{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:D4AXM4J37UKAJPPNQTFAOHDT7N","short_pith_number":"pith:D4AXM4J3","schema_version":"1.0","canonical_sha256":"1f0176713bfd1404bded84ca071c73fb4842c2d2054995c351437deecf6a72fb","source":{"kind":"arxiv","id":"2607.03143","version":1},"attestation_state":"computed","paper":{"title":"Text as Partial Constraint: Core-Residual Alignment for Robust Vision-Language Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Canran Xiao, Chengzhen Yu, Siyuan Ma, Yang Liu","submitted_at":"2026-07-03T09:32:01Z","abstract_excerpt":"Vision-language alignment powers open-vocabulary recognition, retrieval, and LVLM grounding, yet natural captions are often underspecified, making similarity brittle and overly confident under paraphrase and omitted details. We aim to learn representations whose matching is stable across caption views and whose confidence reflects how strongly text constrains an image. We propose Text as Partial Constraint (TPC), a core-residual alignment framework that treats multi-view captions as incomplete supervision. It distills a consensus semantic core as the alignment target, learns a single-view core"},"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":"2607.03143","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-03T09:32:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cfb16a567d0535d7ac14833256e3e0f20a063cb5bcff20a1ab6b7297e49287ec","abstract_canon_sha256":"c8cd44afcb9c24de1875c16037b9fa281a73a278f35584f5b44fc91e07c54404"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T01:16:44.439825Z","signature_b64":"2kICR6cNNSCwXE2XxlrDuPnxEuNS1aXghw9nAbtF0kuZTkIGKQmfZY/eZ4OlSOcPUsIZ9cYtq0bXoX/DpEdTCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f0176713bfd1404bded84ca071c73fb4842c2d2054995c351437deecf6a72fb","last_reissued_at":"2026-07-07T01:16:44.439375Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T01:16:44.439375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text as Partial Constraint: Core-Residual Alignment for Robust Vision-Language Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Canran Xiao, Chengzhen Yu, Siyuan Ma, Yang Liu","submitted_at":"2026-07-03T09:32:01Z","abstract_excerpt":"Vision-language alignment powers open-vocabulary recognition, retrieval, and LVLM grounding, yet natural captions are often underspecified, making similarity brittle and overly confident under paraphrase and omitted details. We aim to learn representations whose matching is stable across caption views and whose confidence reflects how strongly text constrains an image. We propose Text as Partial Constraint (TPC), a core-residual alignment framework that treats multi-view captions as incomplete supervision. It distills a consensus semantic core as the alignment target, learns a single-view core"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03143","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/2607.03143/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":"2607.03143","created_at":"2026-07-07T01:16:44.439434+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.03143v1","created_at":"2026-07-07T01:16:44.439434+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03143","created_at":"2026-07-07T01:16:44.439434+00:00"},{"alias_kind":"pith_short_12","alias_value":"D4AXM4J37UKA","created_at":"2026-07-07T01:16:44.439434+00:00"},{"alias_kind":"pith_short_16","alias_value":"D4AXM4J37UKAJPPN","created_at":"2026-07-07T01:16:44.439434+00:00"},{"alias_kind":"pith_short_8","alias_value":"D4AXM4J3","created_at":"2026-07-07T01:16:44.439434+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/D4AXM4J37UKAJPPNQTFAOHDT7N","json":"https://pith.science/pith/D4AXM4J37UKAJPPNQTFAOHDT7N.json","graph_json":"https://pith.science/api/pith-number/D4AXM4J37UKAJPPNQTFAOHDT7N/graph.json","events_json":"https://pith.science/api/pith-number/D4AXM4J37UKAJPPNQTFAOHDT7N/events.json","paper":"https://pith.science/paper/D4AXM4J3"},"agent_actions":{"view_html":"https://pith.science/pith/D4AXM4J37UKAJPPNQTFAOHDT7N","download_json":"https://pith.science/pith/D4AXM4J37UKAJPPNQTFAOHDT7N.json","view_paper":"https://pith.science/paper/D4AXM4J3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.03143&json=true","fetch_graph":"https://pith.science/api/pith-number/D4AXM4J37UKAJPPNQTFAOHDT7N/graph.json","fetch_events":"https://pith.science/api/pith-number/D4AXM4J37UKAJPPNQTFAOHDT7N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D4AXM4J37UKAJPPNQTFAOHDT7N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D4AXM4J37UKAJPPNQTFAOHDT7N/action/storage_attestation","attest_author":"https://pith.science/pith/D4AXM4J37UKAJPPNQTFAOHDT7N/action/author_attestation","sign_citation":"https://pith.science/pith/D4AXM4J37UKAJPPNQTFAOHDT7N/action/citation_signature","submit_replication":"https://pith.science/pith/D4AXM4J37UKAJPPNQTFAOHDT7N/action/replication_record"}},"created_at":"2026-07-07T01:16:44.439434+00:00","updated_at":"2026-07-07T01:16:44.439434+00:00"}