{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XB4ODC6LCCXK5G3VKJTJK2NWSG","short_pith_number":"pith:XB4ODC6L","canonical_record":{"source":{"id":"2408.13963","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-25T23:57:07Z","cross_cats_sorted":[],"title_canon_sha256":"5c6bcc28ee265ff4cb1792b5372d2a087a2bb43100a26754a5997507c76c9f16","abstract_canon_sha256":"beb43aed51033ce854582e00851e4a89e4c11e70c8a65bb61d8ccb4ba1c360c6"},"schema_version":"1.0"},"canonical_sha256":"b878e18bcb10aeae9b7552669569b691abbf9a1d8a7a4a7f7265a416f6ea0c94","source":{"kind":"arxiv","id":"2408.13963","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.13963","created_at":"2026-07-05T08:59:14Z"},{"alias_kind":"arxiv_version","alias_value":"2408.13963v1","created_at":"2026-07-05T08:59:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.13963","created_at":"2026-07-05T08:59:14Z"},{"alias_kind":"pith_short_12","alias_value":"XB4ODC6LCCXK","created_at":"2026-07-05T08:59:14Z"},{"alias_kind":"pith_short_16","alias_value":"XB4ODC6LCCXK5G3V","created_at":"2026-07-05T08:59:14Z"},{"alias_kind":"pith_short_8","alias_value":"XB4ODC6L","created_at":"2026-07-05T08:59:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XB4ODC6LCCXK5G3VKJTJK2NWSG","target":"record","payload":{"canonical_record":{"source":{"id":"2408.13963","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-25T23:57:07Z","cross_cats_sorted":[],"title_canon_sha256":"5c6bcc28ee265ff4cb1792b5372d2a087a2bb43100a26754a5997507c76c9f16","abstract_canon_sha256":"beb43aed51033ce854582e00851e4a89e4c11e70c8a65bb61d8ccb4ba1c360c6"},"schema_version":"1.0"},"canonical_sha256":"b878e18bcb10aeae9b7552669569b691abbf9a1d8a7a4a7f7265a416f6ea0c94","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:14.170804Z","signature_b64":"VFLJ392IyGykBgIGe3vbKErHwJk7g8uFbzLQeVJnGLKg0Wm/8/3gGOFncz4IuVkHsZxJ+utO7UfmV/JcHQLfBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b878e18bcb10aeae9b7552669569b691abbf9a1d8a7a4a7f7265a416f6ea0c94","last_reissued_at":"2026-07-05T08:59:14.170301Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:14.170301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.13963","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":"2026-07-05T08:59:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qdCVQA1E1lZOt3ge/YdWZv/a4iy9bqcDX9axjVO8fEL0J/44ZYNVrxrN4h3TvNyOc+P9Q3ZmYlOSA2HqmgLNBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:53:13.961199Z"},"content_sha256":"536d165bf34c5484becbd378a997429332365e2d3e8d9471f1df146c0e0b2e2b","schema_version":"1.0","event_id":"sha256:536d165bf34c5484becbd378a997429332365e2d3e8d9471f1df146c0e0b2e2b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XB4ODC6LCCXK5G3VKJTJK2NWSG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Shifted Window Fourier Transform And Retention For Image Captioning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alessandro Capotondi, Jia Cheng Hu, Roberto Cavicchioli","submitted_at":"2024-08-25T23:57:07Z","abstract_excerpt":"Image Captioning is an important Language and Vision task that finds application in a variety of contexts, ranging from healthcare to autonomous vehicles. As many real-world applications rely on devices with limited resources, much effort in the field was put into the development of lighter and faster models. However, much of the current optimizations focus on the Transformer architecture in contrast to the existence of more efficient methods. In this work, we introduce SwiFTeR, an architecture almost entirely based on Fourier Transform and Retention, to tackle the main efficiency bottlenecks "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.13963","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/2408.13963/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:59:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2ee17m/6rw7M3vb13x7OngFQNCTRab1cbfZo4XMBvNfE80GOF0mhjbk2rI9rQupiPRhNGwLIs2et/GLU3jdbAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:53:13.962069Z"},"content_sha256":"15bfc4a18ecc79d615b5f6582db937cf82412bb4b4855a8cab9cf75abc7a13aa","schema_version":"1.0","event_id":"sha256:15bfc4a18ecc79d615b5f6582db937cf82412bb4b4855a8cab9cf75abc7a13aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XB4ODC6LCCXK5G3VKJTJK2NWSG/bundle.json","state_url":"https://pith.science/pith/XB4ODC6LCCXK5G3VKJTJK2NWSG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XB4ODC6LCCXK5G3VKJTJK2NWSG/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":"2026-08-09T07:53:13Z","links":{"resolver":"https://pith.science/pith/XB4ODC6LCCXK5G3VKJTJK2NWSG","bundle":"https://pith.science/pith/XB4ODC6LCCXK5G3VKJTJK2NWSG/bundle.json","state":"https://pith.science/pith/XB4ODC6LCCXK5G3VKJTJK2NWSG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XB4ODC6LCCXK5G3VKJTJK2NWSG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XB4ODC6LCCXK5G3VKJTJK2NWSG","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":"beb43aed51033ce854582e00851e4a89e4c11e70c8a65bb61d8ccb4ba1c360c6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-25T23:57:07Z","title_canon_sha256":"5c6bcc28ee265ff4cb1792b5372d2a087a2bb43100a26754a5997507c76c9f16"},"schema_version":"1.0","source":{"id":"2408.13963","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.13963","created_at":"2026-07-05T08:59:14Z"},{"alias_kind":"arxiv_version","alias_value":"2408.13963v1","created_at":"2026-07-05T08:59:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.13963","created_at":"2026-07-05T08:59:14Z"},{"alias_kind":"pith_short_12","alias_value":"XB4ODC6LCCXK","created_at":"2026-07-05T08:59:14Z"},{"alias_kind":"pith_short_16","alias_value":"XB4ODC6LCCXK5G3V","created_at":"2026-07-05T08:59:14Z"},{"alias_kind":"pith_short_8","alias_value":"XB4ODC6L","created_at":"2026-07-05T08:59:14Z"}],"graph_snapshots":[{"event_id":"sha256:15bfc4a18ecc79d615b5f6582db937cf82412bb4b4855a8cab9cf75abc7a13aa","target":"graph","created_at":"2026-07-05T08:59:14Z","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":[],"endpoint":"/pith/2408.13963/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image Captioning is an important Language and Vision task that finds application in a variety of contexts, ranging from healthcare to autonomous vehicles. As many real-world applications rely on devices with limited resources, much effort in the field was put into the development of lighter and faster models. However, much of the current optimizations focus on the Transformer architecture in contrast to the existence of more efficient methods. In this work, we introduce SwiFTeR, an architecture almost entirely based on Fourier Transform and Retention, to tackle the main efficiency bottlenecks ","authors_text":"Alessandro Capotondi, Jia Cheng Hu, Roberto Cavicchioli","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-25T23:57:07Z","title":"Shifted Window Fourier Transform And Retention For Image Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.13963","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":"sha256:536d165bf34c5484becbd378a997429332365e2d3e8d9471f1df146c0e0b2e2b","target":"record","created_at":"2026-07-05T08:59:14Z","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":"beb43aed51033ce854582e00851e4a89e4c11e70c8a65bb61d8ccb4ba1c360c6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-25T23:57:07Z","title_canon_sha256":"5c6bcc28ee265ff4cb1792b5372d2a087a2bb43100a26754a5997507c76c9f16"},"schema_version":"1.0","source":{"id":"2408.13963","kind":"arxiv","version":1}},"canonical_sha256":"b878e18bcb10aeae9b7552669569b691abbf9a1d8a7a4a7f7265a416f6ea0c94","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b878e18bcb10aeae9b7552669569b691abbf9a1d8a7a4a7f7265a416f6ea0c94","first_computed_at":"2026-07-05T08:59:14.170301Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:59:14.170301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VFLJ392IyGykBgIGe3vbKErHwJk7g8uFbzLQeVJnGLKg0Wm/8/3gGOFncz4IuVkHsZxJ+utO7UfmV/JcHQLfBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:59:14.170804Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.13963","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:536d165bf34c5484becbd378a997429332365e2d3e8d9471f1df146c0e0b2e2b","sha256:15bfc4a18ecc79d615b5f6582db937cf82412bb4b4855a8cab9cf75abc7a13aa"],"state_sha256":"d5bc82a5e1bc80a40096dd3e47bcd656471ea2a4a1dbb3a7cde607b71496ec72"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GPtz01Zg5Lmxdf8QgPDqZqyU4WVXY+sxmRdmrKkcaieJddPgQwtn6zetbP0ZUlYQdxC82Bn2Az+WGYcnm1z0BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T07:53:13.967397Z","bundle_sha256":"15811feefc291073c941d31f13873b914dd68b809094898b256371cc5dbc9f41"}}