{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JI5HTFUHXZSBTJ4X4AOZ62GFGM","short_pith_number":"pith:JI5HTFUH","schema_version":"1.0","canonical_sha256":"4a3a799687be6419a797e01d9f68c53326db267ad267cdd51db61e1e400771f2","source":{"kind":"arxiv","id":"2605.22678","version":1},"attestation_state":"computed","paper":{"title":"Swift Sampling: Selecting Temporal Surprises via Taylor Series","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bhuvan Sachdeva, Dahye Kim, Deepti Ghadiyaram, Karan Uppal, Naman Gupta, Vineeth N. Balasubramanian","submitted_at":"2026-05-21T16:20:31Z","abstract_excerpt":"While most frames in long-form video are redundant, the critical information resides in temporal surprises: moments where the actual visual features deviate from their predicted evolution. Inspired by the human brain's predictive coding, we introduce Swift Sampling, an elegant, training-free frame selection algorithm that automatically identifies high-information moments in a video. Specifically, we model a video as a differentiable trajectory in the visual latent space and compute the velocity and acceleration of its features. Then, we apply Taylor expansion to project the expected path of su"},"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":"2605.22678","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-21T16:20:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"37d4a6831d8a145f644c702014c9769c2f9eaf8c9c91a133a9cb5acea325f017","abstract_canon_sha256":"d7a5df1259b9cffc222b5c5b38b412446ee3b15244821b7e6531516273d86fcb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T02:04:49.816735Z","signature_b64":"luSHEdafUtTdcar9LX++fWaEHeDUh2THwzsfKfIzI6VfTFsCq3MtH44nqvmDiTJthBe0Bzh92YybFNlhCca6AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a3a799687be6419a797e01d9f68c53326db267ad267cdd51db61e1e400771f2","last_reissued_at":"2026-05-22T02:04:49.815927Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T02:04:49.815927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Swift Sampling: Selecting Temporal Surprises via Taylor Series","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bhuvan Sachdeva, Dahye Kim, Deepti Ghadiyaram, Karan Uppal, Naman Gupta, Vineeth N. Balasubramanian","submitted_at":"2026-05-21T16:20:31Z","abstract_excerpt":"While most frames in long-form video are redundant, the critical information resides in temporal surprises: moments where the actual visual features deviate from their predicted evolution. Inspired by the human brain's predictive coding, we introduce Swift Sampling, an elegant, training-free frame selection algorithm that automatically identifies high-information moments in a video. Specifically, we model a video as a differentiable trajectory in the visual latent space and compute the velocity and acceleration of its features. Then, we apply Taylor expansion to project the expected path of su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22678","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/2605.22678/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":"2605.22678","created_at":"2026-05-22T02:04:49.816054+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.22678v1","created_at":"2026-05-22T02:04:49.816054+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22678","created_at":"2026-05-22T02:04:49.816054+00:00"},{"alias_kind":"pith_short_12","alias_value":"JI5HTFUHXZSB","created_at":"2026-05-22T02:04:49.816054+00:00"},{"alias_kind":"pith_short_16","alias_value":"JI5HTFUHXZSBTJ4X","created_at":"2026-05-22T02:04:49.816054+00:00"},{"alias_kind":"pith_short_8","alias_value":"JI5HTFUH","created_at":"2026-05-22T02:04:49.816054+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/JI5HTFUHXZSBTJ4X4AOZ62GFGM","json":"https://pith.science/pith/JI5HTFUHXZSBTJ4X4AOZ62GFGM.json","graph_json":"https://pith.science/api/pith-number/JI5HTFUHXZSBTJ4X4AOZ62GFGM/graph.json","events_json":"https://pith.science/api/pith-number/JI5HTFUHXZSBTJ4X4AOZ62GFGM/events.json","paper":"https://pith.science/paper/JI5HTFUH"},"agent_actions":{"view_html":"https://pith.science/pith/JI5HTFUHXZSBTJ4X4AOZ62GFGM","download_json":"https://pith.science/pith/JI5HTFUHXZSBTJ4X4AOZ62GFGM.json","view_paper":"https://pith.science/paper/JI5HTFUH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.22678&json=true","fetch_graph":"https://pith.science/api/pith-number/JI5HTFUHXZSBTJ4X4AOZ62GFGM/graph.json","fetch_events":"https://pith.science/api/pith-number/JI5HTFUHXZSBTJ4X4AOZ62GFGM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JI5HTFUHXZSBTJ4X4AOZ62GFGM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JI5HTFUHXZSBTJ4X4AOZ62GFGM/action/storage_attestation","attest_author":"https://pith.science/pith/JI5HTFUHXZSBTJ4X4AOZ62GFGM/action/author_attestation","sign_citation":"https://pith.science/pith/JI5HTFUHXZSBTJ4X4AOZ62GFGM/action/citation_signature","submit_replication":"https://pith.science/pith/JI5HTFUHXZSBTJ4X4AOZ62GFGM/action/replication_record"}},"created_at":"2026-05-22T02:04:49.816054+00:00","updated_at":"2026-05-22T02:04:49.816054+00:00"}