":"2608.12748v1","created_at":"2026-08-14T00:47:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12748","created_at":"2026-08-14T00:47:26Z"},{"alias_kind":"pith_short_12","alias_value":"33O6OSZLFMUK","created_at":"2026-08-14T00:47:26Z"},{"alias_kind":"pith_short_16","alias_value":"33O6OSZLFMUKJOH4","created_at":"2026-08-14T00:47:26Z"},{"alias_kind":"pith_short_8","alias_value":"33O6OSZL","created_at":"2026-08-14T00:47:26Z"}],"graph_snapshots":[{"event_id":"sha256:fcabeeb4aa4d983641974d4ca7f250109d74d80533ebf07680b5de9a36d7af43","target":"graph","created_at":"2026-08-14T00:47:26Z","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/2608.12748/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Referring Expression Comprehension (REC) is commonly studied under dataset-specific fine-tuning, resulting in specialist models with limited cross-dataset generalization. In this work, we revisit REC from the perspective of unified open-vocabulary grounding and identify representation degeneration as a key obstacle to scaling a single generalist model. To preserve representation diversity, we propose a holistic data-model co-design framework. Architecturally, we introduce the Modulated Attention-Contrastive Head (mACH) for efficient token-level vision-language alignment and a text-conditioned ","authors_text":"Fengyi Wu, Junli Lin, Junyi Hu, Tian Bai, Wei Wen, Xingchen Li, Yian Huang, Yi Zhang, Zaoli Li, Zhenming Peng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-13T02:57:21Z","title":"Scaling Representation Diversity: Modulated Attention and Reconstructive Regularization for Visual Grounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12748","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":"sha256:0c3dce28bf717583c60992daa72e5197643b5406200ef992b1b1e5cc3ebd6d9e","target":"record","created_at":"2026-08-14T00:47:26Z","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":"e311e080ec7044d0eb8686df20171564cfc14a0f80f1fa9c65164adae741ba5b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-08-13T02:57:21Z","title_canon_sha256":"a5276bc9df514fba09cb513e4e859db47a76d3ff4068f37ad8cc524bd34af3ad"},"schema_version":"1.0","source":{"id":"2608.12748","kind":"arxiv","version":1}},"canonical_sha256":"dedde74b2b2b28a4b8fcce7e4f2da0e506a9b3b84d0560ef62ccde798bac4136","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dedde74b2b2b28a4b8fcce7e4f2da0e506a9b3b84d0560ef62ccde798bac4136","first_computed_at":"2026-08-14T00:47:26.537194Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-14T00:47:26.537194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q1kybx+ZaVLIVhL+oNB8wXgLOjMZ0yypk1as536iFANa7HIEsVZjaCZYkmwhHLoPtEpcNTuIglfAZR2Bg/uiAA==","signature_status":"signed_v1","signed_at":"2026-08-14T00:47:26.565556Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.12748","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c3dce28bf717583c60992daa72e5197643b5406200ef992b1b1e5cc3ebd6d9e","sha256:fcabeeb4aa4d983641974d4ca7f250109d74d80533ebf07680b5de9a36d7af43"],"state_sha256":"eb584b66401e7d567a33c0f28acb0fb6d635aa5bb59a76942d299275603723fa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DNnWvkII9UcZwItsYyvleiKtRrOvXNcTp8eQGs1qNgfLTFSrBR8mqNQzWGLTJsor0FqcW1ZhGNnITTX9H34WAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T10:42:48.679062Z","bundle_sha256":"d36733bb99b81b6f1968f5d1f9cf01e463454c809dc5bb24b208a315212ebe2d"}}