{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7HY5ZSDONWULW6FS3N55Z6U5CV","short_pith_number":"pith:7HY5ZSDO","schema_version":"1.0","canonical_sha256":"f9f1dcc86e6da8bb78b2db7bdcfa9d154b824f92205403b1df81162ff74bfc10","source":{"kind":"arxiv","id":"2605.26689","version":1},"attestation_state":"computed","paper":{"title":"PinPoint: Prompting with Informative Interior Points","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Alex Wong, C. Thomas, Pedro Pablo Guerrero Vela, Pouya Sadeghi, Shawn He, Sirisha Rambhatla","submitted_at":"2026-05-26T08:28:54Z","abstract_excerpt":"Modern referring image segmentation pipelines couple a vision-language model (VLM) for grounding with a promptable segmenter such as the Segment Anything Model (SAM) for mask generation. Prior training-free instances of this recipe consistently trail fine-tuned and reinforcement-learning (RL)-tuned specialists, and it has been unclear whether the gap comes from the VLM's grounding, SAM's capacity, or the prompt. We show that the gap is dominated by prompt ambiguity: a VLM-proposed bounding box (bbox) leaves SAM to guess which pixels inside the bbox belong to the object the expression denotes. "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.26689","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T08:28:54Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"85f847c484cfe31e2684b1afe93a8cef0ecb288133a53f70145cddd1450b0679","abstract_canon_sha256":"7ce0be22298f10561d3f7e8078d1fd6d0c02b30ca322155e1514b511d8d8bff4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:06:06.206300Z","signature_b64":"l1QVCpVbRWV63QoDKgkOdxOwC1Pnwgji1/n0LasW9f6wjQHdDrSRyRU3sEp2ZFJwXm8PQ/vc+hTeKSvD+2rWAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9f1dcc86e6da8bb78b2db7bdcfa9d154b824f92205403b1df81162ff74bfc10","last_reissued_at":"2026-05-27T01:06:06.205567Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:06:06.205567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PinPoint: Prompting with Informative Interior Points","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Alex Wong, C. Thomas, Pedro Pablo Guerrero Vela, Pouya Sadeghi, Shawn He, Sirisha Rambhatla","submitted_at":"2026-05-26T08:28:54Z","abstract_excerpt":"Modern referring image segmentation pipelines couple a vision-language model (VLM) for grounding with a promptable segmenter such as the Segment Anything Model (SAM) for mask generation. Prior training-free instances of this recipe consistently trail fine-tuned and reinforcement-learning (RL)-tuned specialists, and it has been unclear whether the gap comes from the VLM's grounding, SAM's capacity, or the prompt. We show that the gap is dominated by prompt ambiguity: a VLM-proposed bounding box (bbox) leaves SAM to guess which pixels inside the bbox belong to the object the expression denotes. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26689","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/2605.26689/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.26689","created_at":"2026-05-27T01:06:06.205669+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26689v1","created_at":"2026-05-27T01:06:06.205669+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26689","created_at":"2026-05-27T01:06:06.205669+00:00"},{"alias_kind":"pith_short_12","alias_value":"7HY5ZSDONWUL","created_at":"2026-05-27T01:06:06.205669+00:00"},{"alias_kind":"pith_short_16","alias_value":"7HY5ZSDONWULW6FS","created_at":"2026-05-27T01:06:06.205669+00:00"},{"alias_kind":"pith_short_8","alias_value":"7HY5ZSDO","created_at":"2026-05-27T01:06:06.205669+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7HY5ZSDONWULW6FS3N55Z6U5CV","json":"https://pith.science/pith/7HY5ZSDONWULW6FS3N55Z6U5CV.json","graph_json":"https://pith.science/api/pith-number/7HY5ZSDONWULW6FS3N55Z6U5CV/graph.json","events_json":"https://pith.science/api/pith-number/7HY5ZSDONWULW6FS3N55Z6U5CV/events.json","paper":"https://pith.science/paper/7HY5ZSDO"},"agent_actions":{"view_html":"https://pith.science/pith/7HY5ZSDONWULW6FS3N55Z6U5CV","download_json":"https://pith.science/pith/7HY5ZSDONWULW6FS3N55Z6U5CV.json","view_paper":"https://pith.science/paper/7HY5ZSDO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26689&json=true","fetch_graph":"https://pith.science/api/pith-number/7HY5ZSDONWULW6FS3N55Z6U5CV/graph.json","fetch_events":"https://pith.science/api/pith-number/7HY5ZSDONWULW6FS3N55Z6U5CV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7HY5ZSDONWULW6FS3N55Z6U5CV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7HY5ZSDONWULW6FS3N55Z6U5CV/action/storage_attestation","attest_author":"https://pith.science/pith/7HY5ZSDONWULW6FS3N55Z6U5CV/action/author_attestation","sign_citation":"https://pith.science/pith/7HY5ZSDONWULW6FS3N55Z6U5CV/action/citation_signature","submit_replication":"https://pith.science/pith/7HY5ZSDONWULW6FS3N55Z6U5CV/action/replication_record"}},"created_at":"2026-05-27T01:06:06.205669+00:00","updated_at":"2026-05-27T01:06:06.205669+00:00"}