{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AZ3YUCT6TA3U46YYJHJE5TAS7B","short_pith_number":"pith:AZ3YUCT6","schema_version":"1.0","canonical_sha256":"06778a0a7e98374e7b1849d24ecc12f8774ab88fa3bb39a1129b8cd2ee34ab94","source":{"kind":"arxiv","id":"2501.01548","version":1},"attestation_state":"computed","paper":{"title":"Task-Driven Fixation Network: An Efficient Architecture with Fixation Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shuguang Wang, Yuanjing Wang","submitted_at":"2025-01-02T21:38:10Z","abstract_excerpt":"This paper presents a novel neural network architecture featuring automatic fixation point selection, designed to efficiently address complex tasks with reduced network size and computational overhead. The proposed model consists of: a low-resolution channel that captures low-resolution global features from input images; a high-resolution channel that sequentially extracts localized high-resolution features; and a hybrid encoding module that integrates the features from both channels. A defining characteristic of the hybrid encoding module is the inclusion of a fixation point generator, which "},"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":"2501.01548","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-02T21:38:10Z","cross_cats_sorted":[],"title_canon_sha256":"9c86bb68d5d9510830b18c117b858ec47a2f3f844bb16b578438706af84a1ae8","abstract_canon_sha256":"7e36a24322e194a0ee4878b8322240dfe297b64995a1c5419d5e7c454f528079"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:26.550892Z","signature_b64":"Tz9mnmOqCpUNVn5BXcDJZLQA0dekvgWmlZ+UGqS8GSK1ZVB9NuvgYnkrB3Tn7wYSZgKDTdfb2pyQjM/WT4o3Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06778a0a7e98374e7b1849d24ecc12f8774ab88fa3bb39a1129b8cd2ee34ab94","last_reissued_at":"2026-07-05T09:56:26.550443Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:26.550443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Task-Driven Fixation Network: An Efficient Architecture with Fixation Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shuguang Wang, Yuanjing Wang","submitted_at":"2025-01-02T21:38:10Z","abstract_excerpt":"This paper presents a novel neural network architecture featuring automatic fixation point selection, designed to efficiently address complex tasks with reduced network size and computational overhead. The proposed model consists of: a low-resolution channel that captures low-resolution global features from input images; a high-resolution channel that sequentially extracts localized high-resolution features; and a hybrid encoding module that integrates the features from both channels. A defining characteristic of the hybrid encoding module is the inclusion of a fixation point generator, which "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01548","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/2501.01548/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":"2501.01548","created_at":"2026-07-05T09:56:26.550503+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.01548v1","created_at":"2026-07-05T09:56:26.550503+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01548","created_at":"2026-07-05T09:56:26.550503+00:00"},{"alias_kind":"pith_short_12","alias_value":"AZ3YUCT6TA3U","created_at":"2026-07-05T09:56:26.550503+00:00"},{"alias_kind":"pith_short_16","alias_value":"AZ3YUCT6TA3U46YY","created_at":"2026-07-05T09:56:26.550503+00:00"},{"alias_kind":"pith_short_8","alias_value":"AZ3YUCT6","created_at":"2026-07-05T09:56:26.550503+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.15603","citing_title":"Advancing TDFN: Precise Fixation Point Generation Using Reconstruction Differences","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AZ3YUCT6TA3U46YYJHJE5TAS7B","json":"https://pith.science/pith/AZ3YUCT6TA3U46YYJHJE5TAS7B.json","graph_json":"https://pith.science/api/pith-number/AZ3YUCT6TA3U46YYJHJE5TAS7B/graph.json","events_json":"https://pith.science/api/pith-number/AZ3YUCT6TA3U46YYJHJE5TAS7B/events.json","paper":"https://pith.science/paper/AZ3YUCT6"},"agent_actions":{"view_html":"https://pith.science/pith/AZ3YUCT6TA3U46YYJHJE5TAS7B","download_json":"https://pith.science/pith/AZ3YUCT6TA3U46YYJHJE5TAS7B.json","view_paper":"https://pith.science/paper/AZ3YUCT6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.01548&json=true","fetch_graph":"https://pith.science/api/pith-number/AZ3YUCT6TA3U46YYJHJE5TAS7B/graph.json","fetch_events":"https://pith.science/api/pith-number/AZ3YUCT6TA3U46YYJHJE5TAS7B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AZ3YUCT6TA3U46YYJHJE5TAS7B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AZ3YUCT6TA3U46YYJHJE5TAS7B/action/storage_attestation","attest_author":"https://pith.science/pith/AZ3YUCT6TA3U46YYJHJE5TAS7B/action/author_attestation","sign_citation":"https://pith.science/pith/AZ3YUCT6TA3U46YYJHJE5TAS7B/action/citation_signature","submit_replication":"https://pith.science/pith/AZ3YUCT6TA3U46YYJHJE5TAS7B/action/replication_record"}},"created_at":"2026-07-05T09:56:26.550503+00:00","updated_at":"2026-07-05T09:56:26.550503+00:00"}