{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7WI2AVBPUYHGU7Y6BPQKEKFB5L","short_pith_number":"pith:7WI2AVBP","schema_version":"1.0","canonical_sha256":"fd91a0542fa60e6a7f1e0be0a228a1eac7b313f102cfd160eb77459ede6736f4","source":{"kind":"arxiv","id":"2403.18063","version":2},"attestation_state":"computed","paper":{"title":"Heracles: A Hybrid SSM-Transformer Model for High-Resolution Image and Time-Series Analysis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Badri N. Patro, Suhas Ranganath, Vijay S. Agneeswaran, Vinay P. Namboodiri","submitted_at":"2024-03-26T19:29:21Z","abstract_excerpt":"Transformers have revolutionized image modeling tasks with adaptations like DeIT, Swin, SVT, Biformer, STVit, and FDVIT. However, these models often face challenges with inductive bias and high quadratic complexity, making them less efficient for high-resolution images. State space models (SSMs) such as Mamba, V-Mamba, ViM, and SiMBA offer an alternative to handle high resolution images in computer vision tasks. These SSMs encounter two major issues. First, they become unstable when scaled to large network sizes. Second, although they efficiently capture global information in images, they inhe"},"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":"2403.18063","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-26T19:29:21Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.MM"],"title_canon_sha256":"a78f10888f6f5420fc61da701708ecaee2ae9cf92c2fff6552a3ee056ee154a0","abstract_canon_sha256":"8b3fc56a5d48f4bde57b5ff5bb1b62d8251fd7f728ecc7696c09b1a132ca2fcc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:43.920252Z","signature_b64":"aKz95O8P1nQq9jXM+5xQkT+0RoKozh3wn0xMn3pPlVDra8BOIzIa7+wyZdS7feWRwPsXUC8kYlZr2sqrjv4LAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd91a0542fa60e6a7f1e0be0a228a1eac7b313f102cfd160eb77459ede6736f4","last_reissued_at":"2026-07-05T08:26:43.919771Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:43.919771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Heracles: A Hybrid SSM-Transformer Model for High-Resolution Image and Time-Series Analysis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Badri N. Patro, Suhas Ranganath, Vijay S. Agneeswaran, Vinay P. Namboodiri","submitted_at":"2024-03-26T19:29:21Z","abstract_excerpt":"Transformers have revolutionized image modeling tasks with adaptations like DeIT, Swin, SVT, Biformer, STVit, and FDVIT. However, these models often face challenges with inductive bias and high quadratic complexity, making them less efficient for high-resolution images. State space models (SSMs) such as Mamba, V-Mamba, ViM, and SiMBA offer an alternative to handle high resolution images in computer vision tasks. These SSMs encounter two major issues. First, they become unstable when scaled to large network sizes. Second, although they efficiently capture global information in images, they inhe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.18063","kind":"arxiv","version":2},"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/2403.18063/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":"2403.18063","created_at":"2026-07-05T08:26:43.919828+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.18063v2","created_at":"2026-07-05T08:26:43.919828+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.18063","created_at":"2026-07-05T08:26:43.919828+00:00"},{"alias_kind":"pith_short_12","alias_value":"7WI2AVBPUYHG","created_at":"2026-07-05T08:26:43.919828+00:00"},{"alias_kind":"pith_short_16","alias_value":"7WI2AVBPUYHGU7Y6","created_at":"2026-07-05T08:26:43.919828+00:00"},{"alias_kind":"pith_short_8","alias_value":"7WI2AVBP","created_at":"2026-07-05T08:26:43.919828+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14724","citing_title":"HAMSA: Scanning-Free Vision State Space Models via SpectralPulseNet","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7WI2AVBPUYHGU7Y6BPQKEKFB5L","json":"https://pith.science/pith/7WI2AVBPUYHGU7Y6BPQKEKFB5L.json","graph_json":"https://pith.science/api/pith-number/7WI2AVBPUYHGU7Y6BPQKEKFB5L/graph.json","events_json":"https://pith.science/api/pith-number/7WI2AVBPUYHGU7Y6BPQKEKFB5L/events.json","paper":"https://pith.science/paper/7WI2AVBP"},"agent_actions":{"view_html":"https://pith.science/pith/7WI2AVBPUYHGU7Y6BPQKEKFB5L","download_json":"https://pith.science/pith/7WI2AVBPUYHGU7Y6BPQKEKFB5L.json","view_paper":"https://pith.science/paper/7WI2AVBP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.18063&json=true","fetch_graph":"https://pith.science/api/pith-number/7WI2AVBPUYHGU7Y6BPQKEKFB5L/graph.json","fetch_events":"https://pith.science/api/pith-number/7WI2AVBPUYHGU7Y6BPQKEKFB5L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7WI2AVBPUYHGU7Y6BPQKEKFB5L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7WI2AVBPUYHGU7Y6BPQKEKFB5L/action/storage_attestation","attest_author":"https://pith.science/pith/7WI2AVBPUYHGU7Y6BPQKEKFB5L/action/author_attestation","sign_citation":"https://pith.science/pith/7WI2AVBPUYHGU7Y6BPQKEKFB5L/action/citation_signature","submit_replication":"https://pith.science/pith/7WI2AVBPUYHGU7Y6BPQKEKFB5L/action/replication_record"}},"created_at":"2026-07-05T08:26:43.919828+00:00","updated_at":"2026-07-05T08:26:43.919828+00:00"}