{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SX3Y23HVPE5VDDQTJFQAMI4XNJ","short_pith_number":"pith:SX3Y23HV","canonical_record":{"source":{"id":"2605.18018","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T08:09:37Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"5bce525daa5a0ae2f1e6b7807f2c519c6c802e4bec18445e9d13c1f4be0c9d2b","abstract_canon_sha256":"bf3fd6dedfef2bab148bd7c366b6ef9796e66eed6bd077d466c0d5d6a5f07aa1"},"schema_version":"1.0"},"canonical_sha256":"95f78d6cf5793b518e1349600623976a6e3a1bfcaba0acd77a0d92fec3f56ce2","source":{"kind":"arxiv","id":"2605.18018","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18018","created_at":"2026-05-20T00:05:11Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18018v1","created_at":"2026-05-20T00:05:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18018","created_at":"2026-05-20T00:05:11Z"},{"alias_kind":"pith_short_12","alias_value":"SX3Y23HVPE5V","created_at":"2026-05-20T00:05:11Z"},{"alias_kind":"pith_short_16","alias_value":"SX3Y23HVPE5VDDQT","created_at":"2026-05-20T00:05:11Z"},{"alias_kind":"pith_short_8","alias_value":"SX3Y23HV","created_at":"2026-05-20T00:05:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SX3Y23HVPE5VDDQTJFQAMI4XNJ","target":"record","payload":{"canonical_record":{"source":{"id":"2605.18018","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T08:09:37Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"5bce525daa5a0ae2f1e6b7807f2c519c6c802e4bec18445e9d13c1f4be0c9d2b","abstract_canon_sha256":"bf3fd6dedfef2bab148bd7c366b6ef9796e66eed6bd077d466c0d5d6a5f07aa1"},"schema_version":"1.0"},"canonical_sha256":"95f78d6cf5793b518e1349600623976a6e3a1bfcaba0acd77a0d92fec3f56ce2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:11.546659Z","signature_b64":"czBiWD7lkCs+PN40li9bMhNfSwhyG9bXtYChtE5NuxdQkf7f9l1r0vs6zFQ3CrrHD3oJFD+D5IlCLqWpQn9hAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95f78d6cf5793b518e1349600623976a6e3a1bfcaba0acd77a0d92fec3f56ce2","last_reissued_at":"2026-05-20T00:05:11.545836Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:11.545836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.18018","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":"2026-05-20T00:05:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UwzcuYdRb81+SGjI4z2Y27jMc2X/GmysFQlP4S6YRQc4YY39a/AP/qBrtH66ygTdrR89KC1CK1xjOqBKGcn2Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T16:04:56.883281Z"},"content_sha256":"781ae27069d53a99a0ad011db7acdadca60ee77f576779a9c0525df22b50169c","schema_version":"1.0","event_id":"sha256:781ae27069d53a99a0ad011db7acdadca60ee77f576779a9c0525df22b50169c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SX3Y23HVPE5VDDQTJFQAMI4XNJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CV","authors_text":"Bowen Yin, Boyuan Sun, Qibin Hou, Xihan Wei, Yuanming Li","submitted_at":"2026-05-18T08:09:37Z","abstract_excerpt":"We present SWIM (See What I Mean), a novel training strategy that aligns vision and language representations to enable fine-grained object understanding solely from textual prompts. Unlike existing approaches that require explicit visual prompts, such as masks or points, SWIM leverages mask supervision only during training to guide cross-modal attention, allowing the model to automatically attend to the user-specified object at inference. Our cross-attention analysis of pretrained multimodal large languagemodels (MLLMs) reveals a systematic discrepancy: Attribute words produce sharp, localized"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18018","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/2605.18018/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:35.522418Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"399dbc485088d6816e2acf65a36ae24994f906d1741aa8e9068850805d2f04f8"},"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":"2026-05-20T00:05:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6CLtXryGyjL1p0iYm+5aEQK9k621PMud0tAsSQhrnJKJtbFhwEFKob1hyFK65vNI7iGEcCgIb0NkUI0IX9kuAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T16:04:56.884114Z"},"content_sha256":"e1fc61de7f1e3a91165256cfbb87be17f1671bf15c3686203d0055a08e2fa1b1","schema_version":"1.0","event_id":"sha256:e1fc61de7f1e3a91165256cfbb87be17f1671bf15c3686203d0055a08e2fa1b1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SX3Y23HVPE5VDDQTJFQAMI4XNJ/bundle.json","state_url":"https://pith.science/pith/SX3Y23HVPE5VDDQTJFQAMI4XNJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SX3Y23HVPE5VDDQTJFQAMI4XNJ/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":"2026-05-29T16:04:56Z","links":{"resolver":"https://pith.science/pith/SX3Y23HVPE5VDDQTJFQAMI4XNJ","bundle":"https://pith.science/pith/SX3Y23HVPE5VDDQTJFQAMI4XNJ/bundle.json","state":"https://pith.science/pith/SX3Y23HVPE5VDDQTJFQAMI4XNJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SX3Y23HVPE5VDDQTJFQAMI4XNJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SX3Y23HVPE5VDDQTJFQAMI4XNJ","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":"bf3fd6dedfef2bab148bd7c366b6ef9796e66eed6bd077d466c0d5d6a5f07aa1","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T08:09:37Z","title_canon_sha256":"5bce525daa5a0ae2f1e6b7807f2c519c6c802e4bec18445e9d13c1f4be0c9d2b"},"schema_version":"1.0","source":{"id":"2605.18018","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18018","created_at":"2026-05-20T00:05:11Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18018v1","created_at":"2026-05-20T00:05:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18018","created_at":"2026-05-20T00:05:11Z"},{"alias_kind":"pith_short_12","alias_value":"SX3Y23HVPE5V","created_at":"2026-05-20T00:05:11Z"},{"alias_kind":"pith_short_16","alias_value":"SX3Y23HVPE5VDDQT","created_at":"2026-05-20T00:05:11Z"},{"alias_kind":"pith_short_8","alias_value":"SX3Y23HV","created_at":"2026-05-20T00:05:11Z"}],"graph_snapshots":[{"event_id":"sha256:e1fc61de7f1e3a91165256cfbb87be17f1671bf15c3686203d0055a08e2fa1b1","target":"graph","created_at":"2026-05-20T00:05:11Z","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":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:35.522418Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.18018/integrity.json","findings":[],"snapshot_sha256":"399dbc485088d6816e2acf65a36ae24994f906d1741aa8e9068850805d2f04f8","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present SWIM (See What I Mean), a novel training strategy that aligns vision and language representations to enable fine-grained object understanding solely from textual prompts. Unlike existing approaches that require explicit visual prompts, such as masks or points, SWIM leverages mask supervision only during training to guide cross-modal attention, allowing the model to automatically attend to the user-specified object at inference. Our cross-attention analysis of pretrained multimodal large languagemodels (MLLMs) reveals a systematic discrepancy: Attribute words produce sharp, localized","authors_text":"Bowen Yin, Boyuan Sun, Qibin Hou, Xihan Wei, Yuanming Li","cross_cats":["cs.AI","cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T08:09:37Z","title":"See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18018","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":"sha256:781ae27069d53a99a0ad011db7acdadca60ee77f576779a9c0525df22b50169c","target":"record","created_at":"2026-05-20T00:05:11Z","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":"bf3fd6dedfef2bab148bd7c366b6ef9796e66eed6bd077d466c0d5d6a5f07aa1","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T08:09:37Z","title_canon_sha256":"5bce525daa5a0ae2f1e6b7807f2c519c6c802e4bec18445e9d13c1f4be0c9d2b"},"schema_version":"1.0","source":{"id":"2605.18018","kind":"arxiv","version":1}},"canonical_sha256":"95f78d6cf5793b518e1349600623976a6e3a1bfcaba0acd77a0d92fec3f56ce2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95f78d6cf5793b518e1349600623976a6e3a1bfcaba0acd77a0d92fec3f56ce2","first_computed_at":"2026-05-20T00:05:11.545836Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:11.545836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"czBiWD7lkCs+PN40li9bMhNfSwhyG9bXtYChtE5NuxdQkf7f9l1r0vs6zFQ3CrrHD3oJFD+D5IlCLqWpQn9hAA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:11.546659Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18018","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:781ae27069d53a99a0ad011db7acdadca60ee77f576779a9c0525df22b50169c","sha256:e1fc61de7f1e3a91165256cfbb87be17f1671bf15c3686203d0055a08e2fa1b1"],"state_sha256":"832e96d2737e8e6fb20b96f5629129dc590a21e58c184271a89c230ebe14c106"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rf+LV3U8aHGbFs4f3PFyFPk/htnYECLsGkNi/Qs9WmkcDMwheN69iETNZzSJXpOd3Gpg8umaBnD2p4SPzitrAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T16:04:56.888726Z","bundle_sha256":"cbfa639d84e096f155c0bc85dcc2459fc85566b5f4e3ff85e8019bdcb99d88da"}}