{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UORQEYFL2QEYK2UO5FVA5V2QC3","short_pith_number":"pith:UORQEYFL","schema_version":"1.0","canonical_sha256":"a3a30260abd409856a8ee96a0ed75016d8c5f750a18050f71b2b020154f930df","source":{"kind":"arxiv","id":"2606.21734","version":1},"attestation_state":"computed","paper":{"title":"HPP: Hierarchical Programmatic Probing for Long Video Understanding by Decoupling Perception and Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ahmed Hasssan, Awais Rauf, Greg Slabaugh","submitted_at":"2026-06-19T20:43:49Z","abstract_excerpt":"Understanding long videos requires fine-grained perception and multi-step, higher-order reasoning over complex, long-range spatio-temporal dynamics. Vision-language models (VLMs) encode video frames into visual tokens and attempt to perform both perception and multi-step planning latently, within a single forward pass. This coupled formulation, however, is bottlenecked by the LLM's limited capacity to discover and execute multi-step strategies in its latent representations. To address this bottleneck, we propose Hierarchical Programmatic Probing (HPP), a framework that decouples semantic perce"},"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":"2606.21734","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-19T20:43:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ee3e52e450c1387a304876b1cec980ea2ba2bb5f5b87d750d81bcebb62019310","abstract_canon_sha256":"7ae355dca585de6e9abe0655de1c6ddab1a16d06a92b36bb6da4adc343183637"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:13:21.036243Z","signature_b64":"n65F+GeyusDW/9nJall9cRusUUvggFQUkipkUSHw6KDnR4Hxe+Bc34bX2bbl21ZoeUp3k2+8F+q010LawoQ/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3a30260abd409856a8ee96a0ed75016d8c5f750a18050f71b2b020154f930df","last_reissued_at":"2026-06-23T01:13:21.035737Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:13:21.035737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HPP: Hierarchical Programmatic Probing for Long Video Understanding by Decoupling Perception and Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ahmed Hasssan, Awais Rauf, Greg Slabaugh","submitted_at":"2026-06-19T20:43:49Z","abstract_excerpt":"Understanding long videos requires fine-grained perception and multi-step, higher-order reasoning over complex, long-range spatio-temporal dynamics. Vision-language models (VLMs) encode video frames into visual tokens and attempt to perform both perception and multi-step planning latently, within a single forward pass. This coupled formulation, however, is bottlenecked by the LLM's limited capacity to discover and execute multi-step strategies in its latent representations. To address this bottleneck, we propose Hierarchical Programmatic Probing (HPP), a framework that decouples semantic perce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21734","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/2606.21734/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":"2606.21734","created_at":"2026-06-23T01:13:21.035805+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21734v1","created_at":"2026-06-23T01:13:21.035805+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21734","created_at":"2026-06-23T01:13:21.035805+00:00"},{"alias_kind":"pith_short_12","alias_value":"UORQEYFL2QEY","created_at":"2026-06-23T01:13:21.035805+00:00"},{"alias_kind":"pith_short_16","alias_value":"UORQEYFL2QEYK2UO","created_at":"2026-06-23T01:13:21.035805+00:00"},{"alias_kind":"pith_short_8","alias_value":"UORQEYFL","created_at":"2026-06-23T01:13:21.035805+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/UORQEYFL2QEYK2UO5FVA5V2QC3","json":"https://pith.science/pith/UORQEYFL2QEYK2UO5FVA5V2QC3.json","graph_json":"https://pith.science/api/pith-number/UORQEYFL2QEYK2UO5FVA5V2QC3/graph.json","events_json":"https://pith.science/api/pith-number/UORQEYFL2QEYK2UO5FVA5V2QC3/events.json","paper":"https://pith.science/paper/UORQEYFL"},"agent_actions":{"view_html":"https://pith.science/pith/UORQEYFL2QEYK2UO5FVA5V2QC3","download_json":"https://pith.science/pith/UORQEYFL2QEYK2UO5FVA5V2QC3.json","view_paper":"https://pith.science/paper/UORQEYFL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21734&json=true","fetch_graph":"https://pith.science/api/pith-number/UORQEYFL2QEYK2UO5FVA5V2QC3/graph.json","fetch_events":"https://pith.science/api/pith-number/UORQEYFL2QEYK2UO5FVA5V2QC3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UORQEYFL2QEYK2UO5FVA5V2QC3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UORQEYFL2QEYK2UO5FVA5V2QC3/action/storage_attestation","attest_author":"https://pith.science/pith/UORQEYFL2QEYK2UO5FVA5V2QC3/action/author_attestation","sign_citation":"https://pith.science/pith/UORQEYFL2QEYK2UO5FVA5V2QC3/action/citation_signature","submit_replication":"https://pith.science/pith/UORQEYFL2QEYK2UO5FVA5V2QC3/action/replication_record"}},"created_at":"2026-06-23T01:13:21.035805+00:00","updated_at":"2026-06-23T01:13:21.035805+00:00"}