{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5UNYSF5SQTBNUOYQX5MVG7YUKV","short_pith_number":"pith:5UNYSF5S","schema_version":"1.0","canonical_sha256":"ed1b8917b284c2da3b10bf59537f145561be9686e70ad035fb1eec9e2edc7bbe","source":{"kind":"arxiv","id":"2605.30750","version":1},"attestation_state":"computed","paper":{"title":"SLAP: The Semantic Least Action Principle for Variational Video-Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Wanlong Fang, Xiang Fang","submitted_at":"2026-05-29T02:28:33Z","abstract_excerpt":"In the era of Large Video-Language Models (LVLMs), the computational necessity of sparse frame sampling creates a fundamental ``temporal gap'', rendering models blind to critical causal transitions. Existing solutions relying on generative hallucination (e.g., latent diffusion) or autoregressive extrapolation often fail to maintain semantic consistency over long horizons, suffering from object vanishing and energetic instability. We propose a paradigm shift from probabilistic generation to variational mechanics with the \\textbf{Semantic Least Action Principle (SLAP)}. Drawing a rigorous isomor"},"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":"2605.30750","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-29T02:28:33Z","cross_cats_sorted":[],"title_canon_sha256":"181246be5d870386ae0f9d78f2d207b793ffa581dc1841ba271d0e84ed5cf8e7","abstract_canon_sha256":"355b3a4e305ae341acf2f7cebce8f3ffeebac3098e3cf1aee1a4488cd5c46a2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:14.147095Z","signature_b64":"y+ybWg72ScGDZfugO4mDSqsptxXocU2NYyXRyqDmCeSTIXiDOOeEqJ/j8N/Scr/RaNNCGeoXvOnF9gjYKmTlAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed1b8917b284c2da3b10bf59537f145561be9686e70ad035fb1eec9e2edc7bbe","last_reissued_at":"2026-06-01T01:03:14.146220Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:14.146220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SLAP: The Semantic Least Action Principle for Variational Video-Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Wanlong Fang, Xiang Fang","submitted_at":"2026-05-29T02:28:33Z","abstract_excerpt":"In the era of Large Video-Language Models (LVLMs), the computational necessity of sparse frame sampling creates a fundamental ``temporal gap'', rendering models blind to critical causal transitions. Existing solutions relying on generative hallucination (e.g., latent diffusion) or autoregressive extrapolation often fail to maintain semantic consistency over long horizons, suffering from object vanishing and energetic instability. We propose a paradigm shift from probabilistic generation to variational mechanics with the \\textbf{Semantic Least Action Principle (SLAP)}. Drawing a rigorous isomor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30750","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/2605.30750/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":"2605.30750","created_at":"2026-06-01T01:03:14.146375+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30750v1","created_at":"2026-06-01T01:03:14.146375+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30750","created_at":"2026-06-01T01:03:14.146375+00:00"},{"alias_kind":"pith_short_12","alias_value":"5UNYSF5SQTBN","created_at":"2026-06-01T01:03:14.146375+00:00"},{"alias_kind":"pith_short_16","alias_value":"5UNYSF5SQTBNUOYQ","created_at":"2026-06-01T01:03:14.146375+00:00"},{"alias_kind":"pith_short_8","alias_value":"5UNYSF5S","created_at":"2026-06-01T01:03:14.146375+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/5UNYSF5SQTBNUOYQX5MVG7YUKV","json":"https://pith.science/pith/5UNYSF5SQTBNUOYQX5MVG7YUKV.json","graph_json":"https://pith.science/api/pith-number/5UNYSF5SQTBNUOYQX5MVG7YUKV/graph.json","events_json":"https://pith.science/api/pith-number/5UNYSF5SQTBNUOYQX5MVG7YUKV/events.json","paper":"https://pith.science/paper/5UNYSF5S"},"agent_actions":{"view_html":"https://pith.science/pith/5UNYSF5SQTBNUOYQX5MVG7YUKV","download_json":"https://pith.science/pith/5UNYSF5SQTBNUOYQX5MVG7YUKV.json","view_paper":"https://pith.science/paper/5UNYSF5S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30750&json=true","fetch_graph":"https://pith.science/api/pith-number/5UNYSF5SQTBNUOYQX5MVG7YUKV/graph.json","fetch_events":"https://pith.science/api/pith-number/5UNYSF5SQTBNUOYQX5MVG7YUKV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5UNYSF5SQTBNUOYQX5MVG7YUKV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5UNYSF5SQTBNUOYQX5MVG7YUKV/action/storage_attestation","attest_author":"https://pith.science/pith/5UNYSF5SQTBNUOYQX5MVG7YUKV/action/author_attestation","sign_citation":"https://pith.science/pith/5UNYSF5SQTBNUOYQX5MVG7YUKV/action/citation_signature","submit_replication":"https://pith.science/pith/5UNYSF5SQTBNUOYQX5MVG7YUKV/action/replication_record"}},"created_at":"2026-06-01T01:03:14.146375+00:00","updated_at":"2026-06-01T01:03:14.146375+00:00"}