{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JSCDJQFMZSWJBLD7554BHS7Y2H","short_pith_number":"pith:JSCDJQFM","schema_version":"1.0","canonical_sha256":"4c8434c0acccac90ac7fef7813cbf8d1d6d90ffa4ec7c4704febd537de697a24","source":{"kind":"arxiv","id":"2608.03216","version":1},"attestation_state":"computed","paper":{"title":"iFAN: Inference-Aware Learning for Plain Mask Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fang Li, Haoyang Tong, Jingling Fu, Junshi Huang, Ke Zhang, Lichen Ma, Luohang Liu, Tongxuan Liu, Wenxiao Fan, Yu He","submitted_at":"2026-08-04T06:51:06Z","abstract_excerpt":"Query-based mask transformers assemble segmentation outputs through pixel-wise competition among query predictions of the final layer, yet this inference process is not explicitly optimized during training. We identify two key mismatches: the query with the highest probability-mask score does not necessarily produce the most accurate mask, and final-layer decoding may discard superior predictions from intermediate layers. To address these issues, we propose Inference-Aware Learning (iFAN), a general training framework for plain mask transformers. iFAN introduces Adjusted Probability-Mask Ranki"},"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":"2608.03216","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-04T06:51:06Z","cross_cats_sorted":[],"title_canon_sha256":"0092417fab578e96a338131c85947bc704af43c1a3c9652119ee274d917a23d6","abstract_canon_sha256":"0e2b0a7c613172a0ea156d4cc69b32bfdb7f722a58048d41f9e9f50b83d19461"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T00:46:18.014394Z","signature_b64":"0OD/EuZewpsYJklM1VdPGAgewWj5HNSihrMDppAzsjm6XdsAvbUd0IAVlebTjIoM0IyukOB0lLA/gGuWjVZaBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c8434c0acccac90ac7fef7813cbf8d1d6d90ffa4ec7c4704febd537de697a24","last_reissued_at":"2026-08-05T00:46:18.011745Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T00:46:18.011745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"iFAN: Inference-Aware Learning for Plain Mask Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fang Li, Haoyang Tong, Jingling Fu, Junshi Huang, Ke Zhang, Lichen Ma, Luohang Liu, Tongxuan Liu, Wenxiao Fan, Yu He","submitted_at":"2026-08-04T06:51:06Z","abstract_excerpt":"Query-based mask transformers assemble segmentation outputs through pixel-wise competition among query predictions of the final layer, yet this inference process is not explicitly optimized during training. We identify two key mismatches: the query with the highest probability-mask score does not necessarily produce the most accurate mask, and final-layer decoding may discard superior predictions from intermediate layers. To address these issues, we propose Inference-Aware Learning (iFAN), a general training framework for plain mask transformers. iFAN introduces Adjusted Probability-Mask Ranki"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03216","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/2608.03216/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":"2608.03216","created_at":"2026-08-05T00:46:18.012830+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03216v1","created_at":"2026-08-05T00:46:18.012830+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03216","created_at":"2026-08-05T00:46:18.012830+00:00"},{"alias_kind":"pith_short_12","alias_value":"JSCDJQFMZSWJ","created_at":"2026-08-05T00:46:18.012830+00:00"},{"alias_kind":"pith_short_16","alias_value":"JSCDJQFMZSWJBLD7","created_at":"2026-08-05T00:46:18.012830+00:00"},{"alias_kind":"pith_short_8","alias_value":"JSCDJQFM","created_at":"2026-08-05T00:46:18.012830+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/JSCDJQFMZSWJBLD7554BHS7Y2H","json":"https://pith.science/pith/JSCDJQFMZSWJBLD7554BHS7Y2H.json","graph_json":"https://pith.science/api/pith-number/JSCDJQFMZSWJBLD7554BHS7Y2H/graph.json","events_json":"https://pith.science/api/pith-number/JSCDJQFMZSWJBLD7554BHS7Y2H/events.json","paper":"https://pith.science/paper/JSCDJQFM"},"agent_actions":{"view_html":"https://pith.science/pith/JSCDJQFMZSWJBLD7554BHS7Y2H","download_json":"https://pith.science/pith/JSCDJQFMZSWJBLD7554BHS7Y2H.json","view_paper":"https://pith.science/paper/JSCDJQFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03216&json=true","fetch_graph":"https://pith.science/api/pith-number/JSCDJQFMZSWJBLD7554BHS7Y2H/graph.json","fetch_events":"https://pith.science/api/pith-number/JSCDJQFMZSWJBLD7554BHS7Y2H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JSCDJQFMZSWJBLD7554BHS7Y2H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JSCDJQFMZSWJBLD7554BHS7Y2H/action/storage_attestation","attest_author":"https://pith.science/pith/JSCDJQFMZSWJBLD7554BHS7Y2H/action/author_attestation","sign_citation":"https://pith.science/pith/JSCDJQFMZSWJBLD7554BHS7Y2H/action/citation_signature","submit_replication":"https://pith.science/pith/JSCDJQFMZSWJBLD7554BHS7Y2H/action/replication_record"}},"created_at":"2026-08-05T00:46:18.012830+00:00","updated_at":"2026-08-05T00:46:18.012830+00:00"}