{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NDW3BPMEKETEPEJABPWT2MDIQR","short_pith_number":"pith:NDW3BPME","schema_version":"1.0","canonical_sha256":"68edb0bd8451264791200bed3d3068845033b2555798140d1ac6c2a8761e173e","source":{"kind":"arxiv","id":"2506.00770","version":1},"attestation_state":"computed","paper":{"title":"Beyond Attention: Learning Spatio-Temporal Dynamics with Emergent Interpretable Topologies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SI"],"primary_cat":"cs.LG","authors_text":"Sai Vamsi Alisetti, Sanjukta Krishnagopal, Vikas Kalagi","submitted_at":"2025-06-01T01:27:32Z","abstract_excerpt":"Spatio-temporal forecasting is critical in applications such as traffic prediction, energy demand modeling, and weather monitoring. While Graph Attention Networks (GATs) are popular for modeling spatial dependencies, they rely on predefined adjacency structures and dynamic attention scores, introducing inductive biases and computational overhead that can obscure interpretability.\n  We propose InterGAT, a simplified alternative to GAT that replaces masked attention with a fully learnable, symmetric node interaction matrix, capturing latent spatial relationships without relying on fixed graph to"},"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":"2506.00770","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-01T01:27:32Z","cross_cats_sorted":["cs.AI","cs.SI"],"title_canon_sha256":"816793f3567ac17d342e9b4930e61c5f032ee891be9bb10c1d8dd38173280282","abstract_canon_sha256":"0062c70b1e080635c80a7846e408f55926faf945d0eaf72ef56b60a86e446087"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:40.219858Z","signature_b64":"SGNqsAkiqI+loDMC2HFvUgpYEkLZCOG/lXe9q6NdnpN0YiTi665+ZW/DLGN5rOdUKjgAxNryySlGVpMgFMnwAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68edb0bd8451264791200bed3d3068845033b2555798140d1ac6c2a8761e173e","last_reissued_at":"2026-07-05T11:13:40.219215Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:40.219215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Attention: Learning Spatio-Temporal Dynamics with Emergent Interpretable Topologies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SI"],"primary_cat":"cs.LG","authors_text":"Sai Vamsi Alisetti, Sanjukta Krishnagopal, Vikas Kalagi","submitted_at":"2025-06-01T01:27:32Z","abstract_excerpt":"Spatio-temporal forecasting is critical in applications such as traffic prediction, energy demand modeling, and weather monitoring. While Graph Attention Networks (GATs) are popular for modeling spatial dependencies, they rely on predefined adjacency structures and dynamic attention scores, introducing inductive biases and computational overhead that can obscure interpretability.\n  We propose InterGAT, a simplified alternative to GAT that replaces masked attention with a fully learnable, symmetric node interaction matrix, capturing latent spatial relationships without relying on fixed graph to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00770","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/2506.00770/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":"2506.00770","created_at":"2026-07-05T11:13:40.219291+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00770v1","created_at":"2026-07-05T11:13:40.219291+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00770","created_at":"2026-07-05T11:13:40.219291+00:00"},{"alias_kind":"pith_short_12","alias_value":"NDW3BPMEKETE","created_at":"2026-07-05T11:13:40.219291+00:00"},{"alias_kind":"pith_short_16","alias_value":"NDW3BPMEKETEPEJA","created_at":"2026-07-05T11:13:40.219291+00:00"},{"alias_kind":"pith_short_8","alias_value":"NDW3BPME","created_at":"2026-07-05T11:13:40.219291+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/NDW3BPMEKETEPEJABPWT2MDIQR","json":"https://pith.science/pith/NDW3BPMEKETEPEJABPWT2MDIQR.json","graph_json":"https://pith.science/api/pith-number/NDW3BPMEKETEPEJABPWT2MDIQR/graph.json","events_json":"https://pith.science/api/pith-number/NDW3BPMEKETEPEJABPWT2MDIQR/events.json","paper":"https://pith.science/paper/NDW3BPME"},"agent_actions":{"view_html":"https://pith.science/pith/NDW3BPMEKETEPEJABPWT2MDIQR","download_json":"https://pith.science/pith/NDW3BPMEKETEPEJABPWT2MDIQR.json","view_paper":"https://pith.science/paper/NDW3BPME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00770&json=true","fetch_graph":"https://pith.science/api/pith-number/NDW3BPMEKETEPEJABPWT2MDIQR/graph.json","fetch_events":"https://pith.science/api/pith-number/NDW3BPMEKETEPEJABPWT2MDIQR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NDW3BPMEKETEPEJABPWT2MDIQR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NDW3BPMEKETEPEJABPWT2MDIQR/action/storage_attestation","attest_author":"https://pith.science/pith/NDW3BPMEKETEPEJABPWT2MDIQR/action/author_attestation","sign_citation":"https://pith.science/pith/NDW3BPMEKETEPEJABPWT2MDIQR/action/citation_signature","submit_replication":"https://pith.science/pith/NDW3BPMEKETEPEJABPWT2MDIQR/action/replication_record"}},"created_at":"2026-07-05T11:13:40.219291+00:00","updated_at":"2026-07-05T11:13:40.219291+00:00"}